Commit
·
9f6787b
verified
·
0
Parent(s):
Duplicate from babs/vlfm-v3-3B
Browse filesCo-authored-by: Temi <[email protected]>
- .gitattributes +36 -0
- README.md +1 -0
- chat_template.jinja +93 -0
- config.json +220 -0
- configs.py +96 -0
- configuration_vlfm.py +96 -0
- model-00001-of-00005.safetensors +3 -0
- model-00002-of-00005.safetensors +3 -0
- model-00003-of-00005.safetensors +3 -0
- model-00004-of-00005.safetensors +3 -0
- model-00005-of-00005.safetensors +3 -0
- model.py +296 -0
- model.safetensors.index.json +753 -0
- modeling_vlfm.py +296 -0
- preprocessor_config.json +18 -0
- processing_vlfm.py +199 -0
- processor.py +199 -0
- processor_config.json +6 -0
- special_tokens_map.json +26 -0
- tokenizer.json +3 -0
- tokenizer_config.json +2078 -0
.gitattributes
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
# VLFM Model: Custom audio+text model with tokenizer (expanded with <|audio|>), Whisper feature extractor, and processor.
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{{- bos_token }}
|
| 2 |
+
{%- if custom_tools is defined %}
|
| 3 |
+
{%- set tools = custom_tools %}
|
| 4 |
+
{%- endif %}
|
| 5 |
+
{%- if not tools_in_user_message is defined %}
|
| 6 |
+
{%- set tools_in_user_message = true %}
|
| 7 |
+
{%- endif %}
|
| 8 |
+
{%- if not date_string is defined %}
|
| 9 |
+
{%- if strftime_now is defined %}
|
| 10 |
+
{%- set date_string = strftime_now("%d %b %Y") %}
|
| 11 |
+
{%- else %}
|
| 12 |
+
{%- set date_string = "26 Jul 2024" %}
|
| 13 |
+
{%- endif %}
|
| 14 |
+
{%- endif %}
|
| 15 |
+
{%- if not tools is defined %}
|
| 16 |
+
{%- set tools = none %}
|
| 17 |
+
{%- endif %}
|
| 18 |
+
|
| 19 |
+
{#- This block extracts the system message, so we can slot it into the right place. #}
|
| 20 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 21 |
+
{%- set system_message = messages[0]['content']|trim %}
|
| 22 |
+
{%- set messages = messages[1:] %}
|
| 23 |
+
{%- else %}
|
| 24 |
+
{%- set system_message = "" %}
|
| 25 |
+
{%- endif %}
|
| 26 |
+
|
| 27 |
+
{#- System message #}
|
| 28 |
+
{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
|
| 29 |
+
{%- if tools is not none %}
|
| 30 |
+
{{- "Environment: ipython\n" }}
|
| 31 |
+
{%- endif %}
|
| 32 |
+
{{- "Cutting Knowledge Date: December 2023\n" }}
|
| 33 |
+
{{- "Today Date: " + date_string + "\n\n" }}
|
| 34 |
+
{%- if tools is not none and not tools_in_user_message %}
|
| 35 |
+
{{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
|
| 36 |
+
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
|
| 37 |
+
{{- "Do not use variables.\n\n" }}
|
| 38 |
+
{%- for t in tools %}
|
| 39 |
+
{{- t | tojson(indent=4) }}
|
| 40 |
+
{{- "\n\n" }}
|
| 41 |
+
{%- endfor %}
|
| 42 |
+
{%- endif %}
|
| 43 |
+
{{- system_message }}
|
| 44 |
+
{{- "<|eot_id|>" }}
|
| 45 |
+
|
| 46 |
+
{#- Custom tools are passed in a user message with some extra guidance #}
|
| 47 |
+
{%- if tools_in_user_message and not tools is none %}
|
| 48 |
+
{#- Extract the first user message so we can plug it in here #}
|
| 49 |
+
{%- if messages | length != 0 %}
|
| 50 |
+
{%- set first_user_message = messages[0]['content']|trim %}
|
| 51 |
+
{%- set messages = messages[1:] %}
|
| 52 |
+
{%- else %}
|
| 53 |
+
{{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
|
| 54 |
+
{%- endif %}
|
| 55 |
+
{{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
|
| 56 |
+
{{- "Given the following functions, please respond with a JSON for a function call " }}
|
| 57 |
+
{{- "with its proper arguments that best answers the given prompt.\n\n" }}
|
| 58 |
+
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
|
| 59 |
+
{{- "Do not use variables.\n\n" }}
|
| 60 |
+
{%- for t in tools %}
|
| 61 |
+
{{- t | tojson(indent=4) }}
|
| 62 |
+
{{- "\n\n" }}
|
| 63 |
+
{%- endfor %}
|
| 64 |
+
{{- first_user_message + "<|eot_id|>"}}
|
| 65 |
+
{%- endif %}
|
| 66 |
+
|
| 67 |
+
{%- for message in messages %}
|
| 68 |
+
{%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
|
| 69 |
+
{{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
|
| 70 |
+
{%- elif 'tool_calls' in message %}
|
| 71 |
+
{%- if not message.tool_calls|length == 1 %}
|
| 72 |
+
{{- raise_exception("This model only supports single tool-calls at once!") }}
|
| 73 |
+
{%- endif %}
|
| 74 |
+
{%- set tool_call = message.tool_calls[0].function %}
|
| 75 |
+
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
|
| 76 |
+
{{- '{"name": "' + tool_call.name + '", ' }}
|
| 77 |
+
{{- '"parameters": ' }}
|
| 78 |
+
{{- tool_call.arguments | tojson }}
|
| 79 |
+
{{- "}" }}
|
| 80 |
+
{{- "<|eot_id|>" }}
|
| 81 |
+
{%- elif message.role == "tool" or message.role == "ipython" %}
|
| 82 |
+
{{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
|
| 83 |
+
{%- if message.content is mapping or message.content is iterable %}
|
| 84 |
+
{{- message.content | tojson }}
|
| 85 |
+
{%- else %}
|
| 86 |
+
{{- message.content }}
|
| 87 |
+
{%- endif %}
|
| 88 |
+
{{- "<|eot_id|>" }}
|
| 89 |
+
{%- endif %}
|
| 90 |
+
{%- endfor %}
|
| 91 |
+
{%- if add_generation_prompt %}
|
| 92 |
+
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
|
| 93 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,220 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"VLFMModel"
|
| 4 |
+
],
|
| 5 |
+
"audio_config": {
|
| 6 |
+
"_name_or_path": "openai/whisper-large-v3",
|
| 7 |
+
"activation_dropout": 0.0,
|
| 8 |
+
"activation_function": "gelu",
|
| 9 |
+
"add_cross_attention": false,
|
| 10 |
+
"apply_spec_augment": false,
|
| 11 |
+
"architectures": [
|
| 12 |
+
"WhisperForConditionalGeneration"
|
| 13 |
+
],
|
| 14 |
+
"attention_dropout": 0.0,
|
| 15 |
+
"bad_words_ids": null,
|
| 16 |
+
"begin_suppress_tokens": [
|
| 17 |
+
220,
|
| 18 |
+
50257
|
| 19 |
+
],
|
| 20 |
+
"bos_token_id": 50257,
|
| 21 |
+
"chunk_size_feed_forward": 0,
|
| 22 |
+
"classifier_proj_size": 256,
|
| 23 |
+
"cross_attention_hidden_size": null,
|
| 24 |
+
"d_model": 1280,
|
| 25 |
+
"decoder_attention_heads": 20,
|
| 26 |
+
"decoder_ffn_dim": 5120,
|
| 27 |
+
"decoder_layerdrop": 0.0,
|
| 28 |
+
"decoder_layers": 32,
|
| 29 |
+
"decoder_start_token_id": 50258,
|
| 30 |
+
"diversity_penalty": 0.0,
|
| 31 |
+
"do_sample": false,
|
| 32 |
+
"dropout": 0.0,
|
| 33 |
+
"dtype": "float16",
|
| 34 |
+
"early_stopping": false,
|
| 35 |
+
"encoder_attention_heads": 20,
|
| 36 |
+
"encoder_ffn_dim": 5120,
|
| 37 |
+
"encoder_layerdrop": 0.0,
|
| 38 |
+
"encoder_layers": 32,
|
| 39 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 40 |
+
"eos_token_id": 50257,
|
| 41 |
+
"exponential_decay_length_penalty": null,
|
| 42 |
+
"finetuning_task": null,
|
| 43 |
+
"forced_bos_token_id": null,
|
| 44 |
+
"forced_eos_token_id": null,
|
| 45 |
+
"id2label": {
|
| 46 |
+
"0": "LABEL_0",
|
| 47 |
+
"1": "LABEL_1"
|
| 48 |
+
},
|
| 49 |
+
"init_std": 0.02,
|
| 50 |
+
"is_decoder": false,
|
| 51 |
+
"is_encoder_decoder": true,
|
| 52 |
+
"label2id": {
|
| 53 |
+
"LABEL_0": 0,
|
| 54 |
+
"LABEL_1": 1
|
| 55 |
+
},
|
| 56 |
+
"length_penalty": 1.0,
|
| 57 |
+
"mask_feature_length": 10,
|
| 58 |
+
"mask_feature_min_masks": 0,
|
| 59 |
+
"mask_feature_prob": 0.0,
|
| 60 |
+
"mask_time_length": 10,
|
| 61 |
+
"mask_time_min_masks": 2,
|
| 62 |
+
"mask_time_prob": 0.05,
|
| 63 |
+
"max_length": 448,
|
| 64 |
+
"max_source_positions": 1500,
|
| 65 |
+
"max_target_positions": 448,
|
| 66 |
+
"median_filter_width": 7,
|
| 67 |
+
"min_length": 0,
|
| 68 |
+
"model_type": "whisper",
|
| 69 |
+
"no_repeat_ngram_size": 0,
|
| 70 |
+
"num_beam_groups": 1,
|
| 71 |
+
"num_beams": 1,
|
| 72 |
+
"num_hidden_layers": 32,
|
| 73 |
+
"num_mel_bins": 128,
|
| 74 |
+
"num_return_sequences": 1,
|
| 75 |
+
"output_attentions": false,
|
| 76 |
+
"output_hidden_states": false,
|
| 77 |
+
"output_scores": false,
|
| 78 |
+
"pad_token_id": 50256,
|
| 79 |
+
"prefix": null,
|
| 80 |
+
"problem_type": null,
|
| 81 |
+
"pruned_heads": {},
|
| 82 |
+
"remove_invalid_values": false,
|
| 83 |
+
"repetition_penalty": 1.0,
|
| 84 |
+
"return_dict": true,
|
| 85 |
+
"return_dict_in_generate": false,
|
| 86 |
+
"scale_embedding": false,
|
| 87 |
+
"sep_token_id": null,
|
| 88 |
+
"suppress_tokens": null,
|
| 89 |
+
"task_specific_params": null,
|
| 90 |
+
"temperature": 1.0,
|
| 91 |
+
"tf_legacy_loss": false,
|
| 92 |
+
"tie_encoder_decoder": false,
|
| 93 |
+
"tie_word_embeddings": true,
|
| 94 |
+
"tokenizer_class": null,
|
| 95 |
+
"top_k": 50,
|
| 96 |
+
"top_p": 1.0,
|
| 97 |
+
"torchscript": false,
|
| 98 |
+
"typical_p": 1.0,
|
| 99 |
+
"use_bfloat16": false,
|
| 100 |
+
"use_cache": true,
|
| 101 |
+
"use_weighted_layer_sum": false,
|
| 102 |
+
"vocab_size": 51866
|
| 103 |
+
},
|
| 104 |
+
"audio_model_id": "openai/whisper-large-v3",
|
| 105 |
+
"audio_padding": "longest",
|
| 106 |
+
"auto_map": {
|
| 107 |
+
"AutoConfig": "configs.VLFMConfig",
|
| 108 |
+
"AutoModel": "model.VLFMModel"
|
| 109 |
+
},
|
| 110 |
+
"ds_rate": 2,
|
| 111 |
+
"dtype": "bfloat16",
|
| 112 |
+
"ignore_index": -100,
|
| 113 |
+
"llm_hidden_size": 3072,
|
| 114 |
+
"max_seconds": 30,
|
| 115 |
+
"model_type": "babs-vlfm",
|
| 116 |
+
"proj_hidden_dim": 4096,
|
| 117 |
+
"projector_act": "swiglu",
|
| 118 |
+
"projector_ln_mid": true,
|
| 119 |
+
"rms_norm_eps": 1e-06,
|
| 120 |
+
"rms_norm_init_factor": 0.4,
|
| 121 |
+
"speech_encoder_hidden_size": 1280,
|
| 122 |
+
"stack_factor": 8,
|
| 123 |
+
"text_config": {
|
| 124 |
+
"_name_or_path": "meta-llama/Llama-3.2-3B-Instruct",
|
| 125 |
+
"add_cross_attention": false,
|
| 126 |
+
"architectures": [
|
| 127 |
+
"LlamaForCausalLM"
|
| 128 |
+
],
|
| 129 |
+
"attention_bias": false,
|
| 130 |
+
"attention_dropout": 0.0,
|
| 131 |
+
"bad_words_ids": null,
|
| 132 |
+
"begin_suppress_tokens": null,
|
| 133 |
+
"bos_token_id": 128000,
|
| 134 |
+
"chunk_size_feed_forward": 0,
|
| 135 |
+
"cross_attention_hidden_size": null,
|
| 136 |
+
"decoder_start_token_id": null,
|
| 137 |
+
"diversity_penalty": 0.0,
|
| 138 |
+
"do_sample": false,
|
| 139 |
+
"dtype": "bfloat16",
|
| 140 |
+
"early_stopping": false,
|
| 141 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 142 |
+
"eos_token_id": [
|
| 143 |
+
128001,
|
| 144 |
+
128008,
|
| 145 |
+
128009
|
| 146 |
+
],
|
| 147 |
+
"exponential_decay_length_penalty": null,
|
| 148 |
+
"finetuning_task": null,
|
| 149 |
+
"forced_bos_token_id": null,
|
| 150 |
+
"forced_eos_token_id": null,
|
| 151 |
+
"head_dim": 128,
|
| 152 |
+
"hidden_act": "silu",
|
| 153 |
+
"hidden_size": 3072,
|
| 154 |
+
"id2label": {
|
| 155 |
+
"0": "LABEL_0",
|
| 156 |
+
"1": "LABEL_1"
|
| 157 |
+
},
|
| 158 |
+
"initializer_range": 0.02,
|
| 159 |
+
"intermediate_size": 8192,
|
| 160 |
+
"is_decoder": false,
|
| 161 |
+
"is_encoder_decoder": false,
|
| 162 |
+
"label2id": {
|
| 163 |
+
"LABEL_0": 0,
|
| 164 |
+
"LABEL_1": 1
|
| 165 |
+
},
|
| 166 |
+
"length_penalty": 1.0,
|
| 167 |
+
"max_length": 20,
|
| 168 |
+
"max_position_embeddings": 131072,
|
| 169 |
+
"min_length": 0,
|
| 170 |
+
"mlp_bias": false,
|
| 171 |
+
"model_type": "llama",
|
| 172 |
+
"no_repeat_ngram_size": 0,
|
| 173 |
+
"num_attention_heads": 24,
|
| 174 |
+
"num_beam_groups": 1,
|
| 175 |
+
"num_beams": 1,
|
| 176 |
+
"num_hidden_layers": 28,
|
| 177 |
+
"num_key_value_heads": 8,
|
| 178 |
+
"num_return_sequences": 1,
|
| 179 |
+
"output_attentions": false,
|
| 180 |
+
"output_hidden_states": false,
|
| 181 |
+
"output_scores": false,
|
| 182 |
+
"pad_token_id": null,
|
| 183 |
+
"prefix": null,
|
| 184 |
+
"pretraining_tp": 1,
|
| 185 |
+
"problem_type": null,
|
| 186 |
+
"pruned_heads": {},
|
| 187 |
+
"remove_invalid_values": false,
|
| 188 |
+
"repetition_penalty": 1.0,
|
| 189 |
+
"return_dict": true,
|
| 190 |
+
"return_dict_in_generate": false,
|
| 191 |
+
"rms_norm_eps": 1e-05,
|
| 192 |
+
"rope_scaling": {
|
| 193 |
+
"factor": 32.0,
|
| 194 |
+
"high_freq_factor": 4.0,
|
| 195 |
+
"low_freq_factor": 1.0,
|
| 196 |
+
"original_max_position_embeddings": 8192,
|
| 197 |
+
"rope_type": "llama3"
|
| 198 |
+
},
|
| 199 |
+
"rope_theta": 500000.0,
|
| 200 |
+
"sep_token_id": null,
|
| 201 |
+
"suppress_tokens": null,
|
| 202 |
+
"task_specific_params": null,
|
| 203 |
+
"temperature": 1.0,
|
| 204 |
+
"tf_legacy_loss": false,
|
| 205 |
+
"tie_encoder_decoder": false,
|
| 206 |
+
"tie_word_embeddings": true,
|
| 207 |
+
"tokenizer_class": null,
|
| 208 |
+
"top_k": 50,
|
| 209 |
+
"top_p": 1.0,
|
| 210 |
+
"torchscript": false,
|
| 211 |
+
"typical_p": 1.0,
|
| 212 |
+
"use_bfloat16": false,
|
| 213 |
+
"use_cache": true,
|
| 214 |
+
"vocab_size": 128256
|
| 215 |
+
},
|
| 216 |
+
"text_model_id": "meta-llama/Llama-3.2-3B-Instruct",
|
| 217 |
+
"tokenizer_padding_side": "right",
|
| 218 |
+
"transformers_version": "4.57.0",
|
| 219 |
+
"vocab_size": 128257
|
| 220 |
+
}
|
configs.py
ADDED
|
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from enum import Enum
|
| 2 |
+
import dataclasses
|
| 3 |
+
from typing import Optional
|
| 4 |
+
|
| 5 |
+
import transformers
|
| 6 |
+
from transformers import WhisperConfig, AutoConfig
|
| 7 |
+
from transformers import AutoTokenizer
|
| 8 |
+
from constants import IGNORE_INDEX
|
| 9 |
+
|
| 10 |
+
class VLFMConfig(transformers.PretrainedConfig):
|
| 11 |
+
model_type = "babs-vlfm"
|
| 12 |
+
|
| 13 |
+
def __init__(
|
| 14 |
+
self,
|
| 15 |
+
audio_model_id: Optional[str] = None,
|
| 16 |
+
text_model_id: Optional[str] = None,
|
| 17 |
+
*,
|
| 18 |
+
ignore_index: int = IGNORE_INDEX,
|
| 19 |
+
stack_factor: int = 8,
|
| 20 |
+
encoder_ds_factor: int = 2,
|
| 21 |
+
projector_act: str = "swiglu",
|
| 22 |
+
projector_ln_mid: bool = True,
|
| 23 |
+
max_audio_seconds: int = 30,
|
| 24 |
+
audio_padding: str = "longest",
|
| 25 |
+
tokenizer_padding_side: str = "right",
|
| 26 |
+
hidden_size: Optional[int] = 4096,
|
| 27 |
+
speech_encoder_hidden_size: Optional[int] = None,
|
| 28 |
+
vocab_size: Optional[int] = None,
|
| 29 |
+
**kwargs,
|
| 30 |
+
):
|
| 31 |
+
super().__init__(**kwargs)
|
| 32 |
+
|
| 33 |
+
self.audio_model_id = audio_model_id
|
| 34 |
+
self.text_model_id = text_model_id
|
| 35 |
+
|
| 36 |
+
self.ignore_index = ignore_index
|
| 37 |
+
self.stack_factor = stack_factor
|
| 38 |
+
self.ds_rate = encoder_ds_factor
|
| 39 |
+
self.projector_act = projector_act
|
| 40 |
+
self.projector_ln_mid = projector_ln_mid
|
| 41 |
+
self.proj_hidden_dim = hidden_size
|
| 42 |
+
|
| 43 |
+
self.max_seconds = max_audio_seconds
|
| 44 |
+
self.audio_padding = audio_padding
|
| 45 |
+
self.tokenizer_padding_side = tokenizer_padding_side
|
| 46 |
+
self.audio_config = None
|
| 47 |
+
self.text_config = None
|
| 48 |
+
|
| 49 |
+
if audio_model_id:
|
| 50 |
+
self.audio_config = WhisperConfig.from_pretrained(audio_model_id)
|
| 51 |
+
self.speech_encoder_hidden_size = self.audio_config.hidden_size
|
| 52 |
+
#print(f"audio_hidden_size: {self.speech_encoder_hidden_size}")
|
| 53 |
+
else:
|
| 54 |
+
self.speech_encoder_hidden_size = speech_encoder_hidden_size
|
| 55 |
+
|
| 56 |
+
if text_model_id:
|
| 57 |
+
self.text_config = AutoConfig.from_pretrained(text_model_id)
|
| 58 |
+
self.llm_hidden_size = self.text_config.hidden_size
|
| 59 |
+
#self.llm_hidden_size = 2048
|
| 60 |
+
#print(f"LLM hidden size: {self.llm_hidden_size}")
|
| 61 |
+
self.vocab_size = getattr(self.text_config, "vocab_size", vocab_size)
|
| 62 |
+
else:
|
| 63 |
+
self.llm_hidden_size =hidden_size
|
| 64 |
+
self.vocab_size = vocab_size
|
| 65 |
+
|
| 66 |
+
self.rms_norm_eps = 1e-6
|
| 67 |
+
self.rms_norm_init_factor = 0.4
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
class LossFunction(str, Enum):
|
| 71 |
+
CrossEntropy = "ce"
|
| 72 |
+
KL_Divergence = "kl"
|
| 73 |
+
|
| 74 |
+
|
| 75 |
+
@dataclasses.dataclass
|
| 76 |
+
class LossConfig:
|
| 77 |
+
loss_function: LossFunction = LossFunction.CrossEntropy
|
| 78 |
+
kl_temperature: float = 2.0
|
| 79 |
+
ce_weight = 0.5
|
| 80 |
+
|
| 81 |
+
@property
|
| 82 |
+
def requires_alt_fields(self) -> bool:
|
| 83 |
+
return self.loss_function == LossFunction.KL_Divergence
|
| 84 |
+
|
| 85 |
+
AUDIO_PLACEHOLDER = "<|audio|>"
|
| 86 |
+
|
| 87 |
+
def build_tokenizer(text_model_id: str, padding_side: str = "right"):
|
| 88 |
+
tok = AutoTokenizer.from_pretrained(text_model_id)
|
| 89 |
+
if tok.pad_token is None:
|
| 90 |
+
tok.pad_token = tok.eos_token
|
| 91 |
+
tok.padding_side = padding_side
|
| 92 |
+
# Add audio placeholder if missing
|
| 93 |
+
if AUDIO_PLACEHOLDER not in tok.get_vocab():
|
| 94 |
+
tok.add_special_tokens({"additional_special_tokens": [AUDIO_PLACEHOLDER]})
|
| 95 |
+
audio_token_id = tok.convert_tokens_to_ids(AUDIO_PLACEHOLDER)
|
| 96 |
+
return tok, audio_token_id
|
configuration_vlfm.py
ADDED
|
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from enum import Enum
|
| 2 |
+
import dataclasses
|
| 3 |
+
from typing import Optional
|
| 4 |
+
|
| 5 |
+
import transformers
|
| 6 |
+
from transformers import WhisperConfig, AutoConfig
|
| 7 |
+
from transformers import AutoTokenizer
|
| 8 |
+
from constants import IGNORE_INDEX
|
| 9 |
+
|
| 10 |
+
class VLFMConfig(transformers.PretrainedConfig):
|
| 11 |
+
model_type = "babs-vlfm"
|
| 12 |
+
|
| 13 |
+
def __init__(
|
| 14 |
+
self,
|
| 15 |
+
audio_model_id: Optional[str] = None,
|
| 16 |
+
text_model_id: Optional[str] = None,
|
| 17 |
+
*,
|
| 18 |
+
ignore_index: int = IGNORE_INDEX,
|
| 19 |
+
stack_factor: int = 8,
|
| 20 |
+
encoder_ds_factor: int = 2,
|
| 21 |
+
projector_act: str = "swiglu",
|
| 22 |
+
projector_ln_mid: bool = True,
|
| 23 |
+
max_audio_seconds: int = 30,
|
| 24 |
+
audio_padding: str = "longest",
|
| 25 |
+
tokenizer_padding_side: str = "right",
|
| 26 |
+
hidden_size: Optional[int] = 4096,
|
| 27 |
+
speech_encoder_hidden_size: Optional[int] = None,
|
| 28 |
+
vocab_size: Optional[int] = None,
|
| 29 |
+
**kwargs,
|
| 30 |
+
):
|
| 31 |
+
super().__init__(**kwargs)
|
| 32 |
+
|
| 33 |
+
self.audio_model_id = audio_model_id
|
| 34 |
+
self.text_model_id = text_model_id
|
| 35 |
+
|
| 36 |
+
self.ignore_index = ignore_index
|
| 37 |
+
self.stack_factor = stack_factor
|
| 38 |
+
self.ds_rate = encoder_ds_factor
|
| 39 |
+
self.projector_act = projector_act
|
| 40 |
+
self.projector_ln_mid = projector_ln_mid
|
| 41 |
+
self.proj_hidden_dim = hidden_size
|
| 42 |
+
|
| 43 |
+
self.max_seconds = max_audio_seconds
|
| 44 |
+
self.audio_padding = audio_padding
|
| 45 |
+
self.tokenizer_padding_side = tokenizer_padding_side
|
| 46 |
+
self.audio_config = None
|
| 47 |
+
self.text_config = None
|
| 48 |
+
|
| 49 |
+
if audio_model_id:
|
| 50 |
+
self.audio_config = WhisperConfig.from_pretrained(audio_model_id)
|
| 51 |
+
self.speech_encoder_hidden_size = self.audio_config.hidden_size
|
| 52 |
+
#print(f"audio_hidden_size: {self.speech_encoder_hidden_size}")
|
| 53 |
+
else:
|
| 54 |
+
self.speech_encoder_hidden_size = speech_encoder_hidden_size
|
| 55 |
+
|
| 56 |
+
if text_model_id:
|
| 57 |
+
self.text_config = AutoConfig.from_pretrained(text_model_id)
|
| 58 |
+
self.llm_hidden_size = self.text_config.hidden_size
|
| 59 |
+
#self.llm_hidden_size = 2048
|
| 60 |
+
#print(f"LLM hidden size: {self.llm_hidden_size}")
|
| 61 |
+
self.vocab_size = getattr(self.text_config, "vocab_size", vocab_size)
|
| 62 |
+
else:
|
| 63 |
+
self.llm_hidden_size =hidden_size
|
| 64 |
+
self.vocab_size = vocab_size
|
| 65 |
+
|
| 66 |
+
self.rms_norm_eps = 1e-6
|
| 67 |
+
self.rms_norm_init_factor = 0.4
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
class LossFunction(str, Enum):
|
| 71 |
+
CrossEntropy = "ce"
|
| 72 |
+
KL_Divergence = "kl"
|
| 73 |
+
|
| 74 |
+
|
| 75 |
+
@dataclasses.dataclass
|
| 76 |
+
class LossConfig:
|
| 77 |
+
loss_function: LossFunction = LossFunction.CrossEntropy
|
| 78 |
+
kl_temperature: float = 2.0
|
| 79 |
+
ce_weight = 0.5
|
| 80 |
+
|
| 81 |
+
@property
|
| 82 |
+
def requires_alt_fields(self) -> bool:
|
| 83 |
+
return self.loss_function == LossFunction.KL_Divergence
|
| 84 |
+
|
| 85 |
+
AUDIO_PLACEHOLDER = "<|audio|>"
|
| 86 |
+
|
| 87 |
+
def build_tokenizer(text_model_id: str, padding_side: str = "right"):
|
| 88 |
+
tok = AutoTokenizer.from_pretrained(text_model_id)
|
| 89 |
+
if tok.pad_token is None:
|
| 90 |
+
tok.pad_token = tok.eos_token
|
| 91 |
+
tok.padding_side = padding_side
|
| 92 |
+
# Add audio placeholder if missing
|
| 93 |
+
if AUDIO_PLACEHOLDER not in tok.get_vocab():
|
| 94 |
+
tok.add_special_tokens({"additional_special_tokens": [AUDIO_PLACEHOLDER]})
|
| 95 |
+
audio_token_id = tok.convert_tokens_to_ids(AUDIO_PLACEHOLDER)
|
| 96 |
+
return tok, audio_token_id
|
model-00001-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e93644740750f5cdb4491e14d1c969fb1d80d625420bbcb26d40c248204b2c6c
|
| 3 |
+
size 1466959128
|
model-00002-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:199e655b2ca2be11aca16c381b0b6c609d424836b0d1c88ad0b5ab582e5ef032
|
| 3 |
+
size 1996051464
|
model-00003-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8353697e6d2afbcfdf0b6b6cc2e836dc0500990cb6e6cf18f476c7e1b827ff61
|
| 3 |
+
size 1963056200
|
model-00004-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f770e0e318ae60759aaeed07112f36ac0ad26f4f36677c27d388da36247a401e
|
| 3 |
+
size 1963068792
|
model-00005-of-00005.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f1ab0807a4f532670541b0bc04def7b8be97871e857ae98c0cb4408a2e2b0f8
|
| 3 |
+
size 503362456
|
model.py
ADDED
|
@@ -0,0 +1,296 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import torch
|
| 2 |
+
import torch.nn as nn
|
| 3 |
+
import torch.nn.functional as F
|
| 4 |
+
import transformers
|
| 5 |
+
from transformers import (
|
| 6 |
+
AutoConfig, AutoModel,
|
| 7 |
+
AutoModelForCausalLM, WhisperModel)
|
| 8 |
+
|
| 9 |
+
from configs import VLFMConfig, LossFunction, LossConfig, build_tokenizer
|
| 10 |
+
from projector import VLFMProjector
|
| 11 |
+
from constants import IGNORE_INDEX, SPEECH_TOKEN_INDEX
|
| 12 |
+
|
| 13 |
+
from transformers.modeling_outputs import CausalLMOutputWithPast
|
| 14 |
+
from transformers.generation.utils import GenerateOutput
|
| 15 |
+
from typing import Optional, Tuple, List, Union
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
class VLFMModel(transformers.LlamaPreTrainedModel):
|
| 19 |
+
config_class = VLFMConfig
|
| 20 |
+
def __init__(self, config, torch_dtype=torch.bfloat16):
|
| 21 |
+
super(VLFMModel, self).__init__(config)
|
| 22 |
+
|
| 23 |
+
whisper = WhisperModel.from_pretrained(config.audio_model_id,
|
| 24 |
+
torch_dtype=torch_dtype,)
|
| 25 |
+
|
| 26 |
+
self.encoder = whisper.encoder
|
| 27 |
+
self.projector = VLFMProjector(config)
|
| 28 |
+
self.language_model = AutoModelForCausalLM.from_pretrained(config.text_model_id,
|
| 29 |
+
torch_dtype=torch_dtype)
|
| 30 |
+
|
| 31 |
+
self._train_module(self.encoder, False)
|
| 32 |
+
self._train_module(self.language_model, False)
|
| 33 |
+
self._train_module(self.projector, True)
|
| 34 |
+
|
| 35 |
+
self.encoder.to(dtype=torch_dtype)
|
| 36 |
+
self.language_model.to(dtype=torch_dtype)
|
| 37 |
+
self.projector.to(dtype=torch_dtype)
|
| 38 |
+
|
| 39 |
+
self.tokenizer, self.audio_token_id = build_tokenizer(config.text_model_id, config.tokenizer_padding_side)
|
| 40 |
+
|
| 41 |
+
self.tokenizer_model_max_length = self.tokenizer.model_max_length
|
| 42 |
+
self._resize_token_embeddings(self.tokenizer)
|
| 43 |
+
self.get_input_embeddings().to(dtype=self.language_model.dtype)
|
| 44 |
+
if hasattr(self.language_model, "get_output_embeddings") and self.language_model.get_output_embeddings() is not None:
|
| 45 |
+
self.language_model.get_output_embeddings().to(dtype=self.language_model.dtype)
|
| 46 |
+
|
| 47 |
+
self.loss_config = LossConfig(LossFunction.KL_Divergence)
|
| 48 |
+
#self.loss_config.loss_function = LossFunction.KL_Divergence
|
| 49 |
+
|
| 50 |
+
self.post_init()
|
| 51 |
+
|
| 52 |
+
def get_input_embeddings(self):
|
| 53 |
+
return self.language_model.get_input_embeddings()
|
| 54 |
+
|
| 55 |
+
def set_input_embeddings(self, new_emb):
|
| 56 |
+
return self.language_model.set_input_embeddings(new_emb)
|
| 57 |
+
|
| 58 |
+
@property
|
| 59 |
+
def embed_tokens(self):
|
| 60 |
+
return self.language_model.get_input_embeddings()
|
| 61 |
+
|
| 62 |
+
def _train_module(self, module, trainable: bool):
|
| 63 |
+
for param in module.parameters():
|
| 64 |
+
param.requires_grad= trainable
|
| 65 |
+
|
| 66 |
+
def _audio_iter(self, audio_batch_size):
|
| 67 |
+
audio_index = 0
|
| 68 |
+
for i_b, count in enumerate(audio_batch_size.view(-1).tolist()):
|
| 69 |
+
for _ in range(int(count)):
|
| 70 |
+
yield i_b, audio_index
|
| 71 |
+
audio_index += 1
|
| 72 |
+
|
| 73 |
+
def _resize_token_embeddings(self, tokenizer, pad_to_multiple_of=None):
|
| 74 |
+
|
| 75 |
+
model_embeds = self.language_model.resize_token_embeddings(len(tokenizer))
|
| 76 |
+
self.config.vocab_size = model_embeds.num_embeddings
|
| 77 |
+
self.vocab_size = model_embeds.num_embeddings
|
| 78 |
+
return model_embeds
|
| 79 |
+
|
| 80 |
+
def _encode_speech(self, audio_values):
|
| 81 |
+
with torch.no_grad():
|
| 82 |
+
encoder_outputs = self.encoder(audio_values, output_hidden_states=False)
|
| 83 |
+
audio_embeds = encoder_outputs.last_hidden_state
|
| 84 |
+
downsampled_embeds = self.projector(audio_embeds) #(B, T, D)
|
| 85 |
+
#print(f"Shape of projector output: {downsampled_embeds.shape}")
|
| 86 |
+
return downsampled_embeds
|
| 87 |
+
|
| 88 |
+
def _splice_chunks(self, text_embeds, audio_embeds, audio_token_start_idx, audio_token_len, audio_batch_size):
|
| 89 |
+
D = text_embeds.size(-1)
|
| 90 |
+
for i_b, i_chunk in self._audio_iter(audio_batch_size):
|
| 91 |
+
start = int(audio_token_start_idx[i_chunk].item())
|
| 92 |
+
span = int(audio_token_len[i_chunk].item())
|
| 93 |
+
a = audio_embeds[i_chunk]
|
| 94 |
+
Ta = a.size(0)
|
| 95 |
+
use = min(Ta, span)
|
| 96 |
+
text_embeds[i_b, start:start+use, :] = a[:use].to(text_embeds.dtype)
|
| 97 |
+
|
| 98 |
+
|
| 99 |
+
def _compute_kl_loss(
|
| 100 |
+
self,
|
| 101 |
+
*,
|
| 102 |
+
student_logits: torch.Tensor,
|
| 103 |
+
labels: torch.Tensor,
|
| 104 |
+
alt_input_ids: torch.Tensor,
|
| 105 |
+
alt_attention_mask: torch.Tensor,
|
| 106 |
+
alt_labels: torch.Tensor,
|
| 107 |
+
past_key_values=None,
|
| 108 |
+
**kwargs,
|
| 109 |
+
):
|
| 110 |
+
lm_was_training = self.language_model.training
|
| 111 |
+
self.language_model.eval()
|
| 112 |
+
with torch.no_grad():
|
| 113 |
+
alt_input_embeds = self.language_model.get_input_embeddings()(alt_input_ids)
|
| 114 |
+
teacher_out = self.language_model(
|
| 115 |
+
inputs_embeds=alt_input_embeds,
|
| 116 |
+
attention_mask=alt_attention_mask,
|
| 117 |
+
use_cache=False,
|
| 118 |
+
return_dict=True,
|
| 119 |
+
past_key_values=past_key_values,
|
| 120 |
+
)
|
| 121 |
+
teacher_logits = teacher_out.logits
|
| 122 |
+
if lm_was_training:
|
| 123 |
+
self.language_model.train()
|
| 124 |
+
|
| 125 |
+
T = self.loss_config.kl_temperature
|
| 126 |
+
student = F.log_softmax(student_logits[labels != IGNORE_INDEX] / T, dim=-1)
|
| 127 |
+
teacher = F.softmax(teacher_logits[alt_labels != IGNORE_INDEX] / T, dim=-1)
|
| 128 |
+
kl = F.kl_div(student, teacher, reduction="batchmean")
|
| 129 |
+
return kl
|
| 130 |
+
|
| 131 |
+
|
| 132 |
+
|
| 133 |
+
def forward(
|
| 134 |
+
self,
|
| 135 |
+
input_ids,
|
| 136 |
+
attention_mask,
|
| 137 |
+
labels=None,
|
| 138 |
+
*,
|
| 139 |
+
input_features=None,
|
| 140 |
+
audio_token_start_idx = None,
|
| 141 |
+
audio_token_len = None,
|
| 142 |
+
audio_batch_size = None,
|
| 143 |
+
alt_input_ids = None,
|
| 144 |
+
alt_attention_mask = None,
|
| 145 |
+
alt_labels = None,
|
| 146 |
+
return_dict = True,
|
| 147 |
+
**kwargs):
|
| 148 |
+
tok = self.language_model.get_input_embeddings()
|
| 149 |
+
text_embeds = tok(input_ids)
|
| 150 |
+
|
| 151 |
+
if input_features is not None and audio_token_start_idx is not None:
|
| 152 |
+
audio_embeds = self._encode_speech(input_features)
|
| 153 |
+
self._splice_chunks(
|
| 154 |
+
text_embeds,
|
| 155 |
+
audio_embeds,
|
| 156 |
+
audio_token_start_idx,
|
| 157 |
+
audio_token_len,
|
| 158 |
+
audio_batch_size
|
| 159 |
+
)
|
| 160 |
+
|
| 161 |
+
out = self.language_model(
|
| 162 |
+
inputs_embeds=text_embeds,
|
| 163 |
+
attention_mask=attention_mask,
|
| 164 |
+
labels =labels,
|
| 165 |
+
return_dict=True,
|
| 166 |
+
use_cache = True,
|
| 167 |
+
)
|
| 168 |
+
|
| 169 |
+
logits = out.logits
|
| 170 |
+
ce_loss = out.loss
|
| 171 |
+
|
| 172 |
+
alpha = self.loss_config.ce_weight
|
| 173 |
+
alpha = self.loss_config.ce_weight
|
| 174 |
+
|
| 175 |
+
kl = None
|
| 176 |
+
if (
|
| 177 |
+
self.training
|
| 178 |
+
and alt_input_ids is not None
|
| 179 |
+
and alt_attention_mask is not None
|
| 180 |
+
and alt_labels is not None
|
| 181 |
+
):
|
| 182 |
+
|
| 183 |
+
kl = self._compute_kl_loss(
|
| 184 |
+
student_logits=logits,
|
| 185 |
+
labels=labels,
|
| 186 |
+
alt_input_ids=alt_input_ids,
|
| 187 |
+
alt_attention_mask=alt_attention_mask,
|
| 188 |
+
alt_labels=alt_labels,
|
| 189 |
+
past_key_values=None,
|
| 190 |
+
)
|
| 191 |
+
|
| 192 |
+
total_loss = alpha * ce_loss + (1 - alpha) * kl
|
| 193 |
+
else:
|
| 194 |
+
total_loss = ce_loss
|
| 195 |
+
|
| 196 |
+
return {
|
| 197 |
+
"loss": total_loss,
|
| 198 |
+
"loss_ce": ce_loss.detach() if ce_loss is not None else None,
|
| 199 |
+
"loss_kl": kl.detach() if kl is not None else None,
|
| 200 |
+
"logits": logits,}
|
| 201 |
+
|
| 202 |
+
|
| 203 |
+
''' if (
|
| 204 |
+
self.training
|
| 205 |
+
and self.loss_config.loss_function == LossFunction.KL_Divergence
|
| 206 |
+
and alt_input_ids is not None
|
| 207 |
+
and alt_attention_mask is not None
|
| 208 |
+
and alt_labels is not None
|
| 209 |
+
|
| 210 |
+
):
|
| 211 |
+
kl = self._compute_kl_loss(
|
| 212 |
+
student_logits=logits,
|
| 213 |
+
labels=labels,
|
| 214 |
+
alt_input_ids=alt_input_ids,
|
| 215 |
+
alt_attention_mask=alt_attention_mask,
|
| 216 |
+
alt_labels=alt_labels,
|
| 217 |
+
past_key_values=None,)
|
| 218 |
+
|
| 219 |
+
return {
|
| 220 |
+
"loss": kl,
|
| 221 |
+
"loss_ce": (ce_loss.detach() if ce_loss is not None else None),
|
| 222 |
+
logits: logits}
|
| 223 |
+
|
| 224 |
+
if return_dict:
|
| 225 |
+
return out
|
| 226 |
+
return (ce_loss, logits) '''
|
| 227 |
+
|
| 228 |
+
def _prepare_inputs_embeds(
|
| 229 |
+
self,
|
| 230 |
+
input_ids,
|
| 231 |
+
attention_mask,
|
| 232 |
+
*,
|
| 233 |
+
input_features = None,
|
| 234 |
+
audio_token_start_idx = None,
|
| 235 |
+
audio_token_len = None,
|
| 236 |
+
audio_batch_size= None,
|
| 237 |
+
):
|
| 238 |
+
"""
|
| 239 |
+
Returns:
|
| 240 |
+
inputs_embeds: [B, L, D] with audio spliced in
|
| 241 |
+
attention_mask: [B, L] (unchanged)
|
| 242 |
+
"""
|
| 243 |
+
tok = self.language_model.get_input_embeddings()
|
| 244 |
+
inputs_embeds = tok(input_ids) # [B, L, D]
|
| 245 |
+
|
| 246 |
+
if input_features is not None and audio_token_start_idx is not None:
|
| 247 |
+
# Normalize shapes: treat "one audio per sample" as N_chunks == B
|
| 248 |
+
feats = input_features
|
| 249 |
+
if feats.dim() == 3 and feats.size(0) == input_ids.size(0):
|
| 250 |
+
audio_batch_size = torch.ones(input_ids.size(0), dtype=torch.long, device=input_ids.device)
|
| 251 |
+
assert audio_batch_size is not None, "audio_batch_size required when splicing audio."
|
| 252 |
+
|
| 253 |
+
# Encode + project, then splice
|
| 254 |
+
audio_embeds = self._encode_audio(feats) # [N_chunks, T_audio, D]
|
| 255 |
+
self._splice_chunks(
|
| 256 |
+
text_embeds=inputs_embeds,
|
| 257 |
+
audio_embeds=audio_embeds,
|
| 258 |
+
audio_token_start_idx=audio_token_start_idx,
|
| 259 |
+
audio_token_len=audio_token_len,
|
| 260 |
+
audio_batch_size=audio_batch_size,
|
| 261 |
+
)
|
| 262 |
+
|
| 263 |
+
return inputs_embeds, attention_mask
|
| 264 |
+
|
| 265 |
+
@torch.no_grad()
|
| 266 |
+
def generate(
|
| 267 |
+
self,
|
| 268 |
+
input_ids, # [B, L]
|
| 269 |
+
attention_mask, # [B, L]
|
| 270 |
+
*,
|
| 271 |
+
input_features,
|
| 272 |
+
audio_token_start_idx= None,
|
| 273 |
+
audio_token_len= None,
|
| 274 |
+
audio_batch_size = None,
|
| 275 |
+
**gen_kwargs,
|
| 276 |
+
):
|
| 277 |
+
"""
|
| 278 |
+
Build spliced embeddings and call the base LM's generate"""
|
| 279 |
+
self.eval()
|
| 280 |
+
inputs_embeds, attn_mask = self._prepare_inputs_embeds(
|
| 281 |
+
input_ids=input_ids,
|
| 282 |
+
attention_mask=attention_mask,
|
| 283 |
+
input_features=input_features,
|
| 284 |
+
audio_token_start_idx=audio_token_start_idx,
|
| 285 |
+
audio_token_len=audio_token_len,
|
| 286 |
+
audio_batch_size=audio_batch_size,
|
| 287 |
+
)
|
| 288 |
+
return self.language_model.generate(
|
| 289 |
+
inputs_embeds=inputs_embeds,
|
| 290 |
+
attention_mask=attn_mask,
|
| 291 |
+
**gen_kwargs,
|
| 292 |
+
)
|
| 293 |
+
|
| 294 |
+
|
| 295 |
+
AutoConfig.register("babs-vlfm", VLFMConfig)
|
| 296 |
+
AutoModel.register(VLFMConfig, VLFMModel)
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,753 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 3946205184,
|
| 4 |
+
"total_size": 7892410368
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"encoder.conv1.bias": "model-00001-of-00005.safetensors",
|
| 8 |
+
"encoder.conv1.weight": "model-00001-of-00005.safetensors",
|
| 9 |
+
"encoder.conv2.bias": "model-00001-of-00005.safetensors",
|
| 10 |
+
"encoder.conv2.weight": "model-00001-of-00005.safetensors",
|
| 11 |
+
"encoder.embed_positions.weight": "model-00001-of-00005.safetensors",
|
| 12 |
+
"encoder.layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 13 |
+
"encoder.layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 14 |
+
"encoder.layers.0.fc1.bias": "model-00001-of-00005.safetensors",
|
| 15 |
+
"encoder.layers.0.fc1.weight": "model-00001-of-00005.safetensors",
|
| 16 |
+
"encoder.layers.0.fc2.bias": "model-00001-of-00005.safetensors",
|
| 17 |
+
"encoder.layers.0.fc2.weight": "model-00001-of-00005.safetensors",
|
| 18 |
+
"encoder.layers.0.final_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 19 |
+
"encoder.layers.0.final_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 20 |
+
"encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 21 |
+
"encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
|
| 22 |
+
"encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
|
| 23 |
+
"encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
| 24 |
+
"encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 25 |
+
"encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
| 26 |
+
"encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 27 |
+
"encoder.layers.0.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 28 |
+
"encoder.layers.0.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 29 |
+
"encoder.layers.1.fc1.bias": "model-00001-of-00005.safetensors",
|
| 30 |
+
"encoder.layers.1.fc1.weight": "model-00001-of-00005.safetensors",
|
| 31 |
+
"encoder.layers.1.fc2.bias": "model-00001-of-00005.safetensors",
|
| 32 |
+
"encoder.layers.1.fc2.weight": "model-00001-of-00005.safetensors",
|
| 33 |
+
"encoder.layers.1.final_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 34 |
+
"encoder.layers.1.final_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 35 |
+
"encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 36 |
+
"encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
|
| 37 |
+
"encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
|
| 38 |
+
"encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
| 39 |
+
"encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 40 |
+
"encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
| 41 |
+
"encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 42 |
+
"encoder.layers.1.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 43 |
+
"encoder.layers.1.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 44 |
+
"encoder.layers.10.fc1.bias": "model-00001-of-00005.safetensors",
|
| 45 |
+
"encoder.layers.10.fc1.weight": "model-00001-of-00005.safetensors",
|
| 46 |
+
"encoder.layers.10.fc2.bias": "model-00001-of-00005.safetensors",
|
| 47 |
+
"encoder.layers.10.fc2.weight": "model-00001-of-00005.safetensors",
|
| 48 |
+
"encoder.layers.10.final_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 49 |
+
"encoder.layers.10.final_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 50 |
+
"encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 51 |
+
"encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
|
| 52 |
+
"encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
|
| 53 |
+
"encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
| 54 |
+
"encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 55 |
+
"encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
| 56 |
+
"encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 57 |
+
"encoder.layers.10.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 58 |
+
"encoder.layers.10.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 59 |
+
"encoder.layers.11.fc1.bias": "model-00001-of-00005.safetensors",
|
| 60 |
+
"encoder.layers.11.fc1.weight": "model-00001-of-00005.safetensors",
|
| 61 |
+
"encoder.layers.11.fc2.bias": "model-00001-of-00005.safetensors",
|
| 62 |
+
"encoder.layers.11.fc2.weight": "model-00001-of-00005.safetensors",
|
| 63 |
+
"encoder.layers.11.final_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 64 |
+
"encoder.layers.11.final_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 65 |
+
"encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 66 |
+
"encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
|
| 67 |
+
"encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
|
| 68 |
+
"encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
| 69 |
+
"encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 70 |
+
"encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
| 71 |
+
"encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 72 |
+
"encoder.layers.11.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 73 |
+
"encoder.layers.11.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 74 |
+
"encoder.layers.12.fc1.bias": "model-00001-of-00005.safetensors",
|
| 75 |
+
"encoder.layers.12.fc1.weight": "model-00001-of-00005.safetensors",
|
| 76 |
+
"encoder.layers.12.fc2.bias": "model-00001-of-00005.safetensors",
|
| 77 |
+
"encoder.layers.12.fc2.weight": "model-00001-of-00005.safetensors",
|
| 78 |
+
"encoder.layers.12.final_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 79 |
+
"encoder.layers.12.final_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 80 |
+
"encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 81 |
+
"encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
|
| 82 |
+
"encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
|
| 83 |
+
"encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
| 84 |
+
"encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 85 |
+
"encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
| 86 |
+
"encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 87 |
+
"encoder.layers.12.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 88 |
+
"encoder.layers.12.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 89 |
+
"encoder.layers.13.fc1.bias": "model-00001-of-00005.safetensors",
|
| 90 |
+
"encoder.layers.13.fc1.weight": "model-00001-of-00005.safetensors",
|
| 91 |
+
"encoder.layers.13.fc2.bias": "model-00001-of-00005.safetensors",
|
| 92 |
+
"encoder.layers.13.fc2.weight": "model-00001-of-00005.safetensors",
|
| 93 |
+
"encoder.layers.13.final_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 94 |
+
"encoder.layers.13.final_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 95 |
+
"encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 96 |
+
"encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
|
| 97 |
+
"encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
|
| 98 |
+
"encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
| 99 |
+
"encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 100 |
+
"encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
| 101 |
+
"encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 102 |
+
"encoder.layers.13.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 103 |
+
"encoder.layers.13.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 104 |
+
"encoder.layers.14.fc1.bias": "model-00001-of-00005.safetensors",
|
| 105 |
+
"encoder.layers.14.fc1.weight": "model-00001-of-00005.safetensors",
|
| 106 |
+
"encoder.layers.14.fc2.bias": "model-00001-of-00005.safetensors",
|
| 107 |
+
"encoder.layers.14.fc2.weight": "model-00001-of-00005.safetensors",
|
| 108 |
+
"encoder.layers.14.final_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 109 |
+
"encoder.layers.14.final_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 110 |
+
"encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 111 |
+
"encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
|
| 112 |
+
"encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
|
| 113 |
+
"encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
| 114 |
+
"encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 115 |
+
"encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
| 116 |
+
"encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 117 |
+
"encoder.layers.14.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 118 |
+
"encoder.layers.14.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 119 |
+
"encoder.layers.15.fc1.bias": "model-00001-of-00005.safetensors",
|
| 120 |
+
"encoder.layers.15.fc1.weight": "model-00001-of-00005.safetensors",
|
| 121 |
+
"encoder.layers.15.fc2.bias": "model-00001-of-00005.safetensors",
|
| 122 |
+
"encoder.layers.15.fc2.weight": "model-00001-of-00005.safetensors",
|
| 123 |
+
"encoder.layers.15.final_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 124 |
+
"encoder.layers.15.final_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 125 |
+
"encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 126 |
+
"encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
|
| 127 |
+
"encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
|
| 128 |
+
"encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
| 129 |
+
"encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 130 |
+
"encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
| 131 |
+
"encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 132 |
+
"encoder.layers.15.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 133 |
+
"encoder.layers.15.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 134 |
+
"encoder.layers.16.fc1.bias": "model-00001-of-00005.safetensors",
|
| 135 |
+
"encoder.layers.16.fc1.weight": "model-00001-of-00005.safetensors",
|
| 136 |
+
"encoder.layers.16.fc2.bias": "model-00001-of-00005.safetensors",
|
| 137 |
+
"encoder.layers.16.fc2.weight": "model-00001-of-00005.safetensors",
|
| 138 |
+
"encoder.layers.16.final_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 139 |
+
"encoder.layers.16.final_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 140 |
+
"encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 141 |
+
"encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
|
| 142 |
+
"encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
|
| 143 |
+
"encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
| 144 |
+
"encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 145 |
+
"encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
| 146 |
+
"encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 147 |
+
"encoder.layers.16.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 148 |
+
"encoder.layers.16.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 149 |
+
"encoder.layers.17.fc1.bias": "model-00001-of-00005.safetensors",
|
| 150 |
+
"encoder.layers.17.fc1.weight": "model-00001-of-00005.safetensors",
|
| 151 |
+
"encoder.layers.17.fc2.bias": "model-00001-of-00005.safetensors",
|
| 152 |
+
"encoder.layers.17.fc2.weight": "model-00001-of-00005.safetensors",
|
| 153 |
+
"encoder.layers.17.final_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 154 |
+
"encoder.layers.17.final_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 155 |
+
"encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 156 |
+
"encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
|
| 157 |
+
"encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
|
| 158 |
+
"encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
| 159 |
+
"encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 160 |
+
"encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
| 161 |
+
"encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 162 |
+
"encoder.layers.17.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 163 |
+
"encoder.layers.17.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 164 |
+
"encoder.layers.18.fc1.bias": "model-00001-of-00005.safetensors",
|
| 165 |
+
"encoder.layers.18.fc1.weight": "model-00001-of-00005.safetensors",
|
| 166 |
+
"encoder.layers.18.fc2.bias": "model-00001-of-00005.safetensors",
|
| 167 |
+
"encoder.layers.18.fc2.weight": "model-00001-of-00005.safetensors",
|
| 168 |
+
"encoder.layers.18.final_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 169 |
+
"encoder.layers.18.final_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 170 |
+
"encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 171 |
+
"encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
|
| 172 |
+
"encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
|
| 173 |
+
"encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
| 174 |
+
"encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 175 |
+
"encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
| 176 |
+
"encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 177 |
+
"encoder.layers.18.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 178 |
+
"encoder.layers.18.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 179 |
+
"encoder.layers.19.fc1.bias": "model-00001-of-00005.safetensors",
|
| 180 |
+
"encoder.layers.19.fc1.weight": "model-00001-of-00005.safetensors",
|
| 181 |
+
"encoder.layers.19.fc2.bias": "model-00001-of-00005.safetensors",
|
| 182 |
+
"encoder.layers.19.fc2.weight": "model-00001-of-00005.safetensors",
|
| 183 |
+
"encoder.layers.19.final_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 184 |
+
"encoder.layers.19.final_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 185 |
+
"encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 186 |
+
"encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
|
| 187 |
+
"encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
|
| 188 |
+
"encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
| 189 |
+
"encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 190 |
+
"encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
| 191 |
+
"encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 192 |
+
"encoder.layers.19.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 193 |
+
"encoder.layers.19.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 194 |
+
"encoder.layers.2.fc1.bias": "model-00001-of-00005.safetensors",
|
| 195 |
+
"encoder.layers.2.fc1.weight": "model-00001-of-00005.safetensors",
|
| 196 |
+
"encoder.layers.2.fc2.bias": "model-00001-of-00005.safetensors",
|
| 197 |
+
"encoder.layers.2.fc2.weight": "model-00001-of-00005.safetensors",
|
| 198 |
+
"encoder.layers.2.final_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 199 |
+
"encoder.layers.2.final_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 200 |
+
"encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 201 |
+
"encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
|
| 202 |
+
"encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
|
| 203 |
+
"encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
| 204 |
+
"encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 205 |
+
"encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
| 206 |
+
"encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 207 |
+
"encoder.layers.2.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 208 |
+
"encoder.layers.2.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 209 |
+
"encoder.layers.20.fc1.bias": "model-00001-of-00005.safetensors",
|
| 210 |
+
"encoder.layers.20.fc1.weight": "model-00001-of-00005.safetensors",
|
| 211 |
+
"encoder.layers.20.fc2.bias": "model-00001-of-00005.safetensors",
|
| 212 |
+
"encoder.layers.20.fc2.weight": "model-00001-of-00005.safetensors",
|
| 213 |
+
"encoder.layers.20.final_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 214 |
+
"encoder.layers.20.final_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 215 |
+
"encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 216 |
+
"encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
|
| 217 |
+
"encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
|
| 218 |
+
"encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
| 219 |
+
"encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 220 |
+
"encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
| 221 |
+
"encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 222 |
+
"encoder.layers.20.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 223 |
+
"encoder.layers.20.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 224 |
+
"encoder.layers.21.fc1.bias": "model-00001-of-00005.safetensors",
|
| 225 |
+
"encoder.layers.21.fc1.weight": "model-00001-of-00005.safetensors",
|
| 226 |
+
"encoder.layers.21.fc2.bias": "model-00001-of-00005.safetensors",
|
| 227 |
+
"encoder.layers.21.fc2.weight": "model-00001-of-00005.safetensors",
|
| 228 |
+
"encoder.layers.21.final_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 229 |
+
"encoder.layers.21.final_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 230 |
+
"encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 231 |
+
"encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
|
| 232 |
+
"encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
|
| 233 |
+
"encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
| 234 |
+
"encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 235 |
+
"encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
| 236 |
+
"encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 237 |
+
"encoder.layers.21.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 238 |
+
"encoder.layers.21.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 239 |
+
"encoder.layers.22.fc1.bias": "model-00001-of-00005.safetensors",
|
| 240 |
+
"encoder.layers.22.fc1.weight": "model-00001-of-00005.safetensors",
|
| 241 |
+
"encoder.layers.22.fc2.bias": "model-00001-of-00005.safetensors",
|
| 242 |
+
"encoder.layers.22.fc2.weight": "model-00001-of-00005.safetensors",
|
| 243 |
+
"encoder.layers.22.final_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 244 |
+
"encoder.layers.22.final_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 245 |
+
"encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 246 |
+
"encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
|
| 247 |
+
"encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
|
| 248 |
+
"encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
| 249 |
+
"encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 250 |
+
"encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
| 251 |
+
"encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 252 |
+
"encoder.layers.22.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 253 |
+
"encoder.layers.22.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 254 |
+
"encoder.layers.23.fc1.bias": "model-00001-of-00005.safetensors",
|
| 255 |
+
"encoder.layers.23.fc1.weight": "model-00001-of-00005.safetensors",
|
| 256 |
+
"encoder.layers.23.fc2.bias": "model-00001-of-00005.safetensors",
|
| 257 |
+
"encoder.layers.23.fc2.weight": "model-00001-of-00005.safetensors",
|
| 258 |
+
"encoder.layers.23.final_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 259 |
+
"encoder.layers.23.final_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 260 |
+
"encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 261 |
+
"encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
|
| 262 |
+
"encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
|
| 263 |
+
"encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
| 264 |
+
"encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 265 |
+
"encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
| 266 |
+
"encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 267 |
+
"encoder.layers.23.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 268 |
+
"encoder.layers.23.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 269 |
+
"encoder.layers.24.fc1.bias": "model-00001-of-00005.safetensors",
|
| 270 |
+
"encoder.layers.24.fc1.weight": "model-00001-of-00005.safetensors",
|
| 271 |
+
"encoder.layers.24.fc2.bias": "model-00001-of-00005.safetensors",
|
| 272 |
+
"encoder.layers.24.fc2.weight": "model-00001-of-00005.safetensors",
|
| 273 |
+
"encoder.layers.24.final_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 274 |
+
"encoder.layers.24.final_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 275 |
+
"encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 276 |
+
"encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
|
| 277 |
+
"encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
|
| 278 |
+
"encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
| 279 |
+
"encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 280 |
+
"encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
| 281 |
+
"encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 282 |
+
"encoder.layers.24.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 283 |
+
"encoder.layers.24.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 284 |
+
"encoder.layers.25.fc1.bias": "model-00001-of-00005.safetensors",
|
| 285 |
+
"encoder.layers.25.fc1.weight": "model-00001-of-00005.safetensors",
|
| 286 |
+
"encoder.layers.25.fc2.bias": "model-00001-of-00005.safetensors",
|
| 287 |
+
"encoder.layers.25.fc2.weight": "model-00001-of-00005.safetensors",
|
| 288 |
+
"encoder.layers.25.final_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 289 |
+
"encoder.layers.25.final_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 290 |
+
"encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 291 |
+
"encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
|
| 292 |
+
"encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
|
| 293 |
+
"encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
| 294 |
+
"encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 295 |
+
"encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
| 296 |
+
"encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 297 |
+
"encoder.layers.25.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 298 |
+
"encoder.layers.25.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 299 |
+
"encoder.layers.26.fc1.bias": "model-00001-of-00005.safetensors",
|
| 300 |
+
"encoder.layers.26.fc1.weight": "model-00001-of-00005.safetensors",
|
| 301 |
+
"encoder.layers.26.fc2.bias": "model-00001-of-00005.safetensors",
|
| 302 |
+
"encoder.layers.26.fc2.weight": "model-00001-of-00005.safetensors",
|
| 303 |
+
"encoder.layers.26.final_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 304 |
+
"encoder.layers.26.final_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 305 |
+
"encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 306 |
+
"encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
|
| 307 |
+
"encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
|
| 308 |
+
"encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
| 309 |
+
"encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 310 |
+
"encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
| 311 |
+
"encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 312 |
+
"encoder.layers.26.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 313 |
+
"encoder.layers.26.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 314 |
+
"encoder.layers.27.fc1.bias": "model-00001-of-00005.safetensors",
|
| 315 |
+
"encoder.layers.27.fc1.weight": "model-00001-of-00005.safetensors",
|
| 316 |
+
"encoder.layers.27.fc2.bias": "model-00001-of-00005.safetensors",
|
| 317 |
+
"encoder.layers.27.fc2.weight": "model-00001-of-00005.safetensors",
|
| 318 |
+
"encoder.layers.27.final_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 319 |
+
"encoder.layers.27.final_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 320 |
+
"encoder.layers.27.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 321 |
+
"encoder.layers.27.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
|
| 322 |
+
"encoder.layers.27.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
|
| 323 |
+
"encoder.layers.27.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
| 324 |
+
"encoder.layers.27.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 325 |
+
"encoder.layers.27.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
| 326 |
+
"encoder.layers.27.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 327 |
+
"encoder.layers.27.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 328 |
+
"encoder.layers.27.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 329 |
+
"encoder.layers.28.fc1.bias": "model-00001-of-00005.safetensors",
|
| 330 |
+
"encoder.layers.28.fc1.weight": "model-00001-of-00005.safetensors",
|
| 331 |
+
"encoder.layers.28.fc2.bias": "model-00001-of-00005.safetensors",
|
| 332 |
+
"encoder.layers.28.fc2.weight": "model-00001-of-00005.safetensors",
|
| 333 |
+
"encoder.layers.28.final_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 334 |
+
"encoder.layers.28.final_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 335 |
+
"encoder.layers.28.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 336 |
+
"encoder.layers.28.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
|
| 337 |
+
"encoder.layers.28.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
|
| 338 |
+
"encoder.layers.28.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
| 339 |
+
"encoder.layers.28.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 340 |
+
"encoder.layers.28.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
| 341 |
+
"encoder.layers.28.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 342 |
+
"encoder.layers.28.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 343 |
+
"encoder.layers.28.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 344 |
+
"encoder.layers.29.fc1.bias": "model-00001-of-00005.safetensors",
|
| 345 |
+
"encoder.layers.29.fc1.weight": "model-00001-of-00005.safetensors",
|
| 346 |
+
"encoder.layers.29.fc2.bias": "model-00001-of-00005.safetensors",
|
| 347 |
+
"encoder.layers.29.fc2.weight": "model-00001-of-00005.safetensors",
|
| 348 |
+
"encoder.layers.29.final_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 349 |
+
"encoder.layers.29.final_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 350 |
+
"encoder.layers.29.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 351 |
+
"encoder.layers.29.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
|
| 352 |
+
"encoder.layers.29.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
|
| 353 |
+
"encoder.layers.29.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
| 354 |
+
"encoder.layers.29.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 355 |
+
"encoder.layers.29.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
| 356 |
+
"encoder.layers.29.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 357 |
+
"encoder.layers.29.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 358 |
+
"encoder.layers.29.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 359 |
+
"encoder.layers.3.fc1.bias": "model-00001-of-00005.safetensors",
|
| 360 |
+
"encoder.layers.3.fc1.weight": "model-00001-of-00005.safetensors",
|
| 361 |
+
"encoder.layers.3.fc2.bias": "model-00001-of-00005.safetensors",
|
| 362 |
+
"encoder.layers.3.fc2.weight": "model-00001-of-00005.safetensors",
|
| 363 |
+
"encoder.layers.3.final_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 364 |
+
"encoder.layers.3.final_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 365 |
+
"encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 366 |
+
"encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
|
| 367 |
+
"encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
|
| 368 |
+
"encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
| 369 |
+
"encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 370 |
+
"encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
| 371 |
+
"encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 372 |
+
"encoder.layers.3.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 373 |
+
"encoder.layers.3.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 374 |
+
"encoder.layers.30.fc1.bias": "model-00001-of-00005.safetensors",
|
| 375 |
+
"encoder.layers.30.fc1.weight": "model-00001-of-00005.safetensors",
|
| 376 |
+
"encoder.layers.30.fc2.bias": "model-00001-of-00005.safetensors",
|
| 377 |
+
"encoder.layers.30.fc2.weight": "model-00001-of-00005.safetensors",
|
| 378 |
+
"encoder.layers.30.final_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 379 |
+
"encoder.layers.30.final_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 380 |
+
"encoder.layers.30.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 381 |
+
"encoder.layers.30.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
|
| 382 |
+
"encoder.layers.30.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
|
| 383 |
+
"encoder.layers.30.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
| 384 |
+
"encoder.layers.30.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 385 |
+
"encoder.layers.30.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
| 386 |
+
"encoder.layers.30.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 387 |
+
"encoder.layers.30.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 388 |
+
"encoder.layers.30.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 389 |
+
"encoder.layers.31.fc1.bias": "model-00001-of-00005.safetensors",
|
| 390 |
+
"encoder.layers.31.fc1.weight": "model-00001-of-00005.safetensors",
|
| 391 |
+
"encoder.layers.31.fc2.bias": "model-00001-of-00005.safetensors",
|
| 392 |
+
"encoder.layers.31.fc2.weight": "model-00001-of-00005.safetensors",
|
| 393 |
+
"encoder.layers.31.final_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 394 |
+
"encoder.layers.31.final_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 395 |
+
"encoder.layers.31.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 396 |
+
"encoder.layers.31.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
|
| 397 |
+
"encoder.layers.31.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
|
| 398 |
+
"encoder.layers.31.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
| 399 |
+
"encoder.layers.31.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 400 |
+
"encoder.layers.31.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
| 401 |
+
"encoder.layers.31.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 402 |
+
"encoder.layers.31.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 403 |
+
"encoder.layers.31.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 404 |
+
"encoder.layers.4.fc1.bias": "model-00001-of-00005.safetensors",
|
| 405 |
+
"encoder.layers.4.fc1.weight": "model-00001-of-00005.safetensors",
|
| 406 |
+
"encoder.layers.4.fc2.bias": "model-00001-of-00005.safetensors",
|
| 407 |
+
"encoder.layers.4.fc2.weight": "model-00001-of-00005.safetensors",
|
| 408 |
+
"encoder.layers.4.final_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 409 |
+
"encoder.layers.4.final_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 410 |
+
"encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 411 |
+
"encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
|
| 412 |
+
"encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
|
| 413 |
+
"encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
| 414 |
+
"encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 415 |
+
"encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
| 416 |
+
"encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 417 |
+
"encoder.layers.4.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 418 |
+
"encoder.layers.4.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 419 |
+
"encoder.layers.5.fc1.bias": "model-00001-of-00005.safetensors",
|
| 420 |
+
"encoder.layers.5.fc1.weight": "model-00001-of-00005.safetensors",
|
| 421 |
+
"encoder.layers.5.fc2.bias": "model-00001-of-00005.safetensors",
|
| 422 |
+
"encoder.layers.5.fc2.weight": "model-00001-of-00005.safetensors",
|
| 423 |
+
"encoder.layers.5.final_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 424 |
+
"encoder.layers.5.final_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 425 |
+
"encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 426 |
+
"encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
|
| 427 |
+
"encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
|
| 428 |
+
"encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
| 429 |
+
"encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 430 |
+
"encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
| 431 |
+
"encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 432 |
+
"encoder.layers.5.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 433 |
+
"encoder.layers.5.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 434 |
+
"encoder.layers.6.fc1.bias": "model-00001-of-00005.safetensors",
|
| 435 |
+
"encoder.layers.6.fc1.weight": "model-00001-of-00005.safetensors",
|
| 436 |
+
"encoder.layers.6.fc2.bias": "model-00001-of-00005.safetensors",
|
| 437 |
+
"encoder.layers.6.fc2.weight": "model-00001-of-00005.safetensors",
|
| 438 |
+
"encoder.layers.6.final_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 439 |
+
"encoder.layers.6.final_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 440 |
+
"encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 441 |
+
"encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
|
| 442 |
+
"encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
|
| 443 |
+
"encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
| 444 |
+
"encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 445 |
+
"encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
| 446 |
+
"encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 447 |
+
"encoder.layers.6.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 448 |
+
"encoder.layers.6.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 449 |
+
"encoder.layers.7.fc1.bias": "model-00001-of-00005.safetensors",
|
| 450 |
+
"encoder.layers.7.fc1.weight": "model-00001-of-00005.safetensors",
|
| 451 |
+
"encoder.layers.7.fc2.bias": "model-00001-of-00005.safetensors",
|
| 452 |
+
"encoder.layers.7.fc2.weight": "model-00001-of-00005.safetensors",
|
| 453 |
+
"encoder.layers.7.final_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 454 |
+
"encoder.layers.7.final_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 455 |
+
"encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 456 |
+
"encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
|
| 457 |
+
"encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
|
| 458 |
+
"encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
| 459 |
+
"encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 460 |
+
"encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
| 461 |
+
"encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 462 |
+
"encoder.layers.7.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 463 |
+
"encoder.layers.7.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 464 |
+
"encoder.layers.8.fc1.bias": "model-00001-of-00005.safetensors",
|
| 465 |
+
"encoder.layers.8.fc1.weight": "model-00001-of-00005.safetensors",
|
| 466 |
+
"encoder.layers.8.fc2.bias": "model-00001-of-00005.safetensors",
|
| 467 |
+
"encoder.layers.8.fc2.weight": "model-00001-of-00005.safetensors",
|
| 468 |
+
"encoder.layers.8.final_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 469 |
+
"encoder.layers.8.final_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 470 |
+
"encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 471 |
+
"encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
|
| 472 |
+
"encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
|
| 473 |
+
"encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
| 474 |
+
"encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 475 |
+
"encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
| 476 |
+
"encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 477 |
+
"encoder.layers.8.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 478 |
+
"encoder.layers.8.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 479 |
+
"encoder.layers.9.fc1.bias": "model-00001-of-00005.safetensors",
|
| 480 |
+
"encoder.layers.9.fc1.weight": "model-00001-of-00005.safetensors",
|
| 481 |
+
"encoder.layers.9.fc2.bias": "model-00001-of-00005.safetensors",
|
| 482 |
+
"encoder.layers.9.fc2.weight": "model-00001-of-00005.safetensors",
|
| 483 |
+
"encoder.layers.9.final_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 484 |
+
"encoder.layers.9.final_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 485 |
+
"encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
| 486 |
+
"encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00005.safetensors",
|
| 487 |
+
"encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00005.safetensors",
|
| 488 |
+
"encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",
|
| 489 |
+
"encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
| 490 |
+
"encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",
|
| 491 |
+
"encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
| 492 |
+
"encoder.layers.9.self_attn_layer_norm.bias": "model-00001-of-00005.safetensors",
|
| 493 |
+
"encoder.layers.9.self_attn_layer_norm.weight": "model-00001-of-00005.safetensors",
|
| 494 |
+
"language_model.model.embed_tokens.weight": "model-00002-of-00005.safetensors",
|
| 495 |
+
"language_model.model.layers.0.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 496 |
+
"language_model.model.layers.0.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 497 |
+
"language_model.model.layers.0.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 498 |
+
"language_model.model.layers.0.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 499 |
+
"language_model.model.layers.0.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 500 |
+
"language_model.model.layers.0.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 501 |
+
"language_model.model.layers.0.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 502 |
+
"language_model.model.layers.0.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 503 |
+
"language_model.model.layers.0.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 504 |
+
"language_model.model.layers.1.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 505 |
+
"language_model.model.layers.1.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 506 |
+
"language_model.model.layers.1.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 507 |
+
"language_model.model.layers.1.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 508 |
+
"language_model.model.layers.1.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 509 |
+
"language_model.model.layers.1.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 510 |
+
"language_model.model.layers.1.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 511 |
+
"language_model.model.layers.1.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 512 |
+
"language_model.model.layers.1.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 513 |
+
"language_model.model.layers.10.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 514 |
+
"language_model.model.layers.10.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 515 |
+
"language_model.model.layers.10.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 516 |
+
"language_model.model.layers.10.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 517 |
+
"language_model.model.layers.10.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 518 |
+
"language_model.model.layers.10.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 519 |
+
"language_model.model.layers.10.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 520 |
+
"language_model.model.layers.10.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 521 |
+
"language_model.model.layers.10.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 522 |
+
"language_model.model.layers.11.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 523 |
+
"language_model.model.layers.11.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 524 |
+
"language_model.model.layers.11.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 525 |
+
"language_model.model.layers.11.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 526 |
+
"language_model.model.layers.11.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 527 |
+
"language_model.model.layers.11.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 528 |
+
"language_model.model.layers.11.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 529 |
+
"language_model.model.layers.11.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 530 |
+
"language_model.model.layers.11.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 531 |
+
"language_model.model.layers.12.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 532 |
+
"language_model.model.layers.12.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 533 |
+
"language_model.model.layers.12.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 534 |
+
"language_model.model.layers.12.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 535 |
+
"language_model.model.layers.12.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 536 |
+
"language_model.model.layers.12.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 537 |
+
"language_model.model.layers.12.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 538 |
+
"language_model.model.layers.12.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 539 |
+
"language_model.model.layers.12.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 540 |
+
"language_model.model.layers.13.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 541 |
+
"language_model.model.layers.13.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 542 |
+
"language_model.model.layers.13.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 543 |
+
"language_model.model.layers.13.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 544 |
+
"language_model.model.layers.13.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 545 |
+
"language_model.model.layers.13.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 546 |
+
"language_model.model.layers.13.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 547 |
+
"language_model.model.layers.13.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 548 |
+
"language_model.model.layers.13.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 549 |
+
"language_model.model.layers.14.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 550 |
+
"language_model.model.layers.14.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 551 |
+
"language_model.model.layers.14.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 552 |
+
"language_model.model.layers.14.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 553 |
+
"language_model.model.layers.14.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 554 |
+
"language_model.model.layers.14.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 555 |
+
"language_model.model.layers.14.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 556 |
+
"language_model.model.layers.14.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 557 |
+
"language_model.model.layers.14.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 558 |
+
"language_model.model.layers.15.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 559 |
+
"language_model.model.layers.15.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 560 |
+
"language_model.model.layers.15.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 561 |
+
"language_model.model.layers.15.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 562 |
+
"language_model.model.layers.15.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 563 |
+
"language_model.model.layers.15.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 564 |
+
"language_model.model.layers.15.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 565 |
+
"language_model.model.layers.15.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 566 |
+
"language_model.model.layers.15.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 567 |
+
"language_model.model.layers.16.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 568 |
+
"language_model.model.layers.16.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 569 |
+
"language_model.model.layers.16.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 570 |
+
"language_model.model.layers.16.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 571 |
+
"language_model.model.layers.16.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 572 |
+
"language_model.model.layers.16.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 573 |
+
"language_model.model.layers.16.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 574 |
+
"language_model.model.layers.16.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 575 |
+
"language_model.model.layers.16.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 576 |
+
"language_model.model.layers.17.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 577 |
+
"language_model.model.layers.17.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 578 |
+
"language_model.model.layers.17.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 579 |
+
"language_model.model.layers.17.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 580 |
+
"language_model.model.layers.17.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 581 |
+
"language_model.model.layers.17.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 582 |
+
"language_model.model.layers.17.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 583 |
+
"language_model.model.layers.17.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 584 |
+
"language_model.model.layers.17.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 585 |
+
"language_model.model.layers.18.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 586 |
+
"language_model.model.layers.18.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 587 |
+
"language_model.model.layers.18.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 588 |
+
"language_model.model.layers.18.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 589 |
+
"language_model.model.layers.18.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 590 |
+
"language_model.model.layers.18.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 591 |
+
"language_model.model.layers.18.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 592 |
+
"language_model.model.layers.18.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 593 |
+
"language_model.model.layers.18.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 594 |
+
"language_model.model.layers.19.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 595 |
+
"language_model.model.layers.19.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 596 |
+
"language_model.model.layers.19.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 597 |
+
"language_model.model.layers.19.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 598 |
+
"language_model.model.layers.19.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 599 |
+
"language_model.model.layers.19.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 600 |
+
"language_model.model.layers.19.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 601 |
+
"language_model.model.layers.19.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 602 |
+
"language_model.model.layers.19.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 603 |
+
"language_model.model.layers.2.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 604 |
+
"language_model.model.layers.2.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 605 |
+
"language_model.model.layers.2.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 606 |
+
"language_model.model.layers.2.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 607 |
+
"language_model.model.layers.2.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 608 |
+
"language_model.model.layers.2.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 609 |
+
"language_model.model.layers.2.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 610 |
+
"language_model.model.layers.2.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 611 |
+
"language_model.model.layers.2.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 612 |
+
"language_model.model.layers.20.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 613 |
+
"language_model.model.layers.20.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 614 |
+
"language_model.model.layers.20.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 615 |
+
"language_model.model.layers.20.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 616 |
+
"language_model.model.layers.20.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 617 |
+
"language_model.model.layers.20.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 618 |
+
"language_model.model.layers.20.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 619 |
+
"language_model.model.layers.20.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 620 |
+
"language_model.model.layers.20.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 621 |
+
"language_model.model.layers.21.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 622 |
+
"language_model.model.layers.21.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 623 |
+
"language_model.model.layers.21.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 624 |
+
"language_model.model.layers.21.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 625 |
+
"language_model.model.layers.21.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 626 |
+
"language_model.model.layers.21.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 627 |
+
"language_model.model.layers.21.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 628 |
+
"language_model.model.layers.21.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 629 |
+
"language_model.model.layers.21.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 630 |
+
"language_model.model.layers.22.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 631 |
+
"language_model.model.layers.22.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 632 |
+
"language_model.model.layers.22.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 633 |
+
"language_model.model.layers.22.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 634 |
+
"language_model.model.layers.22.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 635 |
+
"language_model.model.layers.22.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 636 |
+
"language_model.model.layers.22.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 637 |
+
"language_model.model.layers.22.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 638 |
+
"language_model.model.layers.22.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 639 |
+
"language_model.model.layers.23.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 640 |
+
"language_model.model.layers.23.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 641 |
+
"language_model.model.layers.23.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 642 |
+
"language_model.model.layers.23.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 643 |
+
"language_model.model.layers.23.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 644 |
+
"language_model.model.layers.23.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 645 |
+
"language_model.model.layers.23.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 646 |
+
"language_model.model.layers.23.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 647 |
+
"language_model.model.layers.23.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 648 |
+
"language_model.model.layers.24.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 649 |
+
"language_model.model.layers.24.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
| 650 |
+
"language_model.model.layers.24.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 651 |
+
"language_model.model.layers.24.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
| 652 |
+
"language_model.model.layers.24.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
| 653 |
+
"language_model.model.layers.24.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 654 |
+
"language_model.model.layers.24.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 655 |
+
"language_model.model.layers.24.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 656 |
+
"language_model.model.layers.24.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 657 |
+
"language_model.model.layers.25.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 658 |
+
"language_model.model.layers.25.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
| 659 |
+
"language_model.model.layers.25.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
| 660 |
+
"language_model.model.layers.25.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
| 661 |
+
"language_model.model.layers.25.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 662 |
+
"language_model.model.layers.25.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
| 663 |
+
"language_model.model.layers.25.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
| 664 |
+
"language_model.model.layers.25.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
| 665 |
+
"language_model.model.layers.25.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
| 666 |
+
"language_model.model.layers.26.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 667 |
+
"language_model.model.layers.26.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
| 668 |
+
"language_model.model.layers.26.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
| 669 |
+
"language_model.model.layers.26.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
| 670 |
+
"language_model.model.layers.26.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 671 |
+
"language_model.model.layers.26.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
| 672 |
+
"language_model.model.layers.26.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
| 673 |
+
"language_model.model.layers.26.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
| 674 |
+
"language_model.model.layers.26.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
| 675 |
+
"language_model.model.layers.27.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 676 |
+
"language_model.model.layers.27.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
| 677 |
+
"language_model.model.layers.27.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
| 678 |
+
"language_model.model.layers.27.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
| 679 |
+
"language_model.model.layers.27.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
| 680 |
+
"language_model.model.layers.27.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
| 681 |
+
"language_model.model.layers.27.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
| 682 |
+
"language_model.model.layers.27.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
| 683 |
+
"language_model.model.layers.27.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
| 684 |
+
"language_model.model.layers.3.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 685 |
+
"language_model.model.layers.3.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 686 |
+
"language_model.model.layers.3.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 687 |
+
"language_model.model.layers.3.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 688 |
+
"language_model.model.layers.3.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 689 |
+
"language_model.model.layers.3.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 690 |
+
"language_model.model.layers.3.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 691 |
+
"language_model.model.layers.3.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 692 |
+
"language_model.model.layers.3.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 693 |
+
"language_model.model.layers.4.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 694 |
+
"language_model.model.layers.4.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 695 |
+
"language_model.model.layers.4.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 696 |
+
"language_model.model.layers.4.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 697 |
+
"language_model.model.layers.4.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 698 |
+
"language_model.model.layers.4.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 699 |
+
"language_model.model.layers.4.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 700 |
+
"language_model.model.layers.4.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 701 |
+
"language_model.model.layers.4.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 702 |
+
"language_model.model.layers.5.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 703 |
+
"language_model.model.layers.5.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
| 704 |
+
"language_model.model.layers.5.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
| 705 |
+
"language_model.model.layers.5.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
| 706 |
+
"language_model.model.layers.5.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
| 707 |
+
"language_model.model.layers.5.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
| 708 |
+
"language_model.model.layers.5.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
| 709 |
+
"language_model.model.layers.5.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
| 710 |
+
"language_model.model.layers.5.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
| 711 |
+
"language_model.model.layers.6.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 712 |
+
"language_model.model.layers.6.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 713 |
+
"language_model.model.layers.6.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 714 |
+
"language_model.model.layers.6.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 715 |
+
"language_model.model.layers.6.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 716 |
+
"language_model.model.layers.6.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 717 |
+
"language_model.model.layers.6.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 718 |
+
"language_model.model.layers.6.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 719 |
+
"language_model.model.layers.6.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 720 |
+
"language_model.model.layers.7.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 721 |
+
"language_model.model.layers.7.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 722 |
+
"language_model.model.layers.7.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 723 |
+
"language_model.model.layers.7.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 724 |
+
"language_model.model.layers.7.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 725 |
+
"language_model.model.layers.7.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 726 |
+
"language_model.model.layers.7.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 727 |
+
"language_model.model.layers.7.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 728 |
+
"language_model.model.layers.7.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 729 |
+
"language_model.model.layers.8.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 730 |
+
"language_model.model.layers.8.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 731 |
+
"language_model.model.layers.8.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 732 |
+
"language_model.model.layers.8.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 733 |
+
"language_model.model.layers.8.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 734 |
+
"language_model.model.layers.8.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 735 |
+
"language_model.model.layers.8.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 736 |
+
"language_model.model.layers.8.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 737 |
+
"language_model.model.layers.8.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 738 |
+
"language_model.model.layers.9.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 739 |
+
"language_model.model.layers.9.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
| 740 |
+
"language_model.model.layers.9.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
| 741 |
+
"language_model.model.layers.9.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
| 742 |
+
"language_model.model.layers.9.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
| 743 |
+
"language_model.model.layers.9.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
| 744 |
+
"language_model.model.layers.9.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
| 745 |
+
"language_model.model.layers.9.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
| 746 |
+
"language_model.model.layers.9.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
| 747 |
+
"language_model.model.norm.weight": "model-00005-of-00005.safetensors",
|
| 748 |
+
"projector.linear_1.weight": "model-00001-of-00005.safetensors",
|
| 749 |
+
"projector.linear_2.weight": "model-00001-of-00005.safetensors",
|
| 750 |
+
"projector.ln_mid.weight": "model-00001-of-00005.safetensors",
|
| 751 |
+
"projector.ln_pre.weight": "model-00001-of-00005.safetensors"
|
| 752 |
+
}
|
| 753 |
+
}
|
modeling_vlfm.py
ADDED
|
@@ -0,0 +1,296 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import torch
|
| 2 |
+
import torch.nn as nn
|
| 3 |
+
import torch.nn.functional as F
|
| 4 |
+
import transformers
|
| 5 |
+
from transformers import (
|
| 6 |
+
AutoConfig, AutoModel,
|
| 7 |
+
AutoModelForCausalLM, WhisperModel)
|
| 8 |
+
|
| 9 |
+
from configs import VLFMConfig, LossFunction, LossConfig, build_tokenizer
|
| 10 |
+
from projector import VLFMProjector
|
| 11 |
+
from constants import IGNORE_INDEX, SPEECH_TOKEN_INDEX
|
| 12 |
+
|
| 13 |
+
from transformers.modeling_outputs import CausalLMOutputWithPast
|
| 14 |
+
from transformers.generation.utils import GenerateOutput
|
| 15 |
+
from typing import Optional, Tuple, List, Union
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
class VLFMModel(transformers.LlamaPreTrainedModel):
|
| 19 |
+
config_class = VLFMConfig
|
| 20 |
+
def __init__(self, config, torch_dtype=torch.bfloat16):
|
| 21 |
+
super(VLFMModel, self).__init__(config)
|
| 22 |
+
|
| 23 |
+
whisper = WhisperModel.from_pretrained(config.audio_model_id,
|
| 24 |
+
torch_dtype=torch_dtype,)
|
| 25 |
+
|
| 26 |
+
self.encoder = whisper.encoder
|
| 27 |
+
self.projector = VLFMProjector(config)
|
| 28 |
+
self.language_model = AutoModelForCausalLM.from_pretrained(config.text_model_id,
|
| 29 |
+
torch_dtype=torch_dtype)
|
| 30 |
+
|
| 31 |
+
self._train_module(self.encoder, False)
|
| 32 |
+
self._train_module(self.language_model, False)
|
| 33 |
+
self._train_module(self.projector, True)
|
| 34 |
+
|
| 35 |
+
self.encoder.to(dtype=torch_dtype)
|
| 36 |
+
self.language_model.to(dtype=torch_dtype)
|
| 37 |
+
self.projector.to(dtype=torch_dtype)
|
| 38 |
+
|
| 39 |
+
self.tokenizer, self.audio_token_id = build_tokenizer(config.text_model_id, config.tokenizer_padding_side)
|
| 40 |
+
|
| 41 |
+
self.tokenizer_model_max_length = self.tokenizer.model_max_length
|
| 42 |
+
self._resize_token_embeddings(self.tokenizer)
|
| 43 |
+
self.get_input_embeddings().to(dtype=self.language_model.dtype)
|
| 44 |
+
if hasattr(self.language_model, "get_output_embeddings") and self.language_model.get_output_embeddings() is not None:
|
| 45 |
+
self.language_model.get_output_embeddings().to(dtype=self.language_model.dtype)
|
| 46 |
+
|
| 47 |
+
self.loss_config = LossConfig(LossFunction.KL_Divergence)
|
| 48 |
+
#self.loss_config.loss_function = LossFunction.KL_Divergence
|
| 49 |
+
|
| 50 |
+
self.post_init()
|
| 51 |
+
|
| 52 |
+
def get_input_embeddings(self):
|
| 53 |
+
return self.language_model.get_input_embeddings()
|
| 54 |
+
|
| 55 |
+
def set_input_embeddings(self, new_emb):
|
| 56 |
+
return self.language_model.set_input_embeddings(new_emb)
|
| 57 |
+
|
| 58 |
+
@property
|
| 59 |
+
def embed_tokens(self):
|
| 60 |
+
return self.language_model.get_input_embeddings()
|
| 61 |
+
|
| 62 |
+
def _train_module(self, module, trainable: bool):
|
| 63 |
+
for param in module.parameters():
|
| 64 |
+
param.requires_grad= trainable
|
| 65 |
+
|
| 66 |
+
def _audio_iter(self, audio_batch_size):
|
| 67 |
+
audio_index = 0
|
| 68 |
+
for i_b, count in enumerate(audio_batch_size.view(-1).tolist()):
|
| 69 |
+
for _ in range(int(count)):
|
| 70 |
+
yield i_b, audio_index
|
| 71 |
+
audio_index += 1
|
| 72 |
+
|
| 73 |
+
def _resize_token_embeddings(self, tokenizer, pad_to_multiple_of=None):
|
| 74 |
+
|
| 75 |
+
model_embeds = self.language_model.resize_token_embeddings(len(tokenizer))
|
| 76 |
+
self.config.vocab_size = model_embeds.num_embeddings
|
| 77 |
+
self.vocab_size = model_embeds.num_embeddings
|
| 78 |
+
return model_embeds
|
| 79 |
+
|
| 80 |
+
def _encode_speech(self, audio_values):
|
| 81 |
+
with torch.no_grad():
|
| 82 |
+
encoder_outputs = self.encoder(audio_values, output_hidden_states=False)
|
| 83 |
+
audio_embeds = encoder_outputs.last_hidden_state
|
| 84 |
+
downsampled_embeds = self.projector(audio_embeds) #(B, T, D)
|
| 85 |
+
#print(f"Shape of projector output: {downsampled_embeds.shape}")
|
| 86 |
+
return downsampled_embeds
|
| 87 |
+
|
| 88 |
+
def _splice_chunks(self, text_embeds, audio_embeds, audio_token_start_idx, audio_token_len, audio_batch_size):
|
| 89 |
+
D = text_embeds.size(-1)
|
| 90 |
+
for i_b, i_chunk in self._audio_iter(audio_batch_size):
|
| 91 |
+
start = int(audio_token_start_idx[i_chunk].item())
|
| 92 |
+
span = int(audio_token_len[i_chunk].item())
|
| 93 |
+
a = audio_embeds[i_chunk]
|
| 94 |
+
Ta = a.size(0)
|
| 95 |
+
use = min(Ta, span)
|
| 96 |
+
text_embeds[i_b, start:start+use, :] = a[:use].to(text_embeds.dtype)
|
| 97 |
+
|
| 98 |
+
|
| 99 |
+
def _compute_kl_loss(
|
| 100 |
+
self,
|
| 101 |
+
*,
|
| 102 |
+
student_logits: torch.Tensor,
|
| 103 |
+
labels: torch.Tensor,
|
| 104 |
+
alt_input_ids: torch.Tensor,
|
| 105 |
+
alt_attention_mask: torch.Tensor,
|
| 106 |
+
alt_labels: torch.Tensor,
|
| 107 |
+
past_key_values=None,
|
| 108 |
+
**kwargs,
|
| 109 |
+
):
|
| 110 |
+
lm_was_training = self.language_model.training
|
| 111 |
+
self.language_model.eval()
|
| 112 |
+
with torch.no_grad():
|
| 113 |
+
alt_input_embeds = self.language_model.get_input_embeddings()(alt_input_ids)
|
| 114 |
+
teacher_out = self.language_model(
|
| 115 |
+
inputs_embeds=alt_input_embeds,
|
| 116 |
+
attention_mask=alt_attention_mask,
|
| 117 |
+
use_cache=False,
|
| 118 |
+
return_dict=True,
|
| 119 |
+
past_key_values=past_key_values,
|
| 120 |
+
)
|
| 121 |
+
teacher_logits = teacher_out.logits
|
| 122 |
+
if lm_was_training:
|
| 123 |
+
self.language_model.train()
|
| 124 |
+
|
| 125 |
+
T = self.loss_config.kl_temperature
|
| 126 |
+
student = F.log_softmax(student_logits[labels != IGNORE_INDEX] / T, dim=-1)
|
| 127 |
+
teacher = F.softmax(teacher_logits[alt_labels != IGNORE_INDEX] / T, dim=-1)
|
| 128 |
+
kl = F.kl_div(student, teacher, reduction="batchmean")
|
| 129 |
+
return kl
|
| 130 |
+
|
| 131 |
+
|
| 132 |
+
|
| 133 |
+
def forward(
|
| 134 |
+
self,
|
| 135 |
+
input_ids,
|
| 136 |
+
attention_mask,
|
| 137 |
+
labels=None,
|
| 138 |
+
*,
|
| 139 |
+
input_features=None,
|
| 140 |
+
audio_token_start_idx = None,
|
| 141 |
+
audio_token_len = None,
|
| 142 |
+
audio_batch_size = None,
|
| 143 |
+
alt_input_ids = None,
|
| 144 |
+
alt_attention_mask = None,
|
| 145 |
+
alt_labels = None,
|
| 146 |
+
return_dict = True,
|
| 147 |
+
**kwargs):
|
| 148 |
+
tok = self.language_model.get_input_embeddings()
|
| 149 |
+
text_embeds = tok(input_ids)
|
| 150 |
+
|
| 151 |
+
if input_features is not None and audio_token_start_idx is not None:
|
| 152 |
+
audio_embeds = self._encode_speech(input_features)
|
| 153 |
+
self._splice_chunks(
|
| 154 |
+
text_embeds,
|
| 155 |
+
audio_embeds,
|
| 156 |
+
audio_token_start_idx,
|
| 157 |
+
audio_token_len,
|
| 158 |
+
audio_batch_size
|
| 159 |
+
)
|
| 160 |
+
|
| 161 |
+
out = self.language_model(
|
| 162 |
+
inputs_embeds=text_embeds,
|
| 163 |
+
attention_mask=attention_mask,
|
| 164 |
+
labels =labels,
|
| 165 |
+
return_dict=True,
|
| 166 |
+
use_cache = True,
|
| 167 |
+
)
|
| 168 |
+
|
| 169 |
+
logits = out.logits
|
| 170 |
+
ce_loss = out.loss
|
| 171 |
+
|
| 172 |
+
alpha = self.loss_config.ce_weight
|
| 173 |
+
alpha = self.loss_config.ce_weight
|
| 174 |
+
|
| 175 |
+
kl = None
|
| 176 |
+
if (
|
| 177 |
+
self.training
|
| 178 |
+
and alt_input_ids is not None
|
| 179 |
+
and alt_attention_mask is not None
|
| 180 |
+
and alt_labels is not None
|
| 181 |
+
):
|
| 182 |
+
|
| 183 |
+
kl = self._compute_kl_loss(
|
| 184 |
+
student_logits=logits,
|
| 185 |
+
labels=labels,
|
| 186 |
+
alt_input_ids=alt_input_ids,
|
| 187 |
+
alt_attention_mask=alt_attention_mask,
|
| 188 |
+
alt_labels=alt_labels,
|
| 189 |
+
past_key_values=None,
|
| 190 |
+
)
|
| 191 |
+
|
| 192 |
+
total_loss = alpha * ce_loss + (1 - alpha) * kl
|
| 193 |
+
else:
|
| 194 |
+
total_loss = ce_loss
|
| 195 |
+
|
| 196 |
+
return {
|
| 197 |
+
"loss": total_loss,
|
| 198 |
+
"loss_ce": ce_loss.detach() if ce_loss is not None else None,
|
| 199 |
+
"loss_kl": kl.detach() if kl is not None else None,
|
| 200 |
+
"logits": logits,}
|
| 201 |
+
|
| 202 |
+
|
| 203 |
+
''' if (
|
| 204 |
+
self.training
|
| 205 |
+
and self.loss_config.loss_function == LossFunction.KL_Divergence
|
| 206 |
+
and alt_input_ids is not None
|
| 207 |
+
and alt_attention_mask is not None
|
| 208 |
+
and alt_labels is not None
|
| 209 |
+
|
| 210 |
+
):
|
| 211 |
+
kl = self._compute_kl_loss(
|
| 212 |
+
student_logits=logits,
|
| 213 |
+
labels=labels,
|
| 214 |
+
alt_input_ids=alt_input_ids,
|
| 215 |
+
alt_attention_mask=alt_attention_mask,
|
| 216 |
+
alt_labels=alt_labels,
|
| 217 |
+
past_key_values=None,)
|
| 218 |
+
|
| 219 |
+
return {
|
| 220 |
+
"loss": kl,
|
| 221 |
+
"loss_ce": (ce_loss.detach() if ce_loss is not None else None),
|
| 222 |
+
logits: logits}
|
| 223 |
+
|
| 224 |
+
if return_dict:
|
| 225 |
+
return out
|
| 226 |
+
return (ce_loss, logits) '''
|
| 227 |
+
|
| 228 |
+
def _prepare_inputs_embeds(
|
| 229 |
+
self,
|
| 230 |
+
input_ids,
|
| 231 |
+
attention_mask,
|
| 232 |
+
*,
|
| 233 |
+
input_features = None,
|
| 234 |
+
audio_token_start_idx = None,
|
| 235 |
+
audio_token_len = None,
|
| 236 |
+
audio_batch_size= None,
|
| 237 |
+
):
|
| 238 |
+
"""
|
| 239 |
+
Returns:
|
| 240 |
+
inputs_embeds: [B, L, D] with audio spliced in
|
| 241 |
+
attention_mask: [B, L] (unchanged)
|
| 242 |
+
"""
|
| 243 |
+
tok = self.language_model.get_input_embeddings()
|
| 244 |
+
inputs_embeds = tok(input_ids) # [B, L, D]
|
| 245 |
+
|
| 246 |
+
if input_features is not None and audio_token_start_idx is not None:
|
| 247 |
+
# Normalize shapes: treat "one audio per sample" as N_chunks == B
|
| 248 |
+
feats = input_features
|
| 249 |
+
if feats.dim() == 3 and feats.size(0) == input_ids.size(0):
|
| 250 |
+
audio_batch_size = torch.ones(input_ids.size(0), dtype=torch.long, device=input_ids.device)
|
| 251 |
+
assert audio_batch_size is not None, "audio_batch_size required when splicing audio."
|
| 252 |
+
|
| 253 |
+
# Encode + project, then splice
|
| 254 |
+
audio_embeds = self._encode_audio(feats) # [N_chunks, T_audio, D]
|
| 255 |
+
self._splice_chunks(
|
| 256 |
+
text_embeds=inputs_embeds,
|
| 257 |
+
audio_embeds=audio_embeds,
|
| 258 |
+
audio_token_start_idx=audio_token_start_idx,
|
| 259 |
+
audio_token_len=audio_token_len,
|
| 260 |
+
audio_batch_size=audio_batch_size,
|
| 261 |
+
)
|
| 262 |
+
|
| 263 |
+
return inputs_embeds, attention_mask
|
| 264 |
+
|
| 265 |
+
@torch.no_grad()
|
| 266 |
+
def generate(
|
| 267 |
+
self,
|
| 268 |
+
input_ids, # [B, L]
|
| 269 |
+
attention_mask, # [B, L]
|
| 270 |
+
*,
|
| 271 |
+
input_features,
|
| 272 |
+
audio_token_start_idx= None,
|
| 273 |
+
audio_token_len= None,
|
| 274 |
+
audio_batch_size = None,
|
| 275 |
+
**gen_kwargs,
|
| 276 |
+
):
|
| 277 |
+
"""
|
| 278 |
+
Build spliced embeddings and call the base LM's generate"""
|
| 279 |
+
self.eval()
|
| 280 |
+
inputs_embeds, attn_mask = self._prepare_inputs_embeds(
|
| 281 |
+
input_ids=input_ids,
|
| 282 |
+
attention_mask=attention_mask,
|
| 283 |
+
input_features=input_features,
|
| 284 |
+
audio_token_start_idx=audio_token_start_idx,
|
| 285 |
+
audio_token_len=audio_token_len,
|
| 286 |
+
audio_batch_size=audio_batch_size,
|
| 287 |
+
)
|
| 288 |
+
return self.language_model.generate(
|
| 289 |
+
inputs_embeds=inputs_embeds,
|
| 290 |
+
attention_mask=attn_mask,
|
| 291 |
+
**gen_kwargs,
|
| 292 |
+
)
|
| 293 |
+
|
| 294 |
+
|
| 295 |
+
AutoConfig.register("babs-vlfm", VLFMConfig)
|
| 296 |
+
AutoModel.register(VLFMConfig, VLFMModel)
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_map": {
|
| 3 |
+
"AutoProcessor": "processor.VLFMProcessor"
|
| 4 |
+
},
|
| 5 |
+
"chunk_length": 30,
|
| 6 |
+
"dither": 0.0,
|
| 7 |
+
"feature_extractor_type": "WhisperFeatureExtractor",
|
| 8 |
+
"feature_size": 128,
|
| 9 |
+
"hop_length": 160,
|
| 10 |
+
"n_fft": 400,
|
| 11 |
+
"n_samples": 480000,
|
| 12 |
+
"nb_max_frames": 3000,
|
| 13 |
+
"padding_side": "right",
|
| 14 |
+
"padding_value": 0.0,
|
| 15 |
+
"processor_class": "VLFMProcessor",
|
| 16 |
+
"return_attention_mask": false,
|
| 17 |
+
"sampling_rate": 16000
|
| 18 |
+
}
|
processing_vlfm.py
ADDED
|
@@ -0,0 +1,199 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import numpy as np
|
| 2 |
+
import torch
|
| 3 |
+
from typing import List, Dict, Any, Union, Optional
|
| 4 |
+
from transformers.processing_utils import ProcessorMixin
|
| 5 |
+
from transformers import WhisperFeatureExtractor, AutoTokenizer, AutoProcessor
|
| 6 |
+
|
| 7 |
+
from configs import VLFMConfig, build_tokenizer
|
| 8 |
+
|
| 9 |
+
|
| 10 |
+
class VLFMProcessor(ProcessorMixin):
|
| 11 |
+
attributes = ["feature_extractor", "tokenizer"]
|
| 12 |
+
feature_extractor_class = "WhisperFeatureExtractor"
|
| 13 |
+
tokenizer_class = "AutoTokenizer"
|
| 14 |
+
|
| 15 |
+
def __init__(
|
| 16 |
+
self,
|
| 17 |
+
feature_extractor: WhisperFeatureExtractor,
|
| 18 |
+
tokenizer: AutoTokenizer,
|
| 19 |
+
config: VLFMConfig,
|
| 20 |
+
):
|
| 21 |
+
super().__init__(feature_extractor=feature_extractor, tokenizer=tokenizer)
|
| 22 |
+
|
| 23 |
+
_, self.audio_token_id = build_tokenizer(
|
| 24 |
+
config.text_model_id, config.tokenizer_padding_side
|
| 25 |
+
)
|
| 26 |
+
if self.audio_token_id == tokenizer.unk_token_id:
|
| 27 |
+
raise ValueError(
|
| 28 |
+
"Audio placeholder token is <unk>. "
|
| 29 |
+
"Add a real special token (e.g. <|audio|>) to the tokenizer vocab."
|
| 30 |
+
)
|
| 31 |
+
#print(f"audio_placeholder_token_id: {self.audio_token_id}")
|
| 32 |
+
|
| 33 |
+
if tokenizer.pad_token_id is None:
|
| 34 |
+
tokenizer.pad_token = tokenizer.eos_token
|
| 35 |
+
tokenizer.padding_side = config.tokenizer_padding_side
|
| 36 |
+
|
| 37 |
+
|
| 38 |
+
self.ds_rate = int(config.ds_rate)
|
| 39 |
+
self.stack_factor = int(config.stack_factor)
|
| 40 |
+
self.max_seconds = float(config.max_seconds)
|
| 41 |
+
|
| 42 |
+
self._marker = "<AUDIO_SPAN>"
|
| 43 |
+
|
| 44 |
+
def __call__(self, text: Union[str, List[str]], **kwargs) -> Dict[str, Any]:
|
| 45 |
+
if isinstance(text, str):
|
| 46 |
+
text = [text]
|
| 47 |
+
|
| 48 |
+
def _contains_audio_placeholder(s: str) -> bool:
|
| 49 |
+
ids = self.tokenizer(s, add_special_tokens=False)["input_ids"]
|
| 50 |
+
return self.audio_token_id in ids
|
| 51 |
+
|
| 52 |
+
if any(_contains_audio_placeholder(t) for t in text):
|
| 53 |
+
raise ValueError(
|
| 54 |
+
"Audio placeholder token detected in raw text. "
|
| 55 |
+
"Use `apply_chat_template` with {'type': 'audio', 'array': ...} instead."
|
| 56 |
+
)
|
| 57 |
+
|
| 58 |
+
enc = self.tokenizer(text, **kwargs)
|
| 59 |
+
return enc
|
| 60 |
+
|
| 61 |
+
def _validate_audio(self, x: np.ndarray) -> np.ndarray:
|
| 62 |
+
if not isinstance(x, np.ndarray):
|
| 63 |
+
x = np.asarray(x)
|
| 64 |
+
if x.ndim == 2:
|
| 65 |
+
x = x.mean(axis=0) if x.shape[0] < x.shape[1] else x.mean(axis=1)
|
| 66 |
+
elif x.ndim != 1:
|
| 67 |
+
raise ValueError(f"Expected 1-D mono waveform, got shape={x.shape}")
|
| 68 |
+
if x.size == 0 or not np.isfinite(x).all():
|
| 69 |
+
raise ValueError("Audio is empty or contains NaNs/Infs.")
|
| 70 |
+
return x.astype(np.float32, copy=False)
|
| 71 |
+
|
| 72 |
+
def apply_chat_template(
|
| 73 |
+
self,
|
| 74 |
+
conversation: List[Dict],
|
| 75 |
+
*,
|
| 76 |
+
tokenize: bool = False,
|
| 77 |
+
add_generation_prompt: bool = False,
|
| 78 |
+
padding: bool = False,
|
| 79 |
+
truncation: bool = True,
|
| 80 |
+
max_length: int = 4096,
|
| 81 |
+
sampling_rate: Optional[int] = 16_000,
|
| 82 |
+
return_tensors: str = "pt",
|
| 83 |
+
**kwargs,
|
| 84 |
+
) -> Dict[str, Any]:
|
| 85 |
+
"""
|
| 86 |
+
conversation: list of turns, where each turn is:
|
| 87 |
+
{"role": "user" | "assistant" | "system", "content": str | List[{"type": "text"|"audio", ...}]}
|
| 88 |
+
|
| 89 |
+
Exactly one audio span is supported per conversation.
|
| 90 |
+
"""
|
| 91 |
+
|
| 92 |
+
if not isinstance(conversation, list) or not conversation:
|
| 93 |
+
raise ValueError("Conversation must be a non-empty list of turns.")
|
| 94 |
+
|
| 95 |
+
text_conv: List[Dict[str, str]] = []
|
| 96 |
+
audio_array: Optional[np.ndarray] = None
|
| 97 |
+
|
| 98 |
+
for turn in conversation:
|
| 99 |
+
role = turn.get("role", None)
|
| 100 |
+
content = turn.get("content", "")
|
| 101 |
+
|
| 102 |
+
if not isinstance(role, str):
|
| 103 |
+
raise ValueError("Each turn must have a string 'role'.")
|
| 104 |
+
if isinstance(content, str):
|
| 105 |
+
text_conv.append({"role": role, "content": content})
|
| 106 |
+
continue
|
| 107 |
+
|
| 108 |
+
buf: List[str] = []
|
| 109 |
+
for item in content:
|
| 110 |
+
t = item.get("type", None)
|
| 111 |
+
if t == "text":
|
| 112 |
+
buf.append(item.get("text", ""))
|
| 113 |
+
elif t == "audio":
|
| 114 |
+
if audio_array is not None:
|
| 115 |
+
raise ValueError(
|
| 116 |
+
"VLFMProcessor supports exactly one audio span per conversation."
|
| 117 |
+
)
|
| 118 |
+
arr = item.get("array", None)
|
| 119 |
+
if arr is None:
|
| 120 |
+
raise ValueError("Audio item missing 'array'.")
|
| 121 |
+
audio_array = self._validate_audio(arr)
|
| 122 |
+
buf.append(self._marker)
|
| 123 |
+
else:
|
| 124 |
+
raise ValueError(f"Unsupported content type: {t}")
|
| 125 |
+
|
| 126 |
+
text_conv.append({"role": role, "content": "".join(buf)})
|
| 127 |
+
|
| 128 |
+
if audio_array is None:
|
| 129 |
+
raise ValueError("No audio found in conversation (exactly one audio span required).")
|
| 130 |
+
|
| 131 |
+
prompt = self.tokenizer.apply_chat_template(
|
| 132 |
+
text_conv, tokenize=False, add_generation_prompt=add_generation_prompt
|
| 133 |
+
)
|
| 134 |
+
#print(f"Output after apply chat: {prompt}")
|
| 135 |
+
|
| 136 |
+
sr = int(sampling_rate or self.feature_extractor.sampling_rate)
|
| 137 |
+
max_samples = int(self.max_seconds * sr)
|
| 138 |
+
if audio_array.shape[0] > max_samples:
|
| 139 |
+
audio_array = audio_array[:max_samples]
|
| 140 |
+
|
| 141 |
+
hop = int(self.feature_extractor.hop_length)
|
| 142 |
+
if audio_array.shape[0] < 2 * hop:
|
| 143 |
+
audio_array = np.pad(audio_array, (0, 2 * hop - audio_array.shape[0]))
|
| 144 |
+
|
| 145 |
+
feat = self.feature_extractor(
|
| 146 |
+
[audio_array],
|
| 147 |
+
sampling_rate=sr,
|
| 148 |
+
return_attention_mask=True,
|
| 149 |
+
return_tensors="pt",
|
| 150 |
+
**kwargs,
|
| 151 |
+
)
|
| 152 |
+
feats = feat.input_features
|
| 153 |
+
attn = feat.attention_mask
|
| 154 |
+
mel_len = int(attn.sum(-1).item())
|
| 155 |
+
|
| 156 |
+
scale = self.ds_rate * self.stack_factor
|
| 157 |
+
audio_token_len = int(np.ceil(mel_len / float(scale)))
|
| 158 |
+
if audio_token_len <= 0:
|
| 159 |
+
raise ValueError(f"Computed non-positive audio_token_len={audio_token_len} (mel_len={mel_len}).")
|
| 160 |
+
|
| 161 |
+
left, sep, right = prompt.partition(self._marker)
|
| 162 |
+
if sep == "":
|
| 163 |
+
raise ValueError("Internal error: <AUDIO_SPAN> marker missing.")
|
| 164 |
+
|
| 165 |
+
left_ids = self.tokenizer(left, add_special_tokens=False)["input_ids"]
|
| 166 |
+
right_ids = self.tokenizer(right, add_special_tokens=False)["input_ids"]
|
| 167 |
+
|
| 168 |
+
input_ids = left_ids + [self.audio_token_id] * audio_token_len + right_ids
|
| 169 |
+
attention_mask = [1] * len(input_ids)
|
| 170 |
+
audio_token_start_idx = len(left_ids)
|
| 171 |
+
|
| 172 |
+
out = {
|
| 173 |
+
"input_ids": torch.tensor(input_ids, dtype=torch.long),
|
| 174 |
+
"attention_mask": torch.tensor(attention_mask, dtype=torch.long),
|
| 175 |
+
|
| 176 |
+
# Audio side:
|
| 177 |
+
"input_features": feats[0].clone(),
|
| 178 |
+
"audio_lens": torch.tensor([mel_len], dtype=torch.long),
|
| 179 |
+
|
| 180 |
+
# Splicing helpers:
|
| 181 |
+
"audio_token_start_idx": torch.tensor([audio_token_start_idx], dtype=torch.long), # [1]
|
| 182 |
+
"audio_token_len": torch.tensor([audio_token_len], dtype=torch.long), # [1]
|
| 183 |
+
|
| 184 |
+
"audio_batch_size": torch.tensor([1], dtype=torch.long), # [1]
|
| 185 |
+
"audio_is_continuation": torch.tensor([False]), # [1]
|
| 186 |
+
}
|
| 187 |
+
|
| 188 |
+
if tokenize:
|
| 189 |
+
tok = self.tokenizer(
|
| 190 |
+
prompt,
|
| 191 |
+
padding=padding,
|
| 192 |
+
truncation=truncation,
|
| 193 |
+
max_length=max_length,
|
| 194 |
+
return_tensors="pt",
|
| 195 |
+
)
|
| 196 |
+
return out
|
| 197 |
+
|
| 198 |
+
VLFMProcessor.register_for_auto_class()
|
| 199 |
+
AutoProcessor.register(VLFMConfig, VLFMProcessor)
|
processor.py
ADDED
|
@@ -0,0 +1,199 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import numpy as np
|
| 2 |
+
import torch
|
| 3 |
+
from typing import List, Dict, Any, Union, Optional
|
| 4 |
+
from transformers.processing_utils import ProcessorMixin
|
| 5 |
+
from transformers import WhisperFeatureExtractor, AutoTokenizer, AutoProcessor
|
| 6 |
+
|
| 7 |
+
from configs import VLFMConfig, build_tokenizer
|
| 8 |
+
|
| 9 |
+
|
| 10 |
+
class VLFMProcessor(ProcessorMixin):
|
| 11 |
+
attributes = ["feature_extractor", "tokenizer"]
|
| 12 |
+
feature_extractor_class = "WhisperFeatureExtractor"
|
| 13 |
+
tokenizer_class = "AutoTokenizer"
|
| 14 |
+
|
| 15 |
+
def __init__(
|
| 16 |
+
self,
|
| 17 |
+
feature_extractor: WhisperFeatureExtractor,
|
| 18 |
+
tokenizer: AutoTokenizer,
|
| 19 |
+
config: VLFMConfig,
|
| 20 |
+
):
|
| 21 |
+
super().__init__(feature_extractor=feature_extractor, tokenizer=tokenizer)
|
| 22 |
+
|
| 23 |
+
_, self.audio_token_id = build_tokenizer(
|
| 24 |
+
config.text_model_id, config.tokenizer_padding_side
|
| 25 |
+
)
|
| 26 |
+
if self.audio_token_id == tokenizer.unk_token_id:
|
| 27 |
+
raise ValueError(
|
| 28 |
+
"Audio placeholder token is <unk>. "
|
| 29 |
+
"Add a real special token (e.g. <|audio|>) to the tokenizer vocab."
|
| 30 |
+
)
|
| 31 |
+
#print(f"audio_placeholder_token_id: {self.audio_token_id}")
|
| 32 |
+
|
| 33 |
+
if tokenizer.pad_token_id is None:
|
| 34 |
+
tokenizer.pad_token = tokenizer.eos_token
|
| 35 |
+
tokenizer.padding_side = config.tokenizer_padding_side
|
| 36 |
+
|
| 37 |
+
|
| 38 |
+
self.ds_rate = int(config.ds_rate)
|
| 39 |
+
self.stack_factor = int(config.stack_factor)
|
| 40 |
+
self.max_seconds = float(config.max_seconds)
|
| 41 |
+
|
| 42 |
+
self._marker = "<AUDIO_SPAN>"
|
| 43 |
+
|
| 44 |
+
def __call__(self, text: Union[str, List[str]], **kwargs) -> Dict[str, Any]:
|
| 45 |
+
if isinstance(text, str):
|
| 46 |
+
text = [text]
|
| 47 |
+
|
| 48 |
+
def _contains_audio_placeholder(s: str) -> bool:
|
| 49 |
+
ids = self.tokenizer(s, add_special_tokens=False)["input_ids"]
|
| 50 |
+
return self.audio_token_id in ids
|
| 51 |
+
|
| 52 |
+
if any(_contains_audio_placeholder(t) for t in text):
|
| 53 |
+
raise ValueError(
|
| 54 |
+
"Audio placeholder token detected in raw text. "
|
| 55 |
+
"Use `apply_chat_template` with {'type': 'audio', 'array': ...} instead."
|
| 56 |
+
)
|
| 57 |
+
|
| 58 |
+
enc = self.tokenizer(text, **kwargs)
|
| 59 |
+
return enc
|
| 60 |
+
|
| 61 |
+
def _validate_audio(self, x: np.ndarray) -> np.ndarray:
|
| 62 |
+
if not isinstance(x, np.ndarray):
|
| 63 |
+
x = np.asarray(x)
|
| 64 |
+
if x.ndim == 2:
|
| 65 |
+
x = x.mean(axis=0) if x.shape[0] < x.shape[1] else x.mean(axis=1)
|
| 66 |
+
elif x.ndim != 1:
|
| 67 |
+
raise ValueError(f"Expected 1-D mono waveform, got shape={x.shape}")
|
| 68 |
+
if x.size == 0 or not np.isfinite(x).all():
|
| 69 |
+
raise ValueError("Audio is empty or contains NaNs/Infs.")
|
| 70 |
+
return x.astype(np.float32, copy=False)
|
| 71 |
+
|
| 72 |
+
def apply_chat_template(
|
| 73 |
+
self,
|
| 74 |
+
conversation: List[Dict],
|
| 75 |
+
*,
|
| 76 |
+
tokenize: bool = False,
|
| 77 |
+
add_generation_prompt: bool = False,
|
| 78 |
+
padding: bool = False,
|
| 79 |
+
truncation: bool = True,
|
| 80 |
+
max_length: int = 4096,
|
| 81 |
+
sampling_rate: Optional[int] = 16_000,
|
| 82 |
+
return_tensors: str = "pt",
|
| 83 |
+
**kwargs,
|
| 84 |
+
) -> Dict[str, Any]:
|
| 85 |
+
"""
|
| 86 |
+
conversation: list of turns, where each turn is:
|
| 87 |
+
{"role": "user" | "assistant" | "system", "content": str | List[{"type": "text"|"audio", ...}]}
|
| 88 |
+
|
| 89 |
+
Exactly one audio span is supported per conversation.
|
| 90 |
+
"""
|
| 91 |
+
|
| 92 |
+
if not isinstance(conversation, list) or not conversation:
|
| 93 |
+
raise ValueError("Conversation must be a non-empty list of turns.")
|
| 94 |
+
|
| 95 |
+
text_conv: List[Dict[str, str]] = []
|
| 96 |
+
audio_array: Optional[np.ndarray] = None
|
| 97 |
+
|
| 98 |
+
for turn in conversation:
|
| 99 |
+
role = turn.get("role", None)
|
| 100 |
+
content = turn.get("content", "")
|
| 101 |
+
|
| 102 |
+
if not isinstance(role, str):
|
| 103 |
+
raise ValueError("Each turn must have a string 'role'.")
|
| 104 |
+
if isinstance(content, str):
|
| 105 |
+
text_conv.append({"role": role, "content": content})
|
| 106 |
+
continue
|
| 107 |
+
|
| 108 |
+
buf: List[str] = []
|
| 109 |
+
for item in content:
|
| 110 |
+
t = item.get("type", None)
|
| 111 |
+
if t == "text":
|
| 112 |
+
buf.append(item.get("text", ""))
|
| 113 |
+
elif t == "audio":
|
| 114 |
+
if audio_array is not None:
|
| 115 |
+
raise ValueError(
|
| 116 |
+
"VLFMProcessor supports exactly one audio span per conversation."
|
| 117 |
+
)
|
| 118 |
+
arr = item.get("array", None)
|
| 119 |
+
if arr is None:
|
| 120 |
+
raise ValueError("Audio item missing 'array'.")
|
| 121 |
+
audio_array = self._validate_audio(arr)
|
| 122 |
+
buf.append(self._marker)
|
| 123 |
+
else:
|
| 124 |
+
raise ValueError(f"Unsupported content type: {t}")
|
| 125 |
+
|
| 126 |
+
text_conv.append({"role": role, "content": "".join(buf)})
|
| 127 |
+
|
| 128 |
+
if audio_array is None:
|
| 129 |
+
raise ValueError("No audio found in conversation (exactly one audio span required).")
|
| 130 |
+
|
| 131 |
+
prompt = self.tokenizer.apply_chat_template(
|
| 132 |
+
text_conv, tokenize=False, add_generation_prompt=add_generation_prompt
|
| 133 |
+
)
|
| 134 |
+
#print(f"Output after apply chat: {prompt}")
|
| 135 |
+
|
| 136 |
+
sr = int(sampling_rate or self.feature_extractor.sampling_rate)
|
| 137 |
+
max_samples = int(self.max_seconds * sr)
|
| 138 |
+
if audio_array.shape[0] > max_samples:
|
| 139 |
+
audio_array = audio_array[:max_samples]
|
| 140 |
+
|
| 141 |
+
hop = int(self.feature_extractor.hop_length)
|
| 142 |
+
if audio_array.shape[0] < 2 * hop:
|
| 143 |
+
audio_array = np.pad(audio_array, (0, 2 * hop - audio_array.shape[0]))
|
| 144 |
+
|
| 145 |
+
feat = self.feature_extractor(
|
| 146 |
+
[audio_array],
|
| 147 |
+
sampling_rate=sr,
|
| 148 |
+
return_attention_mask=True,
|
| 149 |
+
return_tensors="pt",
|
| 150 |
+
**kwargs,
|
| 151 |
+
)
|
| 152 |
+
feats = feat.input_features
|
| 153 |
+
attn = feat.attention_mask
|
| 154 |
+
mel_len = int(attn.sum(-1).item())
|
| 155 |
+
|
| 156 |
+
scale = self.ds_rate * self.stack_factor
|
| 157 |
+
audio_token_len = int(np.ceil(mel_len / float(scale)))
|
| 158 |
+
if audio_token_len <= 0:
|
| 159 |
+
raise ValueError(f"Computed non-positive audio_token_len={audio_token_len} (mel_len={mel_len}).")
|
| 160 |
+
|
| 161 |
+
left, sep, right = prompt.partition(self._marker)
|
| 162 |
+
if sep == "":
|
| 163 |
+
raise ValueError("Internal error: <AUDIO_SPAN> marker missing.")
|
| 164 |
+
|
| 165 |
+
left_ids = self.tokenizer(left, add_special_tokens=False)["input_ids"]
|
| 166 |
+
right_ids = self.tokenizer(right, add_special_tokens=False)["input_ids"]
|
| 167 |
+
|
| 168 |
+
input_ids = left_ids + [self.audio_token_id] * audio_token_len + right_ids
|
| 169 |
+
attention_mask = [1] * len(input_ids)
|
| 170 |
+
audio_token_start_idx = len(left_ids)
|
| 171 |
+
|
| 172 |
+
out = {
|
| 173 |
+
"input_ids": torch.tensor(input_ids, dtype=torch.long),
|
| 174 |
+
"attention_mask": torch.tensor(attention_mask, dtype=torch.long),
|
| 175 |
+
|
| 176 |
+
# Audio side:
|
| 177 |
+
"input_features": feats[0].clone(),
|
| 178 |
+
"audio_lens": torch.tensor([mel_len], dtype=torch.long),
|
| 179 |
+
|
| 180 |
+
# Splicing helpers:
|
| 181 |
+
"audio_token_start_idx": torch.tensor([audio_token_start_idx], dtype=torch.long), # [1]
|
| 182 |
+
"audio_token_len": torch.tensor([audio_token_len], dtype=torch.long), # [1]
|
| 183 |
+
|
| 184 |
+
"audio_batch_size": torch.tensor([1], dtype=torch.long), # [1]
|
| 185 |
+
"audio_is_continuation": torch.tensor([False]), # [1]
|
| 186 |
+
}
|
| 187 |
+
|
| 188 |
+
if tokenize:
|
| 189 |
+
tok = self.tokenizer(
|
| 190 |
+
prompt,
|
| 191 |
+
padding=padding,
|
| 192 |
+
truncation=truncation,
|
| 193 |
+
max_length=max_length,
|
| 194 |
+
return_tensors="pt",
|
| 195 |
+
)
|
| 196 |
+
return out
|
| 197 |
+
|
| 198 |
+
VLFMProcessor.register_for_auto_class()
|
| 199 |
+
AutoProcessor.register(VLFMConfig, VLFMProcessor)
|
processor_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_map": {
|
| 3 |
+
"AutoProcessor": "processor.VLFMProcessor"
|
| 4 |
+
},
|
| 5 |
+
"processor_class": "VLFMProcessor"
|
| 6 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "<|audio|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
}
|
| 10 |
+
],
|
| 11 |
+
"bos_token": {
|
| 12 |
+
"content": "<|begin_of_text|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false
|
| 17 |
+
},
|
| 18 |
+
"eos_token": {
|
| 19 |
+
"content": "<|eot_id|>",
|
| 20 |
+
"lstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"rstrip": false,
|
| 23 |
+
"single_word": false
|
| 24 |
+
},
|
| 25 |
+
"pad_token": "<|eot_id|>"
|
| 26 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e87771bfea74770d36a1432b5f9ba6d7f611d33fb63681d10c2479540c1591f8
|
| 3 |
+
size 17210106
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,2078 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"128000": {
|
| 4 |
+
"content": "<|begin_of_text|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"128001": {
|
| 12 |
+
"content": "<|end_of_text|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"128002": {
|
| 20 |
+
"content": "<|reserved_special_token_0|>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"128003": {
|
| 28 |
+
"content": "<|reserved_special_token_1|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128004": {
|
| 36 |
+
"content": "<|finetune_right_pad_id|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"128005": {
|
| 44 |
+
"content": "<|reserved_special_token_2|>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"128006": {
|
| 52 |
+
"content": "<|start_header_id|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"128007": {
|
| 60 |
+
"content": "<|end_header_id|>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"128008": {
|
| 68 |
+
"content": "<|eom_id|>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"128009": {
|
| 76 |
+
"content": "<|eot_id|>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"128010": {
|
| 84 |
+
"content": "<|python_tag|>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"128011": {
|
| 92 |
+
"content": "<|reserved_special_token_3|>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"128012": {
|
| 100 |
+
"content": "<|reserved_special_token_4|>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"128013": {
|
| 108 |
+
"content": "<|reserved_special_token_5|>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"128014": {
|
| 116 |
+
"content": "<|reserved_special_token_6|>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"128015": {
|
| 124 |
+
"content": "<|reserved_special_token_7|>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"128016": {
|
| 132 |
+
"content": "<|reserved_special_token_8|>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"128017": {
|
| 140 |
+
"content": "<|reserved_special_token_9|>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"128018": {
|
| 148 |
+
"content": "<|reserved_special_token_10|>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"128019": {
|
| 156 |
+
"content": "<|reserved_special_token_11|>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"128020": {
|
| 164 |
+
"content": "<|reserved_special_token_12|>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"128021": {
|
| 172 |
+
"content": "<|reserved_special_token_13|>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"128022": {
|
| 180 |
+
"content": "<|reserved_special_token_14|>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"128023": {
|
| 188 |
+
"content": "<|reserved_special_token_15|>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"128024": {
|
| 196 |
+
"content": "<|reserved_special_token_16|>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"128025": {
|
| 204 |
+
"content": "<|reserved_special_token_17|>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"128026": {
|
| 212 |
+
"content": "<|reserved_special_token_18|>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"128027": {
|
| 220 |
+
"content": "<|reserved_special_token_19|>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"128028": {
|
| 228 |
+
"content": "<|reserved_special_token_20|>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"128029": {
|
| 236 |
+
"content": "<|reserved_special_token_21|>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"128030": {
|
| 244 |
+
"content": "<|reserved_special_token_22|>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"128031": {
|
| 252 |
+
"content": "<|reserved_special_token_23|>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"128032": {
|
| 260 |
+
"content": "<|reserved_special_token_24|>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"128033": {
|
| 268 |
+
"content": "<|reserved_special_token_25|>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"128034": {
|
| 276 |
+
"content": "<|reserved_special_token_26|>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"128035": {
|
| 284 |
+
"content": "<|reserved_special_token_27|>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"128036": {
|
| 292 |
+
"content": "<|reserved_special_token_28|>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"128037": {
|
| 300 |
+
"content": "<|reserved_special_token_29|>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"128038": {
|
| 308 |
+
"content": "<|reserved_special_token_30|>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"128039": {
|
| 316 |
+
"content": "<|reserved_special_token_31|>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"128040": {
|
| 324 |
+
"content": "<|reserved_special_token_32|>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"128041": {
|
| 332 |
+
"content": "<|reserved_special_token_33|>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"128042": {
|
| 340 |
+
"content": "<|reserved_special_token_34|>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"128043": {
|
| 348 |
+
"content": "<|reserved_special_token_35|>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"128044": {
|
| 356 |
+
"content": "<|reserved_special_token_36|>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"128045": {
|
| 364 |
+
"content": "<|reserved_special_token_37|>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"128046": {
|
| 372 |
+
"content": "<|reserved_special_token_38|>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"128047": {
|
| 380 |
+
"content": "<|reserved_special_token_39|>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"128048": {
|
| 388 |
+
"content": "<|reserved_special_token_40|>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"128049": {
|
| 396 |
+
"content": "<|reserved_special_token_41|>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"128050": {
|
| 404 |
+
"content": "<|reserved_special_token_42|>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"128051": {
|
| 412 |
+
"content": "<|reserved_special_token_43|>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"128052": {
|
| 420 |
+
"content": "<|reserved_special_token_44|>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"128053": {
|
| 428 |
+
"content": "<|reserved_special_token_45|>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"128054": {
|
| 436 |
+
"content": "<|reserved_special_token_46|>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"128055": {
|
| 444 |
+
"content": "<|reserved_special_token_47|>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"128056": {
|
| 452 |
+
"content": "<|reserved_special_token_48|>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"128057": {
|
| 460 |
+
"content": "<|reserved_special_token_49|>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"128058": {
|
| 468 |
+
"content": "<|reserved_special_token_50|>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"128059": {
|
| 476 |
+
"content": "<|reserved_special_token_51|>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"128060": {
|
| 484 |
+
"content": "<|reserved_special_token_52|>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"128061": {
|
| 492 |
+
"content": "<|reserved_special_token_53|>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"128062": {
|
| 500 |
+
"content": "<|reserved_special_token_54|>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"128063": {
|
| 508 |
+
"content": "<|reserved_special_token_55|>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"128064": {
|
| 516 |
+
"content": "<|reserved_special_token_56|>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"128065": {
|
| 524 |
+
"content": "<|reserved_special_token_57|>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"128066": {
|
| 532 |
+
"content": "<|reserved_special_token_58|>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"128067": {
|
| 540 |
+
"content": "<|reserved_special_token_59|>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"128068": {
|
| 548 |
+
"content": "<|reserved_special_token_60|>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"128069": {
|
| 556 |
+
"content": "<|reserved_special_token_61|>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"128070": {
|
| 564 |
+
"content": "<|reserved_special_token_62|>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"128071": {
|
| 572 |
+
"content": "<|reserved_special_token_63|>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"128072": {
|
| 580 |
+
"content": "<|reserved_special_token_64|>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"128073": {
|
| 588 |
+
"content": "<|reserved_special_token_65|>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"128074": {
|
| 596 |
+
"content": "<|reserved_special_token_66|>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"128075": {
|
| 604 |
+
"content": "<|reserved_special_token_67|>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"128076": {
|
| 612 |
+
"content": "<|reserved_special_token_68|>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"128077": {
|
| 620 |
+
"content": "<|reserved_special_token_69|>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"128078": {
|
| 628 |
+
"content": "<|reserved_special_token_70|>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"128079": {
|
| 636 |
+
"content": "<|reserved_special_token_71|>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"128080": {
|
| 644 |
+
"content": "<|reserved_special_token_72|>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"128081": {
|
| 652 |
+
"content": "<|reserved_special_token_73|>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"128082": {
|
| 660 |
+
"content": "<|reserved_special_token_74|>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"128083": {
|
| 668 |
+
"content": "<|reserved_special_token_75|>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"128084": {
|
| 676 |
+
"content": "<|reserved_special_token_76|>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"128085": {
|
| 684 |
+
"content": "<|reserved_special_token_77|>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"128086": {
|
| 692 |
+
"content": "<|reserved_special_token_78|>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"128087": {
|
| 700 |
+
"content": "<|reserved_special_token_79|>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"128088": {
|
| 708 |
+
"content": "<|reserved_special_token_80|>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"128089": {
|
| 716 |
+
"content": "<|reserved_special_token_81|>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"128090": {
|
| 724 |
+
"content": "<|reserved_special_token_82|>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"128091": {
|
| 732 |
+
"content": "<|reserved_special_token_83|>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"128092": {
|
| 740 |
+
"content": "<|reserved_special_token_84|>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"128093": {
|
| 748 |
+
"content": "<|reserved_special_token_85|>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"128094": {
|
| 756 |
+
"content": "<|reserved_special_token_86|>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"128095": {
|
| 764 |
+
"content": "<|reserved_special_token_87|>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"128096": {
|
| 772 |
+
"content": "<|reserved_special_token_88|>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"128097": {
|
| 780 |
+
"content": "<|reserved_special_token_89|>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"128098": {
|
| 788 |
+
"content": "<|reserved_special_token_90|>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"128099": {
|
| 796 |
+
"content": "<|reserved_special_token_91|>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"128100": {
|
| 804 |
+
"content": "<|reserved_special_token_92|>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"128101": {
|
| 812 |
+
"content": "<|reserved_special_token_93|>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"128102": {
|
| 820 |
+
"content": "<|reserved_special_token_94|>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
},
|
| 827 |
+
"128103": {
|
| 828 |
+
"content": "<|reserved_special_token_95|>",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": false,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": true
|
| 834 |
+
},
|
| 835 |
+
"128104": {
|
| 836 |
+
"content": "<|reserved_special_token_96|>",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": false,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": true
|
| 842 |
+
},
|
| 843 |
+
"128105": {
|
| 844 |
+
"content": "<|reserved_special_token_97|>",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": false,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": true
|
| 850 |
+
},
|
| 851 |
+
"128106": {
|
| 852 |
+
"content": "<|reserved_special_token_98|>",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": false,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": true
|
| 858 |
+
},
|
| 859 |
+
"128107": {
|
| 860 |
+
"content": "<|reserved_special_token_99|>",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": false,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": true
|
| 866 |
+
},
|
| 867 |
+
"128108": {
|
| 868 |
+
"content": "<|reserved_special_token_100|>",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": false,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": true
|
| 874 |
+
},
|
| 875 |
+
"128109": {
|
| 876 |
+
"content": "<|reserved_special_token_101|>",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": false,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": true
|
| 882 |
+
},
|
| 883 |
+
"128110": {
|
| 884 |
+
"content": "<|reserved_special_token_102|>",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": false,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": true
|
| 890 |
+
},
|
| 891 |
+
"128111": {
|
| 892 |
+
"content": "<|reserved_special_token_103|>",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": false,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": true
|
| 898 |
+
},
|
| 899 |
+
"128112": {
|
| 900 |
+
"content": "<|reserved_special_token_104|>",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": false,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": true
|
| 906 |
+
},
|
| 907 |
+
"128113": {
|
| 908 |
+
"content": "<|reserved_special_token_105|>",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": false,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": true
|
| 914 |
+
},
|
| 915 |
+
"128114": {
|
| 916 |
+
"content": "<|reserved_special_token_106|>",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": false,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": true
|
| 922 |
+
},
|
| 923 |
+
"128115": {
|
| 924 |
+
"content": "<|reserved_special_token_107|>",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": false,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": true
|
| 930 |
+
},
|
| 931 |
+
"128116": {
|
| 932 |
+
"content": "<|reserved_special_token_108|>",
|
| 933 |
+
"lstrip": false,
|
| 934 |
+
"normalized": false,
|
| 935 |
+
"rstrip": false,
|
| 936 |
+
"single_word": false,
|
| 937 |
+
"special": true
|
| 938 |
+
},
|
| 939 |
+
"128117": {
|
| 940 |
+
"content": "<|reserved_special_token_109|>",
|
| 941 |
+
"lstrip": false,
|
| 942 |
+
"normalized": false,
|
| 943 |
+
"rstrip": false,
|
| 944 |
+
"single_word": false,
|
| 945 |
+
"special": true
|
| 946 |
+
},
|
| 947 |
+
"128118": {
|
| 948 |
+
"content": "<|reserved_special_token_110|>",
|
| 949 |
+
"lstrip": false,
|
| 950 |
+
"normalized": false,
|
| 951 |
+
"rstrip": false,
|
| 952 |
+
"single_word": false,
|
| 953 |
+
"special": true
|
| 954 |
+
},
|
| 955 |
+
"128119": {
|
| 956 |
+
"content": "<|reserved_special_token_111|>",
|
| 957 |
+
"lstrip": false,
|
| 958 |
+
"normalized": false,
|
| 959 |
+
"rstrip": false,
|
| 960 |
+
"single_word": false,
|
| 961 |
+
"special": true
|
| 962 |
+
},
|
| 963 |
+
"128120": {
|
| 964 |
+
"content": "<|reserved_special_token_112|>",
|
| 965 |
+
"lstrip": false,
|
| 966 |
+
"normalized": false,
|
| 967 |
+
"rstrip": false,
|
| 968 |
+
"single_word": false,
|
| 969 |
+
"special": true
|
| 970 |
+
},
|
| 971 |
+
"128121": {
|
| 972 |
+
"content": "<|reserved_special_token_113|>",
|
| 973 |
+
"lstrip": false,
|
| 974 |
+
"normalized": false,
|
| 975 |
+
"rstrip": false,
|
| 976 |
+
"single_word": false,
|
| 977 |
+
"special": true
|
| 978 |
+
},
|
| 979 |
+
"128122": {
|
| 980 |
+
"content": "<|reserved_special_token_114|>",
|
| 981 |
+
"lstrip": false,
|
| 982 |
+
"normalized": false,
|
| 983 |
+
"rstrip": false,
|
| 984 |
+
"single_word": false,
|
| 985 |
+
"special": true
|
| 986 |
+
},
|
| 987 |
+
"128123": {
|
| 988 |
+
"content": "<|reserved_special_token_115|>",
|
| 989 |
+
"lstrip": false,
|
| 990 |
+
"normalized": false,
|
| 991 |
+
"rstrip": false,
|
| 992 |
+
"single_word": false,
|
| 993 |
+
"special": true
|
| 994 |
+
},
|
| 995 |
+
"128124": {
|
| 996 |
+
"content": "<|reserved_special_token_116|>",
|
| 997 |
+
"lstrip": false,
|
| 998 |
+
"normalized": false,
|
| 999 |
+
"rstrip": false,
|
| 1000 |
+
"single_word": false,
|
| 1001 |
+
"special": true
|
| 1002 |
+
},
|
| 1003 |
+
"128125": {
|
| 1004 |
+
"content": "<|reserved_special_token_117|>",
|
| 1005 |
+
"lstrip": false,
|
| 1006 |
+
"normalized": false,
|
| 1007 |
+
"rstrip": false,
|
| 1008 |
+
"single_word": false,
|
| 1009 |
+
"special": true
|
| 1010 |
+
},
|
| 1011 |
+
"128126": {
|
| 1012 |
+
"content": "<|reserved_special_token_118|>",
|
| 1013 |
+
"lstrip": false,
|
| 1014 |
+
"normalized": false,
|
| 1015 |
+
"rstrip": false,
|
| 1016 |
+
"single_word": false,
|
| 1017 |
+
"special": true
|
| 1018 |
+
},
|
| 1019 |
+
"128127": {
|
| 1020 |
+
"content": "<|reserved_special_token_119|>",
|
| 1021 |
+
"lstrip": false,
|
| 1022 |
+
"normalized": false,
|
| 1023 |
+
"rstrip": false,
|
| 1024 |
+
"single_word": false,
|
| 1025 |
+
"special": true
|
| 1026 |
+
},
|
| 1027 |
+
"128128": {
|
| 1028 |
+
"content": "<|reserved_special_token_120|>",
|
| 1029 |
+
"lstrip": false,
|
| 1030 |
+
"normalized": false,
|
| 1031 |
+
"rstrip": false,
|
| 1032 |
+
"single_word": false,
|
| 1033 |
+
"special": true
|
| 1034 |
+
},
|
| 1035 |
+
"128129": {
|
| 1036 |
+
"content": "<|reserved_special_token_121|>",
|
| 1037 |
+
"lstrip": false,
|
| 1038 |
+
"normalized": false,
|
| 1039 |
+
"rstrip": false,
|
| 1040 |
+
"single_word": false,
|
| 1041 |
+
"special": true
|
| 1042 |
+
},
|
| 1043 |
+
"128130": {
|
| 1044 |
+
"content": "<|reserved_special_token_122|>",
|
| 1045 |
+
"lstrip": false,
|
| 1046 |
+
"normalized": false,
|
| 1047 |
+
"rstrip": false,
|
| 1048 |
+
"single_word": false,
|
| 1049 |
+
"special": true
|
| 1050 |
+
},
|
| 1051 |
+
"128131": {
|
| 1052 |
+
"content": "<|reserved_special_token_123|>",
|
| 1053 |
+
"lstrip": false,
|
| 1054 |
+
"normalized": false,
|
| 1055 |
+
"rstrip": false,
|
| 1056 |
+
"single_word": false,
|
| 1057 |
+
"special": true
|
| 1058 |
+
},
|
| 1059 |
+
"128132": {
|
| 1060 |
+
"content": "<|reserved_special_token_124|>",
|
| 1061 |
+
"lstrip": false,
|
| 1062 |
+
"normalized": false,
|
| 1063 |
+
"rstrip": false,
|
| 1064 |
+
"single_word": false,
|
| 1065 |
+
"special": true
|
| 1066 |
+
},
|
| 1067 |
+
"128133": {
|
| 1068 |
+
"content": "<|reserved_special_token_125|>",
|
| 1069 |
+
"lstrip": false,
|
| 1070 |
+
"normalized": false,
|
| 1071 |
+
"rstrip": false,
|
| 1072 |
+
"single_word": false,
|
| 1073 |
+
"special": true
|
| 1074 |
+
},
|
| 1075 |
+
"128134": {
|
| 1076 |
+
"content": "<|reserved_special_token_126|>",
|
| 1077 |
+
"lstrip": false,
|
| 1078 |
+
"normalized": false,
|
| 1079 |
+
"rstrip": false,
|
| 1080 |
+
"single_word": false,
|
| 1081 |
+
"special": true
|
| 1082 |
+
},
|
| 1083 |
+
"128135": {
|
| 1084 |
+
"content": "<|reserved_special_token_127|>",
|
| 1085 |
+
"lstrip": false,
|
| 1086 |
+
"normalized": false,
|
| 1087 |
+
"rstrip": false,
|
| 1088 |
+
"single_word": false,
|
| 1089 |
+
"special": true
|
| 1090 |
+
},
|
| 1091 |
+
"128136": {
|
| 1092 |
+
"content": "<|reserved_special_token_128|>",
|
| 1093 |
+
"lstrip": false,
|
| 1094 |
+
"normalized": false,
|
| 1095 |
+
"rstrip": false,
|
| 1096 |
+
"single_word": false,
|
| 1097 |
+
"special": true
|
| 1098 |
+
},
|
| 1099 |
+
"128137": {
|
| 1100 |
+
"content": "<|reserved_special_token_129|>",
|
| 1101 |
+
"lstrip": false,
|
| 1102 |
+
"normalized": false,
|
| 1103 |
+
"rstrip": false,
|
| 1104 |
+
"single_word": false,
|
| 1105 |
+
"special": true
|
| 1106 |
+
},
|
| 1107 |
+
"128138": {
|
| 1108 |
+
"content": "<|reserved_special_token_130|>",
|
| 1109 |
+
"lstrip": false,
|
| 1110 |
+
"normalized": false,
|
| 1111 |
+
"rstrip": false,
|
| 1112 |
+
"single_word": false,
|
| 1113 |
+
"special": true
|
| 1114 |
+
},
|
| 1115 |
+
"128139": {
|
| 1116 |
+
"content": "<|reserved_special_token_131|>",
|
| 1117 |
+
"lstrip": false,
|
| 1118 |
+
"normalized": false,
|
| 1119 |
+
"rstrip": false,
|
| 1120 |
+
"single_word": false,
|
| 1121 |
+
"special": true
|
| 1122 |
+
},
|
| 1123 |
+
"128140": {
|
| 1124 |
+
"content": "<|reserved_special_token_132|>",
|
| 1125 |
+
"lstrip": false,
|
| 1126 |
+
"normalized": false,
|
| 1127 |
+
"rstrip": false,
|
| 1128 |
+
"single_word": false,
|
| 1129 |
+
"special": true
|
| 1130 |
+
},
|
| 1131 |
+
"128141": {
|
| 1132 |
+
"content": "<|reserved_special_token_133|>",
|
| 1133 |
+
"lstrip": false,
|
| 1134 |
+
"normalized": false,
|
| 1135 |
+
"rstrip": false,
|
| 1136 |
+
"single_word": false,
|
| 1137 |
+
"special": true
|
| 1138 |
+
},
|
| 1139 |
+
"128142": {
|
| 1140 |
+
"content": "<|reserved_special_token_134|>",
|
| 1141 |
+
"lstrip": false,
|
| 1142 |
+
"normalized": false,
|
| 1143 |
+
"rstrip": false,
|
| 1144 |
+
"single_word": false,
|
| 1145 |
+
"special": true
|
| 1146 |
+
},
|
| 1147 |
+
"128143": {
|
| 1148 |
+
"content": "<|reserved_special_token_135|>",
|
| 1149 |
+
"lstrip": false,
|
| 1150 |
+
"normalized": false,
|
| 1151 |
+
"rstrip": false,
|
| 1152 |
+
"single_word": false,
|
| 1153 |
+
"special": true
|
| 1154 |
+
},
|
| 1155 |
+
"128144": {
|
| 1156 |
+
"content": "<|reserved_special_token_136|>",
|
| 1157 |
+
"lstrip": false,
|
| 1158 |
+
"normalized": false,
|
| 1159 |
+
"rstrip": false,
|
| 1160 |
+
"single_word": false,
|
| 1161 |
+
"special": true
|
| 1162 |
+
},
|
| 1163 |
+
"128145": {
|
| 1164 |
+
"content": "<|reserved_special_token_137|>",
|
| 1165 |
+
"lstrip": false,
|
| 1166 |
+
"normalized": false,
|
| 1167 |
+
"rstrip": false,
|
| 1168 |
+
"single_word": false,
|
| 1169 |
+
"special": true
|
| 1170 |
+
},
|
| 1171 |
+
"128146": {
|
| 1172 |
+
"content": "<|reserved_special_token_138|>",
|
| 1173 |
+
"lstrip": false,
|
| 1174 |
+
"normalized": false,
|
| 1175 |
+
"rstrip": false,
|
| 1176 |
+
"single_word": false,
|
| 1177 |
+
"special": true
|
| 1178 |
+
},
|
| 1179 |
+
"128147": {
|
| 1180 |
+
"content": "<|reserved_special_token_139|>",
|
| 1181 |
+
"lstrip": false,
|
| 1182 |
+
"normalized": false,
|
| 1183 |
+
"rstrip": false,
|
| 1184 |
+
"single_word": false,
|
| 1185 |
+
"special": true
|
| 1186 |
+
},
|
| 1187 |
+
"128148": {
|
| 1188 |
+
"content": "<|reserved_special_token_140|>",
|
| 1189 |
+
"lstrip": false,
|
| 1190 |
+
"normalized": false,
|
| 1191 |
+
"rstrip": false,
|
| 1192 |
+
"single_word": false,
|
| 1193 |
+
"special": true
|
| 1194 |
+
},
|
| 1195 |
+
"128149": {
|
| 1196 |
+
"content": "<|reserved_special_token_141|>",
|
| 1197 |
+
"lstrip": false,
|
| 1198 |
+
"normalized": false,
|
| 1199 |
+
"rstrip": false,
|
| 1200 |
+
"single_word": false,
|
| 1201 |
+
"special": true
|
| 1202 |
+
},
|
| 1203 |
+
"128150": {
|
| 1204 |
+
"content": "<|reserved_special_token_142|>",
|
| 1205 |
+
"lstrip": false,
|
| 1206 |
+
"normalized": false,
|
| 1207 |
+
"rstrip": false,
|
| 1208 |
+
"single_word": false,
|
| 1209 |
+
"special": true
|
| 1210 |
+
},
|
| 1211 |
+
"128151": {
|
| 1212 |
+
"content": "<|reserved_special_token_143|>",
|
| 1213 |
+
"lstrip": false,
|
| 1214 |
+
"normalized": false,
|
| 1215 |
+
"rstrip": false,
|
| 1216 |
+
"single_word": false,
|
| 1217 |
+
"special": true
|
| 1218 |
+
},
|
| 1219 |
+
"128152": {
|
| 1220 |
+
"content": "<|reserved_special_token_144|>",
|
| 1221 |
+
"lstrip": false,
|
| 1222 |
+
"normalized": false,
|
| 1223 |
+
"rstrip": false,
|
| 1224 |
+
"single_word": false,
|
| 1225 |
+
"special": true
|
| 1226 |
+
},
|
| 1227 |
+
"128153": {
|
| 1228 |
+
"content": "<|reserved_special_token_145|>",
|
| 1229 |
+
"lstrip": false,
|
| 1230 |
+
"normalized": false,
|
| 1231 |
+
"rstrip": false,
|
| 1232 |
+
"single_word": false,
|
| 1233 |
+
"special": true
|
| 1234 |
+
},
|
| 1235 |
+
"128154": {
|
| 1236 |
+
"content": "<|reserved_special_token_146|>",
|
| 1237 |
+
"lstrip": false,
|
| 1238 |
+
"normalized": false,
|
| 1239 |
+
"rstrip": false,
|
| 1240 |
+
"single_word": false,
|
| 1241 |
+
"special": true
|
| 1242 |
+
},
|
| 1243 |
+
"128155": {
|
| 1244 |
+
"content": "<|reserved_special_token_147|>",
|
| 1245 |
+
"lstrip": false,
|
| 1246 |
+
"normalized": false,
|
| 1247 |
+
"rstrip": false,
|
| 1248 |
+
"single_word": false,
|
| 1249 |
+
"special": true
|
| 1250 |
+
},
|
| 1251 |
+
"128156": {
|
| 1252 |
+
"content": "<|reserved_special_token_148|>",
|
| 1253 |
+
"lstrip": false,
|
| 1254 |
+
"normalized": false,
|
| 1255 |
+
"rstrip": false,
|
| 1256 |
+
"single_word": false,
|
| 1257 |
+
"special": true
|
| 1258 |
+
},
|
| 1259 |
+
"128157": {
|
| 1260 |
+
"content": "<|reserved_special_token_149|>",
|
| 1261 |
+
"lstrip": false,
|
| 1262 |
+
"normalized": false,
|
| 1263 |
+
"rstrip": false,
|
| 1264 |
+
"single_word": false,
|
| 1265 |
+
"special": true
|
| 1266 |
+
},
|
| 1267 |
+
"128158": {
|
| 1268 |
+
"content": "<|reserved_special_token_150|>",
|
| 1269 |
+
"lstrip": false,
|
| 1270 |
+
"normalized": false,
|
| 1271 |
+
"rstrip": false,
|
| 1272 |
+
"single_word": false,
|
| 1273 |
+
"special": true
|
| 1274 |
+
},
|
| 1275 |
+
"128159": {
|
| 1276 |
+
"content": "<|reserved_special_token_151|>",
|
| 1277 |
+
"lstrip": false,
|
| 1278 |
+
"normalized": false,
|
| 1279 |
+
"rstrip": false,
|
| 1280 |
+
"single_word": false,
|
| 1281 |
+
"special": true
|
| 1282 |
+
},
|
| 1283 |
+
"128160": {
|
| 1284 |
+
"content": "<|reserved_special_token_152|>",
|
| 1285 |
+
"lstrip": false,
|
| 1286 |
+
"normalized": false,
|
| 1287 |
+
"rstrip": false,
|
| 1288 |
+
"single_word": false,
|
| 1289 |
+
"special": true
|
| 1290 |
+
},
|
| 1291 |
+
"128161": {
|
| 1292 |
+
"content": "<|reserved_special_token_153|>",
|
| 1293 |
+
"lstrip": false,
|
| 1294 |
+
"normalized": false,
|
| 1295 |
+
"rstrip": false,
|
| 1296 |
+
"single_word": false,
|
| 1297 |
+
"special": true
|
| 1298 |
+
},
|
| 1299 |
+
"128162": {
|
| 1300 |
+
"content": "<|reserved_special_token_154|>",
|
| 1301 |
+
"lstrip": false,
|
| 1302 |
+
"normalized": false,
|
| 1303 |
+
"rstrip": false,
|
| 1304 |
+
"single_word": false,
|
| 1305 |
+
"special": true
|
| 1306 |
+
},
|
| 1307 |
+
"128163": {
|
| 1308 |
+
"content": "<|reserved_special_token_155|>",
|
| 1309 |
+
"lstrip": false,
|
| 1310 |
+
"normalized": false,
|
| 1311 |
+
"rstrip": false,
|
| 1312 |
+
"single_word": false,
|
| 1313 |
+
"special": true
|
| 1314 |
+
},
|
| 1315 |
+
"128164": {
|
| 1316 |
+
"content": "<|reserved_special_token_156|>",
|
| 1317 |
+
"lstrip": false,
|
| 1318 |
+
"normalized": false,
|
| 1319 |
+
"rstrip": false,
|
| 1320 |
+
"single_word": false,
|
| 1321 |
+
"special": true
|
| 1322 |
+
},
|
| 1323 |
+
"128165": {
|
| 1324 |
+
"content": "<|reserved_special_token_157|>",
|
| 1325 |
+
"lstrip": false,
|
| 1326 |
+
"normalized": false,
|
| 1327 |
+
"rstrip": false,
|
| 1328 |
+
"single_word": false,
|
| 1329 |
+
"special": true
|
| 1330 |
+
},
|
| 1331 |
+
"128166": {
|
| 1332 |
+
"content": "<|reserved_special_token_158|>",
|
| 1333 |
+
"lstrip": false,
|
| 1334 |
+
"normalized": false,
|
| 1335 |
+
"rstrip": false,
|
| 1336 |
+
"single_word": false,
|
| 1337 |
+
"special": true
|
| 1338 |
+
},
|
| 1339 |
+
"128167": {
|
| 1340 |
+
"content": "<|reserved_special_token_159|>",
|
| 1341 |
+
"lstrip": false,
|
| 1342 |
+
"normalized": false,
|
| 1343 |
+
"rstrip": false,
|
| 1344 |
+
"single_word": false,
|
| 1345 |
+
"special": true
|
| 1346 |
+
},
|
| 1347 |
+
"128168": {
|
| 1348 |
+
"content": "<|reserved_special_token_160|>",
|
| 1349 |
+
"lstrip": false,
|
| 1350 |
+
"normalized": false,
|
| 1351 |
+
"rstrip": false,
|
| 1352 |
+
"single_word": false,
|
| 1353 |
+
"special": true
|
| 1354 |
+
},
|
| 1355 |
+
"128169": {
|
| 1356 |
+
"content": "<|reserved_special_token_161|>",
|
| 1357 |
+
"lstrip": false,
|
| 1358 |
+
"normalized": false,
|
| 1359 |
+
"rstrip": false,
|
| 1360 |
+
"single_word": false,
|
| 1361 |
+
"special": true
|
| 1362 |
+
},
|
| 1363 |
+
"128170": {
|
| 1364 |
+
"content": "<|reserved_special_token_162|>",
|
| 1365 |
+
"lstrip": false,
|
| 1366 |
+
"normalized": false,
|
| 1367 |
+
"rstrip": false,
|
| 1368 |
+
"single_word": false,
|
| 1369 |
+
"special": true
|
| 1370 |
+
},
|
| 1371 |
+
"128171": {
|
| 1372 |
+
"content": "<|reserved_special_token_163|>",
|
| 1373 |
+
"lstrip": false,
|
| 1374 |
+
"normalized": false,
|
| 1375 |
+
"rstrip": false,
|
| 1376 |
+
"single_word": false,
|
| 1377 |
+
"special": true
|
| 1378 |
+
},
|
| 1379 |
+
"128172": {
|
| 1380 |
+
"content": "<|reserved_special_token_164|>",
|
| 1381 |
+
"lstrip": false,
|
| 1382 |
+
"normalized": false,
|
| 1383 |
+
"rstrip": false,
|
| 1384 |
+
"single_word": false,
|
| 1385 |
+
"special": true
|
| 1386 |
+
},
|
| 1387 |
+
"128173": {
|
| 1388 |
+
"content": "<|reserved_special_token_165|>",
|
| 1389 |
+
"lstrip": false,
|
| 1390 |
+
"normalized": false,
|
| 1391 |
+
"rstrip": false,
|
| 1392 |
+
"single_word": false,
|
| 1393 |
+
"special": true
|
| 1394 |
+
},
|
| 1395 |
+
"128174": {
|
| 1396 |
+
"content": "<|reserved_special_token_166|>",
|
| 1397 |
+
"lstrip": false,
|
| 1398 |
+
"normalized": false,
|
| 1399 |
+
"rstrip": false,
|
| 1400 |
+
"single_word": false,
|
| 1401 |
+
"special": true
|
| 1402 |
+
},
|
| 1403 |
+
"128175": {
|
| 1404 |
+
"content": "<|reserved_special_token_167|>",
|
| 1405 |
+
"lstrip": false,
|
| 1406 |
+
"normalized": false,
|
| 1407 |
+
"rstrip": false,
|
| 1408 |
+
"single_word": false,
|
| 1409 |
+
"special": true
|
| 1410 |
+
},
|
| 1411 |
+
"128176": {
|
| 1412 |
+
"content": "<|reserved_special_token_168|>",
|
| 1413 |
+
"lstrip": false,
|
| 1414 |
+
"normalized": false,
|
| 1415 |
+
"rstrip": false,
|
| 1416 |
+
"single_word": false,
|
| 1417 |
+
"special": true
|
| 1418 |
+
},
|
| 1419 |
+
"128177": {
|
| 1420 |
+
"content": "<|reserved_special_token_169|>",
|
| 1421 |
+
"lstrip": false,
|
| 1422 |
+
"normalized": false,
|
| 1423 |
+
"rstrip": false,
|
| 1424 |
+
"single_word": false,
|
| 1425 |
+
"special": true
|
| 1426 |
+
},
|
| 1427 |
+
"128178": {
|
| 1428 |
+
"content": "<|reserved_special_token_170|>",
|
| 1429 |
+
"lstrip": false,
|
| 1430 |
+
"normalized": false,
|
| 1431 |
+
"rstrip": false,
|
| 1432 |
+
"single_word": false,
|
| 1433 |
+
"special": true
|
| 1434 |
+
},
|
| 1435 |
+
"128179": {
|
| 1436 |
+
"content": "<|reserved_special_token_171|>",
|
| 1437 |
+
"lstrip": false,
|
| 1438 |
+
"normalized": false,
|
| 1439 |
+
"rstrip": false,
|
| 1440 |
+
"single_word": false,
|
| 1441 |
+
"special": true
|
| 1442 |
+
},
|
| 1443 |
+
"128180": {
|
| 1444 |
+
"content": "<|reserved_special_token_172|>",
|
| 1445 |
+
"lstrip": false,
|
| 1446 |
+
"normalized": false,
|
| 1447 |
+
"rstrip": false,
|
| 1448 |
+
"single_word": false,
|
| 1449 |
+
"special": true
|
| 1450 |
+
},
|
| 1451 |
+
"128181": {
|
| 1452 |
+
"content": "<|reserved_special_token_173|>",
|
| 1453 |
+
"lstrip": false,
|
| 1454 |
+
"normalized": false,
|
| 1455 |
+
"rstrip": false,
|
| 1456 |
+
"single_word": false,
|
| 1457 |
+
"special": true
|
| 1458 |
+
},
|
| 1459 |
+
"128182": {
|
| 1460 |
+
"content": "<|reserved_special_token_174|>",
|
| 1461 |
+
"lstrip": false,
|
| 1462 |
+
"normalized": false,
|
| 1463 |
+
"rstrip": false,
|
| 1464 |
+
"single_word": false,
|
| 1465 |
+
"special": true
|
| 1466 |
+
},
|
| 1467 |
+
"128183": {
|
| 1468 |
+
"content": "<|reserved_special_token_175|>",
|
| 1469 |
+
"lstrip": false,
|
| 1470 |
+
"normalized": false,
|
| 1471 |
+
"rstrip": false,
|
| 1472 |
+
"single_word": false,
|
| 1473 |
+
"special": true
|
| 1474 |
+
},
|
| 1475 |
+
"128184": {
|
| 1476 |
+
"content": "<|reserved_special_token_176|>",
|
| 1477 |
+
"lstrip": false,
|
| 1478 |
+
"normalized": false,
|
| 1479 |
+
"rstrip": false,
|
| 1480 |
+
"single_word": false,
|
| 1481 |
+
"special": true
|
| 1482 |
+
},
|
| 1483 |
+
"128185": {
|
| 1484 |
+
"content": "<|reserved_special_token_177|>",
|
| 1485 |
+
"lstrip": false,
|
| 1486 |
+
"normalized": false,
|
| 1487 |
+
"rstrip": false,
|
| 1488 |
+
"single_word": false,
|
| 1489 |
+
"special": true
|
| 1490 |
+
},
|
| 1491 |
+
"128186": {
|
| 1492 |
+
"content": "<|reserved_special_token_178|>",
|
| 1493 |
+
"lstrip": false,
|
| 1494 |
+
"normalized": false,
|
| 1495 |
+
"rstrip": false,
|
| 1496 |
+
"single_word": false,
|
| 1497 |
+
"special": true
|
| 1498 |
+
},
|
| 1499 |
+
"128187": {
|
| 1500 |
+
"content": "<|reserved_special_token_179|>",
|
| 1501 |
+
"lstrip": false,
|
| 1502 |
+
"normalized": false,
|
| 1503 |
+
"rstrip": false,
|
| 1504 |
+
"single_word": false,
|
| 1505 |
+
"special": true
|
| 1506 |
+
},
|
| 1507 |
+
"128188": {
|
| 1508 |
+
"content": "<|reserved_special_token_180|>",
|
| 1509 |
+
"lstrip": false,
|
| 1510 |
+
"normalized": false,
|
| 1511 |
+
"rstrip": false,
|
| 1512 |
+
"single_word": false,
|
| 1513 |
+
"special": true
|
| 1514 |
+
},
|
| 1515 |
+
"128189": {
|
| 1516 |
+
"content": "<|reserved_special_token_181|>",
|
| 1517 |
+
"lstrip": false,
|
| 1518 |
+
"normalized": false,
|
| 1519 |
+
"rstrip": false,
|
| 1520 |
+
"single_word": false,
|
| 1521 |
+
"special": true
|
| 1522 |
+
},
|
| 1523 |
+
"128190": {
|
| 1524 |
+
"content": "<|reserved_special_token_182|>",
|
| 1525 |
+
"lstrip": false,
|
| 1526 |
+
"normalized": false,
|
| 1527 |
+
"rstrip": false,
|
| 1528 |
+
"single_word": false,
|
| 1529 |
+
"special": true
|
| 1530 |
+
},
|
| 1531 |
+
"128191": {
|
| 1532 |
+
"content": "<|reserved_special_token_183|>",
|
| 1533 |
+
"lstrip": false,
|
| 1534 |
+
"normalized": false,
|
| 1535 |
+
"rstrip": false,
|
| 1536 |
+
"single_word": false,
|
| 1537 |
+
"special": true
|
| 1538 |
+
},
|
| 1539 |
+
"128192": {
|
| 1540 |
+
"content": "<|reserved_special_token_184|>",
|
| 1541 |
+
"lstrip": false,
|
| 1542 |
+
"normalized": false,
|
| 1543 |
+
"rstrip": false,
|
| 1544 |
+
"single_word": false,
|
| 1545 |
+
"special": true
|
| 1546 |
+
},
|
| 1547 |
+
"128193": {
|
| 1548 |
+
"content": "<|reserved_special_token_185|>",
|
| 1549 |
+
"lstrip": false,
|
| 1550 |
+
"normalized": false,
|
| 1551 |
+
"rstrip": false,
|
| 1552 |
+
"single_word": false,
|
| 1553 |
+
"special": true
|
| 1554 |
+
},
|
| 1555 |
+
"128194": {
|
| 1556 |
+
"content": "<|reserved_special_token_186|>",
|
| 1557 |
+
"lstrip": false,
|
| 1558 |
+
"normalized": false,
|
| 1559 |
+
"rstrip": false,
|
| 1560 |
+
"single_word": false,
|
| 1561 |
+
"special": true
|
| 1562 |
+
},
|
| 1563 |
+
"128195": {
|
| 1564 |
+
"content": "<|reserved_special_token_187|>",
|
| 1565 |
+
"lstrip": false,
|
| 1566 |
+
"normalized": false,
|
| 1567 |
+
"rstrip": false,
|
| 1568 |
+
"single_word": false,
|
| 1569 |
+
"special": true
|
| 1570 |
+
},
|
| 1571 |
+
"128196": {
|
| 1572 |
+
"content": "<|reserved_special_token_188|>",
|
| 1573 |
+
"lstrip": false,
|
| 1574 |
+
"normalized": false,
|
| 1575 |
+
"rstrip": false,
|
| 1576 |
+
"single_word": false,
|
| 1577 |
+
"special": true
|
| 1578 |
+
},
|
| 1579 |
+
"128197": {
|
| 1580 |
+
"content": "<|reserved_special_token_189|>",
|
| 1581 |
+
"lstrip": false,
|
| 1582 |
+
"normalized": false,
|
| 1583 |
+
"rstrip": false,
|
| 1584 |
+
"single_word": false,
|
| 1585 |
+
"special": true
|
| 1586 |
+
},
|
| 1587 |
+
"128198": {
|
| 1588 |
+
"content": "<|reserved_special_token_190|>",
|
| 1589 |
+
"lstrip": false,
|
| 1590 |
+
"normalized": false,
|
| 1591 |
+
"rstrip": false,
|
| 1592 |
+
"single_word": false,
|
| 1593 |
+
"special": true
|
| 1594 |
+
},
|
| 1595 |
+
"128199": {
|
| 1596 |
+
"content": "<|reserved_special_token_191|>",
|
| 1597 |
+
"lstrip": false,
|
| 1598 |
+
"normalized": false,
|
| 1599 |
+
"rstrip": false,
|
| 1600 |
+
"single_word": false,
|
| 1601 |
+
"special": true
|
| 1602 |
+
},
|
| 1603 |
+
"128200": {
|
| 1604 |
+
"content": "<|reserved_special_token_192|>",
|
| 1605 |
+
"lstrip": false,
|
| 1606 |
+
"normalized": false,
|
| 1607 |
+
"rstrip": false,
|
| 1608 |
+
"single_word": false,
|
| 1609 |
+
"special": true
|
| 1610 |
+
},
|
| 1611 |
+
"128201": {
|
| 1612 |
+
"content": "<|reserved_special_token_193|>",
|
| 1613 |
+
"lstrip": false,
|
| 1614 |
+
"normalized": false,
|
| 1615 |
+
"rstrip": false,
|
| 1616 |
+
"single_word": false,
|
| 1617 |
+
"special": true
|
| 1618 |
+
},
|
| 1619 |
+
"128202": {
|
| 1620 |
+
"content": "<|reserved_special_token_194|>",
|
| 1621 |
+
"lstrip": false,
|
| 1622 |
+
"normalized": false,
|
| 1623 |
+
"rstrip": false,
|
| 1624 |
+
"single_word": false,
|
| 1625 |
+
"special": true
|
| 1626 |
+
},
|
| 1627 |
+
"128203": {
|
| 1628 |
+
"content": "<|reserved_special_token_195|>",
|
| 1629 |
+
"lstrip": false,
|
| 1630 |
+
"normalized": false,
|
| 1631 |
+
"rstrip": false,
|
| 1632 |
+
"single_word": false,
|
| 1633 |
+
"special": true
|
| 1634 |
+
},
|
| 1635 |
+
"128204": {
|
| 1636 |
+
"content": "<|reserved_special_token_196|>",
|
| 1637 |
+
"lstrip": false,
|
| 1638 |
+
"normalized": false,
|
| 1639 |
+
"rstrip": false,
|
| 1640 |
+
"single_word": false,
|
| 1641 |
+
"special": true
|
| 1642 |
+
},
|
| 1643 |
+
"128205": {
|
| 1644 |
+
"content": "<|reserved_special_token_197|>",
|
| 1645 |
+
"lstrip": false,
|
| 1646 |
+
"normalized": false,
|
| 1647 |
+
"rstrip": false,
|
| 1648 |
+
"single_word": false,
|
| 1649 |
+
"special": true
|
| 1650 |
+
},
|
| 1651 |
+
"128206": {
|
| 1652 |
+
"content": "<|reserved_special_token_198|>",
|
| 1653 |
+
"lstrip": false,
|
| 1654 |
+
"normalized": false,
|
| 1655 |
+
"rstrip": false,
|
| 1656 |
+
"single_word": false,
|
| 1657 |
+
"special": true
|
| 1658 |
+
},
|
| 1659 |
+
"128207": {
|
| 1660 |
+
"content": "<|reserved_special_token_199|>",
|
| 1661 |
+
"lstrip": false,
|
| 1662 |
+
"normalized": false,
|
| 1663 |
+
"rstrip": false,
|
| 1664 |
+
"single_word": false,
|
| 1665 |
+
"special": true
|
| 1666 |
+
},
|
| 1667 |
+
"128208": {
|
| 1668 |
+
"content": "<|reserved_special_token_200|>",
|
| 1669 |
+
"lstrip": false,
|
| 1670 |
+
"normalized": false,
|
| 1671 |
+
"rstrip": false,
|
| 1672 |
+
"single_word": false,
|
| 1673 |
+
"special": true
|
| 1674 |
+
},
|
| 1675 |
+
"128209": {
|
| 1676 |
+
"content": "<|reserved_special_token_201|>",
|
| 1677 |
+
"lstrip": false,
|
| 1678 |
+
"normalized": false,
|
| 1679 |
+
"rstrip": false,
|
| 1680 |
+
"single_word": false,
|
| 1681 |
+
"special": true
|
| 1682 |
+
},
|
| 1683 |
+
"128210": {
|
| 1684 |
+
"content": "<|reserved_special_token_202|>",
|
| 1685 |
+
"lstrip": false,
|
| 1686 |
+
"normalized": false,
|
| 1687 |
+
"rstrip": false,
|
| 1688 |
+
"single_word": false,
|
| 1689 |
+
"special": true
|
| 1690 |
+
},
|
| 1691 |
+
"128211": {
|
| 1692 |
+
"content": "<|reserved_special_token_203|>",
|
| 1693 |
+
"lstrip": false,
|
| 1694 |
+
"normalized": false,
|
| 1695 |
+
"rstrip": false,
|
| 1696 |
+
"single_word": false,
|
| 1697 |
+
"special": true
|
| 1698 |
+
},
|
| 1699 |
+
"128212": {
|
| 1700 |
+
"content": "<|reserved_special_token_204|>",
|
| 1701 |
+
"lstrip": false,
|
| 1702 |
+
"normalized": false,
|
| 1703 |
+
"rstrip": false,
|
| 1704 |
+
"single_word": false,
|
| 1705 |
+
"special": true
|
| 1706 |
+
},
|
| 1707 |
+
"128213": {
|
| 1708 |
+
"content": "<|reserved_special_token_205|>",
|
| 1709 |
+
"lstrip": false,
|
| 1710 |
+
"normalized": false,
|
| 1711 |
+
"rstrip": false,
|
| 1712 |
+
"single_word": false,
|
| 1713 |
+
"special": true
|
| 1714 |
+
},
|
| 1715 |
+
"128214": {
|
| 1716 |
+
"content": "<|reserved_special_token_206|>",
|
| 1717 |
+
"lstrip": false,
|
| 1718 |
+
"normalized": false,
|
| 1719 |
+
"rstrip": false,
|
| 1720 |
+
"single_word": false,
|
| 1721 |
+
"special": true
|
| 1722 |
+
},
|
| 1723 |
+
"128215": {
|
| 1724 |
+
"content": "<|reserved_special_token_207|>",
|
| 1725 |
+
"lstrip": false,
|
| 1726 |
+
"normalized": false,
|
| 1727 |
+
"rstrip": false,
|
| 1728 |
+
"single_word": false,
|
| 1729 |
+
"special": true
|
| 1730 |
+
},
|
| 1731 |
+
"128216": {
|
| 1732 |
+
"content": "<|reserved_special_token_208|>",
|
| 1733 |
+
"lstrip": false,
|
| 1734 |
+
"normalized": false,
|
| 1735 |
+
"rstrip": false,
|
| 1736 |
+
"single_word": false,
|
| 1737 |
+
"special": true
|
| 1738 |
+
},
|
| 1739 |
+
"128217": {
|
| 1740 |
+
"content": "<|reserved_special_token_209|>",
|
| 1741 |
+
"lstrip": false,
|
| 1742 |
+
"normalized": false,
|
| 1743 |
+
"rstrip": false,
|
| 1744 |
+
"single_word": false,
|
| 1745 |
+
"special": true
|
| 1746 |
+
},
|
| 1747 |
+
"128218": {
|
| 1748 |
+
"content": "<|reserved_special_token_210|>",
|
| 1749 |
+
"lstrip": false,
|
| 1750 |
+
"normalized": false,
|
| 1751 |
+
"rstrip": false,
|
| 1752 |
+
"single_word": false,
|
| 1753 |
+
"special": true
|
| 1754 |
+
},
|
| 1755 |
+
"128219": {
|
| 1756 |
+
"content": "<|reserved_special_token_211|>",
|
| 1757 |
+
"lstrip": false,
|
| 1758 |
+
"normalized": false,
|
| 1759 |
+
"rstrip": false,
|
| 1760 |
+
"single_word": false,
|
| 1761 |
+
"special": true
|
| 1762 |
+
},
|
| 1763 |
+
"128220": {
|
| 1764 |
+
"content": "<|reserved_special_token_212|>",
|
| 1765 |
+
"lstrip": false,
|
| 1766 |
+
"normalized": false,
|
| 1767 |
+
"rstrip": false,
|
| 1768 |
+
"single_word": false,
|
| 1769 |
+
"special": true
|
| 1770 |
+
},
|
| 1771 |
+
"128221": {
|
| 1772 |
+
"content": "<|reserved_special_token_213|>",
|
| 1773 |
+
"lstrip": false,
|
| 1774 |
+
"normalized": false,
|
| 1775 |
+
"rstrip": false,
|
| 1776 |
+
"single_word": false,
|
| 1777 |
+
"special": true
|
| 1778 |
+
},
|
| 1779 |
+
"128222": {
|
| 1780 |
+
"content": "<|reserved_special_token_214|>",
|
| 1781 |
+
"lstrip": false,
|
| 1782 |
+
"normalized": false,
|
| 1783 |
+
"rstrip": false,
|
| 1784 |
+
"single_word": false,
|
| 1785 |
+
"special": true
|
| 1786 |
+
},
|
| 1787 |
+
"128223": {
|
| 1788 |
+
"content": "<|reserved_special_token_215|>",
|
| 1789 |
+
"lstrip": false,
|
| 1790 |
+
"normalized": false,
|
| 1791 |
+
"rstrip": false,
|
| 1792 |
+
"single_word": false,
|
| 1793 |
+
"special": true
|
| 1794 |
+
},
|
| 1795 |
+
"128224": {
|
| 1796 |
+
"content": "<|reserved_special_token_216|>",
|
| 1797 |
+
"lstrip": false,
|
| 1798 |
+
"normalized": false,
|
| 1799 |
+
"rstrip": false,
|
| 1800 |
+
"single_word": false,
|
| 1801 |
+
"special": true
|
| 1802 |
+
},
|
| 1803 |
+
"128225": {
|
| 1804 |
+
"content": "<|reserved_special_token_217|>",
|
| 1805 |
+
"lstrip": false,
|
| 1806 |
+
"normalized": false,
|
| 1807 |
+
"rstrip": false,
|
| 1808 |
+
"single_word": false,
|
| 1809 |
+
"special": true
|
| 1810 |
+
},
|
| 1811 |
+
"128226": {
|
| 1812 |
+
"content": "<|reserved_special_token_218|>",
|
| 1813 |
+
"lstrip": false,
|
| 1814 |
+
"normalized": false,
|
| 1815 |
+
"rstrip": false,
|
| 1816 |
+
"single_word": false,
|
| 1817 |
+
"special": true
|
| 1818 |
+
},
|
| 1819 |
+
"128227": {
|
| 1820 |
+
"content": "<|reserved_special_token_219|>",
|
| 1821 |
+
"lstrip": false,
|
| 1822 |
+
"normalized": false,
|
| 1823 |
+
"rstrip": false,
|
| 1824 |
+
"single_word": false,
|
| 1825 |
+
"special": true
|
| 1826 |
+
},
|
| 1827 |
+
"128228": {
|
| 1828 |
+
"content": "<|reserved_special_token_220|>",
|
| 1829 |
+
"lstrip": false,
|
| 1830 |
+
"normalized": false,
|
| 1831 |
+
"rstrip": false,
|
| 1832 |
+
"single_word": false,
|
| 1833 |
+
"special": true
|
| 1834 |
+
},
|
| 1835 |
+
"128229": {
|
| 1836 |
+
"content": "<|reserved_special_token_221|>",
|
| 1837 |
+
"lstrip": false,
|
| 1838 |
+
"normalized": false,
|
| 1839 |
+
"rstrip": false,
|
| 1840 |
+
"single_word": false,
|
| 1841 |
+
"special": true
|
| 1842 |
+
},
|
| 1843 |
+
"128230": {
|
| 1844 |
+
"content": "<|reserved_special_token_222|>",
|
| 1845 |
+
"lstrip": false,
|
| 1846 |
+
"normalized": false,
|
| 1847 |
+
"rstrip": false,
|
| 1848 |
+
"single_word": false,
|
| 1849 |
+
"special": true
|
| 1850 |
+
},
|
| 1851 |
+
"128231": {
|
| 1852 |
+
"content": "<|reserved_special_token_223|>",
|
| 1853 |
+
"lstrip": false,
|
| 1854 |
+
"normalized": false,
|
| 1855 |
+
"rstrip": false,
|
| 1856 |
+
"single_word": false,
|
| 1857 |
+
"special": true
|
| 1858 |
+
},
|
| 1859 |
+
"128232": {
|
| 1860 |
+
"content": "<|reserved_special_token_224|>",
|
| 1861 |
+
"lstrip": false,
|
| 1862 |
+
"normalized": false,
|
| 1863 |
+
"rstrip": false,
|
| 1864 |
+
"single_word": false,
|
| 1865 |
+
"special": true
|
| 1866 |
+
},
|
| 1867 |
+
"128233": {
|
| 1868 |
+
"content": "<|reserved_special_token_225|>",
|
| 1869 |
+
"lstrip": false,
|
| 1870 |
+
"normalized": false,
|
| 1871 |
+
"rstrip": false,
|
| 1872 |
+
"single_word": false,
|
| 1873 |
+
"special": true
|
| 1874 |
+
},
|
| 1875 |
+
"128234": {
|
| 1876 |
+
"content": "<|reserved_special_token_226|>",
|
| 1877 |
+
"lstrip": false,
|
| 1878 |
+
"normalized": false,
|
| 1879 |
+
"rstrip": false,
|
| 1880 |
+
"single_word": false,
|
| 1881 |
+
"special": true
|
| 1882 |
+
},
|
| 1883 |
+
"128235": {
|
| 1884 |
+
"content": "<|reserved_special_token_227|>",
|
| 1885 |
+
"lstrip": false,
|
| 1886 |
+
"normalized": false,
|
| 1887 |
+
"rstrip": false,
|
| 1888 |
+
"single_word": false,
|
| 1889 |
+
"special": true
|
| 1890 |
+
},
|
| 1891 |
+
"128236": {
|
| 1892 |
+
"content": "<|reserved_special_token_228|>",
|
| 1893 |
+
"lstrip": false,
|
| 1894 |
+
"normalized": false,
|
| 1895 |
+
"rstrip": false,
|
| 1896 |
+
"single_word": false,
|
| 1897 |
+
"special": true
|
| 1898 |
+
},
|
| 1899 |
+
"128237": {
|
| 1900 |
+
"content": "<|reserved_special_token_229|>",
|
| 1901 |
+
"lstrip": false,
|
| 1902 |
+
"normalized": false,
|
| 1903 |
+
"rstrip": false,
|
| 1904 |
+
"single_word": false,
|
| 1905 |
+
"special": true
|
| 1906 |
+
},
|
| 1907 |
+
"128238": {
|
| 1908 |
+
"content": "<|reserved_special_token_230|>",
|
| 1909 |
+
"lstrip": false,
|
| 1910 |
+
"normalized": false,
|
| 1911 |
+
"rstrip": false,
|
| 1912 |
+
"single_word": false,
|
| 1913 |
+
"special": true
|
| 1914 |
+
},
|
| 1915 |
+
"128239": {
|
| 1916 |
+
"content": "<|reserved_special_token_231|>",
|
| 1917 |
+
"lstrip": false,
|
| 1918 |
+
"normalized": false,
|
| 1919 |
+
"rstrip": false,
|
| 1920 |
+
"single_word": false,
|
| 1921 |
+
"special": true
|
| 1922 |
+
},
|
| 1923 |
+
"128240": {
|
| 1924 |
+
"content": "<|reserved_special_token_232|>",
|
| 1925 |
+
"lstrip": false,
|
| 1926 |
+
"normalized": false,
|
| 1927 |
+
"rstrip": false,
|
| 1928 |
+
"single_word": false,
|
| 1929 |
+
"special": true
|
| 1930 |
+
},
|
| 1931 |
+
"128241": {
|
| 1932 |
+
"content": "<|reserved_special_token_233|>",
|
| 1933 |
+
"lstrip": false,
|
| 1934 |
+
"normalized": false,
|
| 1935 |
+
"rstrip": false,
|
| 1936 |
+
"single_word": false,
|
| 1937 |
+
"special": true
|
| 1938 |
+
},
|
| 1939 |
+
"128242": {
|
| 1940 |
+
"content": "<|reserved_special_token_234|>",
|
| 1941 |
+
"lstrip": false,
|
| 1942 |
+
"normalized": false,
|
| 1943 |
+
"rstrip": false,
|
| 1944 |
+
"single_word": false,
|
| 1945 |
+
"special": true
|
| 1946 |
+
},
|
| 1947 |
+
"128243": {
|
| 1948 |
+
"content": "<|reserved_special_token_235|>",
|
| 1949 |
+
"lstrip": false,
|
| 1950 |
+
"normalized": false,
|
| 1951 |
+
"rstrip": false,
|
| 1952 |
+
"single_word": false,
|
| 1953 |
+
"special": true
|
| 1954 |
+
},
|
| 1955 |
+
"128244": {
|
| 1956 |
+
"content": "<|reserved_special_token_236|>",
|
| 1957 |
+
"lstrip": false,
|
| 1958 |
+
"normalized": false,
|
| 1959 |
+
"rstrip": false,
|
| 1960 |
+
"single_word": false,
|
| 1961 |
+
"special": true
|
| 1962 |
+
},
|
| 1963 |
+
"128245": {
|
| 1964 |
+
"content": "<|reserved_special_token_237|>",
|
| 1965 |
+
"lstrip": false,
|
| 1966 |
+
"normalized": false,
|
| 1967 |
+
"rstrip": false,
|
| 1968 |
+
"single_word": false,
|
| 1969 |
+
"special": true
|
| 1970 |
+
},
|
| 1971 |
+
"128246": {
|
| 1972 |
+
"content": "<|reserved_special_token_238|>",
|
| 1973 |
+
"lstrip": false,
|
| 1974 |
+
"normalized": false,
|
| 1975 |
+
"rstrip": false,
|
| 1976 |
+
"single_word": false,
|
| 1977 |
+
"special": true
|
| 1978 |
+
},
|
| 1979 |
+
"128247": {
|
| 1980 |
+
"content": "<|reserved_special_token_239|>",
|
| 1981 |
+
"lstrip": false,
|
| 1982 |
+
"normalized": false,
|
| 1983 |
+
"rstrip": false,
|
| 1984 |
+
"single_word": false,
|
| 1985 |
+
"special": true
|
| 1986 |
+
},
|
| 1987 |
+
"128248": {
|
| 1988 |
+
"content": "<|reserved_special_token_240|>",
|
| 1989 |
+
"lstrip": false,
|
| 1990 |
+
"normalized": false,
|
| 1991 |
+
"rstrip": false,
|
| 1992 |
+
"single_word": false,
|
| 1993 |
+
"special": true
|
| 1994 |
+
},
|
| 1995 |
+
"128249": {
|
| 1996 |
+
"content": "<|reserved_special_token_241|>",
|
| 1997 |
+
"lstrip": false,
|
| 1998 |
+
"normalized": false,
|
| 1999 |
+
"rstrip": false,
|
| 2000 |
+
"single_word": false,
|
| 2001 |
+
"special": true
|
| 2002 |
+
},
|
| 2003 |
+
"128250": {
|
| 2004 |
+
"content": "<|reserved_special_token_242|>",
|
| 2005 |
+
"lstrip": false,
|
| 2006 |
+
"normalized": false,
|
| 2007 |
+
"rstrip": false,
|
| 2008 |
+
"single_word": false,
|
| 2009 |
+
"special": true
|
| 2010 |
+
},
|
| 2011 |
+
"128251": {
|
| 2012 |
+
"content": "<|reserved_special_token_243|>",
|
| 2013 |
+
"lstrip": false,
|
| 2014 |
+
"normalized": false,
|
| 2015 |
+
"rstrip": false,
|
| 2016 |
+
"single_word": false,
|
| 2017 |
+
"special": true
|
| 2018 |
+
},
|
| 2019 |
+
"128252": {
|
| 2020 |
+
"content": "<|reserved_special_token_244|>",
|
| 2021 |
+
"lstrip": false,
|
| 2022 |
+
"normalized": false,
|
| 2023 |
+
"rstrip": false,
|
| 2024 |
+
"single_word": false,
|
| 2025 |
+
"special": true
|
| 2026 |
+
},
|
| 2027 |
+
"128253": {
|
| 2028 |
+
"content": "<|reserved_special_token_245|>",
|
| 2029 |
+
"lstrip": false,
|
| 2030 |
+
"normalized": false,
|
| 2031 |
+
"rstrip": false,
|
| 2032 |
+
"single_word": false,
|
| 2033 |
+
"special": true
|
| 2034 |
+
},
|
| 2035 |
+
"128254": {
|
| 2036 |
+
"content": "<|reserved_special_token_246|>",
|
| 2037 |
+
"lstrip": false,
|
| 2038 |
+
"normalized": false,
|
| 2039 |
+
"rstrip": false,
|
| 2040 |
+
"single_word": false,
|
| 2041 |
+
"special": true
|
| 2042 |
+
},
|
| 2043 |
+
"128255": {
|
| 2044 |
+
"content": "<|reserved_special_token_247|>",
|
| 2045 |
+
"lstrip": false,
|
| 2046 |
+
"normalized": false,
|
| 2047 |
+
"rstrip": false,
|
| 2048 |
+
"single_word": false,
|
| 2049 |
+
"special": true
|
| 2050 |
+
},
|
| 2051 |
+
"128256": {
|
| 2052 |
+
"content": "<|audio|>",
|
| 2053 |
+
"lstrip": false,
|
| 2054 |
+
"normalized": false,
|
| 2055 |
+
"rstrip": false,
|
| 2056 |
+
"single_word": false,
|
| 2057 |
+
"special": true
|
| 2058 |
+
}
|
| 2059 |
+
},
|
| 2060 |
+
"additional_special_tokens": [
|
| 2061 |
+
"<|audio|>"
|
| 2062 |
+
],
|
| 2063 |
+
"auto_map": {
|
| 2064 |
+
"AutoProcessor": "processor.VLFMProcessor"
|
| 2065 |
+
},
|
| 2066 |
+
"bos_token": "<|begin_of_text|>",
|
| 2067 |
+
"clean_up_tokenization_spaces": true,
|
| 2068 |
+
"eos_token": "<|eot_id|>",
|
| 2069 |
+
"extra_special_tokens": {},
|
| 2070 |
+
"model_input_names": [
|
| 2071 |
+
"input_ids",
|
| 2072 |
+
"attention_mask"
|
| 2073 |
+
],
|
| 2074 |
+
"model_max_length": 131072,
|
| 2075 |
+
"pad_token": "<|eot_id|>",
|
| 2076 |
+
"processor_class": "VLFMProcessor",
|
| 2077 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 2078 |
+
}
|