Upload 6 files
Browse files- added_tokens (1).json +24 -0
- chat_template.jinja +7 -0
- config (1).json +143 -0
- config.json +37 -0
- gitattributes (1) +27 -0
- pytorch_model.bin +3 -0
added_tokens (1).json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
|
| 2 |
+
You are a helpful assistant.<|im_end|>
|
| 3 |
+
{% endif %}<|im_start|>{{ message['role'] }}
|
| 4 |
+
{% if message['content'] is string %}{{ message['content'] }}<|im_end|>
|
| 5 |
+
{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
|
| 6 |
+
{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
|
| 7 |
+
{% endif %}
|
config (1).json
ADDED
|
@@ -0,0 +1,143 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2_5_VLForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 151643,
|
| 7 |
+
"eos_token_id": 151645,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 2048,
|
| 10 |
+
"image_token_id": 151655,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 11008,
|
| 13 |
+
"max_position_embeddings": 128000,
|
| 14 |
+
"max_window_layers": 70,
|
| 15 |
+
"model_type": "qwen2_5_vl",
|
| 16 |
+
"num_attention_heads": 16,
|
| 17 |
+
"num_hidden_layers": 36,
|
| 18 |
+
"num_key_value_heads": 2,
|
| 19 |
+
"rms_norm_eps": 1e-06,
|
| 20 |
+
"rope_scaling": {
|
| 21 |
+
"mrope_section": [
|
| 22 |
+
16,
|
| 23 |
+
24,
|
| 24 |
+
24
|
| 25 |
+
],
|
| 26 |
+
"rope_type": "default",
|
| 27 |
+
"type": "default"
|
| 28 |
+
},
|
| 29 |
+
"rope_theta": 1000000.0,
|
| 30 |
+
"sliding_window": 32768,
|
| 31 |
+
"text_config": {
|
| 32 |
+
"architectures": [
|
| 33 |
+
"Qwen2_5_VLForConditionalGeneration"
|
| 34 |
+
],
|
| 35 |
+
"attention_dropout": 0.0,
|
| 36 |
+
"bos_token_id": 151643,
|
| 37 |
+
"eos_token_id": 151645,
|
| 38 |
+
"hidden_act": "silu",
|
| 39 |
+
"hidden_size": 2048,
|
| 40 |
+
"image_token_id": null,
|
| 41 |
+
"initializer_range": 0.02,
|
| 42 |
+
"intermediate_size": 11008,
|
| 43 |
+
"layer_types": [
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"full_attention",
|
| 51 |
+
"full_attention",
|
| 52 |
+
"full_attention",
|
| 53 |
+
"full_attention",
|
| 54 |
+
"full_attention",
|
| 55 |
+
"full_attention",
|
| 56 |
+
"full_attention",
|
| 57 |
+
"full_attention",
|
| 58 |
+
"full_attention",
|
| 59 |
+
"full_attention",
|
| 60 |
+
"full_attention",
|
| 61 |
+
"full_attention",
|
| 62 |
+
"full_attention",
|
| 63 |
+
"full_attention",
|
| 64 |
+
"full_attention",
|
| 65 |
+
"full_attention",
|
| 66 |
+
"full_attention",
|
| 67 |
+
"full_attention",
|
| 68 |
+
"full_attention",
|
| 69 |
+
"full_attention",
|
| 70 |
+
"full_attention",
|
| 71 |
+
"full_attention",
|
| 72 |
+
"full_attention",
|
| 73 |
+
"full_attention",
|
| 74 |
+
"full_attention",
|
| 75 |
+
"full_attention",
|
| 76 |
+
"full_attention",
|
| 77 |
+
"full_attention",
|
| 78 |
+
"full_attention",
|
| 79 |
+
"full_attention"
|
| 80 |
+
],
|
| 81 |
+
"max_position_embeddings": 128000,
|
| 82 |
+
"max_window_layers": 70,
|
| 83 |
+
"model_type": "qwen2_5_vl_text",
|
| 84 |
+
"num_attention_heads": 16,
|
| 85 |
+
"num_hidden_layers": 36,
|
| 86 |
+
"num_key_value_heads": 2,
|
| 87 |
+
"rms_norm_eps": 1e-06,
|
| 88 |
+
"rope_scaling": {
|
| 89 |
+
"mrope_section": [
|
| 90 |
+
16,
|
| 91 |
+
24,
|
| 92 |
+
24
|
| 93 |
+
],
|
| 94 |
+
"rope_type": "default",
|
| 95 |
+
"type": "default"
|
| 96 |
+
},
|
| 97 |
+
"rope_theta": 1000000.0,
|
| 98 |
+
"sliding_window": null,
|
| 99 |
+
"tie_word_embeddings": true,
|
| 100 |
+
"torch_dtype": "bfloat16",
|
| 101 |
+
"use_cache": true,
|
| 102 |
+
"use_sliding_window": false,
|
| 103 |
+
"video_token_id": null,
|
| 104 |
+
"vision_end_token_id": 151653,
|
| 105 |
+
"vision_start_token_id": 151652,
|
| 106 |
+
"vision_token_id": 151654,
|
| 107 |
+
"vocab_size": 151936
|
| 108 |
+
},
|
| 109 |
+
"torch_dtype": "bfloat16",
|
| 110 |
+
"transformers_version": "4.55.4",
|
| 111 |
+
"use_cache": true,
|
| 112 |
+
"use_sliding_window": false,
|
| 113 |
+
"video_token_id": 151656,
|
| 114 |
+
"vision_config": {
|
| 115 |
+
"depth": 32,
|
| 116 |
+
"fullatt_block_indexes": [
|
| 117 |
+
7,
|
| 118 |
+
15,
|
| 119 |
+
23,
|
| 120 |
+
31
|
| 121 |
+
],
|
| 122 |
+
"hidden_act": "silu",
|
| 123 |
+
"hidden_size": 1280,
|
| 124 |
+
"in_channels": 3,
|
| 125 |
+
"in_chans": 3,
|
| 126 |
+
"initializer_range": 0.02,
|
| 127 |
+
"intermediate_size": 3420,
|
| 128 |
+
"model_type": "qwen2_5_vl",
|
| 129 |
+
"num_heads": 16,
|
| 130 |
+
"out_hidden_size": 2048,
|
| 131 |
+
"patch_size": 14,
|
| 132 |
+
"spatial_merge_size": 2,
|
| 133 |
+
"spatial_patch_size": 14,
|
| 134 |
+
"temporal_patch_size": 2,
|
| 135 |
+
"tokens_per_second": 2,
|
| 136 |
+
"torch_dtype": "bfloat16",
|
| 137 |
+
"window_size": 112
|
| 138 |
+
},
|
| 139 |
+
"vision_end_token_id": 151653,
|
| 140 |
+
"vision_start_token_id": 151652,
|
| 141 |
+
"vision_token_id": 151654,
|
| 142 |
+
"vocab_size": 151936
|
| 143 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "edbeeching/decision-transformer-gym-hopper-expert",
|
| 3 |
+
"act_dim": 3,
|
| 4 |
+
"action_tanh": true,
|
| 5 |
+
"activation_function": "relu",
|
| 6 |
+
"architectures": [
|
| 7 |
+
"DecisionTransformerModel"
|
| 8 |
+
],
|
| 9 |
+
"attn_pdrop": 0.1,
|
| 10 |
+
"bos_token_id": 50256,
|
| 11 |
+
"embd_pdrop": 0.1,
|
| 12 |
+
"eos_token_id": 50256,
|
| 13 |
+
"hidden_size": 128,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"layer_norm_epsilon": 1e-05,
|
| 16 |
+
"max_ep_len": 1000,
|
| 17 |
+
"model_type": "decision_transformer",
|
| 18 |
+
"n_embd": 768,
|
| 19 |
+
"n_head": 1,
|
| 20 |
+
"n_inner": null,
|
| 21 |
+
"n_layer": 3,
|
| 22 |
+
"n_positions": 1024,
|
| 23 |
+
"reorder_and_upcast_attn": false,
|
| 24 |
+
"resid_pdrop": 0.1,
|
| 25 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 26 |
+
"scale_attn_weights": true,
|
| 27 |
+
"state_dim": 11,
|
| 28 |
+
"summary_activation": null,
|
| 29 |
+
"summary_first_dropout": 0.1,
|
| 30 |
+
"summary_proj_to_labels": true,
|
| 31 |
+
"summary_type": "cls_index",
|
| 32 |
+
"summary_use_proj": true,
|
| 33 |
+
"torch_dtype": "float32",
|
| 34 |
+
"transformers_version": "4.18.0.dev0",
|
| 35 |
+
"use_cache": true,
|
| 36 |
+
"vocab_size": 1
|
| 37 |
+
}
|
gitattributes (1)
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.bz2 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 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4c16a90bfc8bcca09a015021250df79d6d1450e85ac01b7ca5ac549318695893
|
| 3 |
+
size 6600494
|