Hugging Face's logo

scb10x
/
typhoon2.1-gemma3-12b-fp8

Text Generation
Safetensors
gemma3_text
conversational
compressed-tensors
Model card Files
xet
Community
pittawat commited on
Commit
8cf2342
·
verified ·
1 Parent(s): db3bcde

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +3 -0
  3. chat_template.jinja +146 -0
  4. config.json +134 -0
  5. generation_config.json +13 -0
  6. model-00001-of-00003.safetensors +3 -0
  7. model-00002-of-00003.safetensors +3 -0
  8. model-00003-of-00003.safetensors +3 -0
  9. model.safetensors.index.json +971 -0
  10. recipe.yaml +6 -0
  11. special_tokens_map.json +33 -0
  12. tokenizer.json +3 -0
  13. tokenizer.model +3 -0
  14. tokenizer_config.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* 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
 
 
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
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<image_soft_token>": 262144
3
+ }
chat_template.jinja ADDED
@@ -0,0 +1,146 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {#- Begin-of-sequence token to start the model prompt -#}
2
+ {{ bos_token }}
3
+ {#- Extracts the system message. Gemma does not support system messages so it will be prepended to first user message. -#}
4
+ {%- if messages[0]['role'] == 'system' -%}
5
+ {%- if messages[0]['content'] is string -%}
6
+ {%- set first_user_prefix = messages[0]['content'] -%}
7
+ {%- else -%}
8
+ {%- set first_user_prefix = messages[0]['content'][0]['text'] -%}
9
+ {%- endif -%}
10
+ {%- set loop_messages = messages[1:] -%}
11
+ {%- else -%}
12
+ {%- set first_user_prefix = "You are a helpful assistant named Typhoon created by SCB 10X to be helpful, harmless, and honest." -%}
13
+ {%- set loop_messages = messages -%}
14
+ {%- endif -%}
15
+ {%- if enable_thinking is defined and enable_thinking is true %}
16
+ {%- set first_user_prefix = first_user_prefix + " First, think through the reasoning internally, then present the reasoning within <think>...</think>. After thinking, clearly state a response that addresses the user's request and aligns with their preferences, not just providing a direct answer." -%}
17
+ {%- endif %}
18
+ {%- set first_user_prefix = first_user_prefix + '\n\n' -%}
19
+ {#- Set tools to none if not defined for this ChatCompletion request (helps avoid errors later) -#}
20
+ {%- if not tools is defined %}
21
+ {%- set tools = none %}
22
+ {%- endif %}
23
+
24
+ {#- If given only system message -#}
25
+ {%- if loop_messages|length == 0 -%}
26
+ {{ '<start_of_turn>user\n' -}}
27
+ {{ first_user_prefix }}
28
+ {#- Append system message with tool information if using tools in message request. -#}
29
+ {%- if tools is not none -%}
30
+ {{- "Tools (functions) are available. If you decide to invoke one or more of the tools, you must respond with a python list of the function calls.\n" -}}
31
+ {{- "Example Format: [func_name1(params_name1=params_value1, params_name2=params_value2...), func_name2(params)] \n" -}}
32
+ {{- "Do not use variables. DO NOT USE MARKDOWN SYNTAX. You SHOULD NOT include any other text in the response if you call a function. If none of the functions can be used, point it out. If you lack the parameters required by the function, also point it out.\n" -}}
33
+ {{- "Here is a list of functions in JSON format that you can invoke.\n" -}}
34
+ {{- tools | tojson(indent=4) -}}
35
+ {{- "\n\n" -}}
36
+ {%- endif -%}
37
+ {%- endif %}
38
+
39
+ {#- Main loop over all messages in the conversation history -#}
40
+ {%- for message in loop_messages -%}
41
+ {#- Normalize roles for model prompt formatting -#}
42
+ {%- if (message['role'] == 'assistant') -%}
43
+ {%- set role = "model" -%}
44
+ {%- elif (message['role'] == 'tool') -%}
45
+ {%- set role = "user" -%}
46
+ {%- else -%}
47
+ {%- set role = message['role'] -%}
48
+ {%- endif -%}
49
+ {#- Mark the start of a message block with the appropriate role -#}
50
+ {{ '<start_of_turn>' + role + '\n' -}}
51
+
52
+ {#- Insert system message content (if present) at the beginning of the first message. -#}
53
+ {%- if loop.first -%}
54
+ {{ first_user_prefix }}
55
+ {#- Append system message with tool information if using tools in message request. -#}
56
+ {%- if tools is not none -%}
57
+ {{- "Tools (functions) are available. If you decide to invoke one or more of the tools, you must respond with a python list of the function calls.\n" -}}
58
+ {{- "Example Format: [func_name1(params_name1=params_value1, params_name2=params_value2...), func_name2(params)] \n" -}}
59
+ {{- "Do not use variables. DO NOT USE MARKDOWN SYNTAX. You SHOULD NOT include any other text in the response if you call a function. If none of the functions can be used, point it out. If you lack the parameters required by the function, also point it out.\n" -}}
60
+ {{- "Here is a list of functions in JSON format that you can invoke.\n" -}}
61
+ {{- tools | tojson(indent=4) -}}
62
+ {{- "\n\n" -}}
63
+ {%- endif -%}
64
+ {%- endif -%}
65
+
66
+ {#- Format model tool calls (turns where model indicates they want to call a tool) -#}
67
+ {%- if 'tool_calls' in message -%}
68
+ {#- Opening bracket for tool call list. -#}
69
+ {{- '[' -}}
70
+ {#- For each tool call -#}
71
+ {%- for tool_call in message.tool_calls -%}
72
+ {#- Function name & opening parenthesis. -#}
73
+ {%- if tool_call.function is defined -%}
74
+ {%- set tool_call = tool_call.function -%}
75
+ {%- endif -%}
76
+ {{- tool_call.name + '(' -}}
77
+
78
+ {#-- Handle arguments as list (positional) or dict (named) --#}
79
+ {#-- Named arguments (dict) --#}
80
+ {%- if tool_call.arguments is iterable and tool_call.arguments is mapping -%}
81
+ {%- set first = true -%}
82
+ {%- for key, val in tool_call.arguments.items() -%}
83
+ {%- if not first %}, {% endif -%}
84
+ {{ key }}={{ val | tojson }}
85
+ {%- set first = false -%}
86
+ {%- endfor -%}
87
+ {#-- Positional arguments (list) --#}
88
+ {%- elif tool_call.arguments is iterable -%}
89
+ {{- tool_call.arguments | map('tojson') | join(', ') -}}
90
+ {#-- Fallback: single positional value --#}
91
+ {%- else -%}
92
+ {{- tool_call.arguments | tojson -}}
93
+ {#-- Closing parenthesis. --#}
94
+ {%- endif -%}
95
+ {{- ')' -}}
96
+ {#-- If more than one tool call, place comma and move to formatting next tool call --#}
97
+ {%- if not loop.last -%}, {% endif -%}
98
+ {%- endfor -%}
99
+ {#- Closing bracket for tool call list. -#}
100
+ {{- ']' -}}
101
+ {%- endif -%}
102
+
103
+ {#- Tool response start tag (for messages from a tool) -#}
104
+ {%- if (message['role'] == 'tool') -%}
105
+ {{ '<tool_response>\n' -}}
106
+ {%- endif -%}
107
+
108
+ {#- Render the message content: handle plain string or multimodal content like image/text -#}
109
+ {%- if message['content'] is string -%}
110
+ {%- set content = message['content'] -%}
111
+ {%- if '</think>' in content -%}
112
+ {%- set content = content.split('</think>')[-1] -%}
113
+ {%- endif -%}
114
+ {{ content | trim }}
115
+ {%- elif message['content'] is iterable -%}
116
+ {%- for item in message['content'] -%}
117
+ {%- if item['type'] == 'image' -%}
118
+ {{ '<start_of_image>' }}
119
+ {%- elif item['type'] == 'text' -%}
120
+ {%- set content = item['text'] -%}
121
+ {%- if '</think>' in content -%}
122
+ {%- set content = content.split('</think>')[-1] -%}
123
+ {%- endif -%}
124
+ {{ content | trim }}
125
+ {%- endif -%}
126
+ {%- endfor -%}
127
+ {%- else -%}
128
+ {{ raise_exception("Invalid content type") }}
129
+ {%- endif -%}
130
+
131
+ {#- Tool response end tag -#}
132
+ {%- if (message['role'] == 'tool') -%}
133
+ {{ '</tool_response>' -}}
134
+ {%- endif -%}
135
+
136
+ {#- Mark end of a single turn -#}
137
+ {{ '<end_of_turn>\n' }}
138
+ {%- endfor -%}
139
+
140
+ {#- If generation is to be triggered, add model prompt prefix -#}
141
+ {%- if add_generation_prompt -%}
142
+ {{'<start_of_turn>model\n'}}
143
+ {%- if enable_thinking is defined and enable_thinking is true -%}
144
+ {{- '<think>' -}}
145
+ {%- endif %}
146
+ {%- endif -%}
config.json ADDED
@@ -0,0 +1,134 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_sliding_window_pattern": 6,
3
+ "architectures": [
4
+ "Gemma3ForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "attn_logit_softcapping": null,
9
+ "bos_token_id": 2,
10
+ "cache_implementation": "hybrid",
11
+ "eos_token_id": 1,
12
+ "final_logit_softcapping": null,
13
+ "head_dim": 256,
14
+ "hidden_activation": "gelu_pytorch_tanh",
15
+ "hidden_size": 3840,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 15360,
18
+ "layer_types": [
19
+ "sliding_attention",
20
+ "sliding_attention",
21
+ "sliding_attention",
22
+ "sliding_attention",
23
+ "sliding_attention",
24
+ "full_attention",
25
+ "sliding_attention",
26
+ "sliding_attention",
27
+ "sliding_attention",
28
+ "sliding_attention",
29
+ "sliding_attention",
30
+ "full_attention",
31
+ "sliding_attention",
32
+ "sliding_attention",
33
+ "sliding_attention",
34
+ "sliding_attention",
35
+ "sliding_attention",
36
+ "full_attention",
37
+ "sliding_attention",
38
+ "sliding_attention",
39
+ "sliding_attention",
40
+ "sliding_attention",
41
+ "sliding_attention",
42
+ "full_attention",
43
+ "sliding_attention",
44
+ "sliding_attention",
45
+ "sliding_attention",
46
+ "sliding_attention",
47
+ "sliding_attention",
48
+ "full_attention",
49
+ "sliding_attention",
50
+ "sliding_attention",
51
+ "sliding_attention",
52
+ "sliding_attention",
53
+ "sliding_attention",
54
+ "full_attention",
55
+ "sliding_attention",
56
+ "sliding_attention",
57
+ "sliding_attention",
58
+ "sliding_attention",
59
+ "sliding_attention",
60
+ "full_attention",
61
+ "sliding_attention",
62
+ "sliding_attention",
63
+ "sliding_attention",
64
+ "sliding_attention",
65
+ "sliding_attention",
66
+ "full_attention"
67
+ ],
68
+ "max_position_embeddings": 131072,
69
+ "model_type": "gemma3_text",
70
+ "num_attention_heads": 16,
71
+ "num_hidden_layers": 48,
72
+ "num_key_value_heads": 8,
73
+ "pad_token_id": 0,
74
+ "quantization_config": {
75
+ "config_groups": {
76
+ "group_0": {
77
+ "format": "float-quantized",
78
+ "input_activations": {
79
+ "actorder": null,
80
+ "block_structure": null,
81
+ "dynamic": true,
82
+ "group_size": null,
83
+ "num_bits": 8,
84
+ "observer": null,
85
+ "observer_kwargs": {},
86
+ "strategy": "token",
87
+ "symmetric": true,
88
+ "type": "float"
89
+ },
90
+ "output_activations": null,
91
+ "targets": [
92
+ "Linear"
93
+ ],
94
+ "weights": {
95
+ "actorder": null,
96
+ "block_structure": null,
97
+ "dynamic": false,
98
+ "group_size": null,
99
+ "num_bits": 8,
100
+ "observer": "minmax",
101
+ "observer_kwargs": {},
102
+ "strategy": "channel",
103
+ "symmetric": true,
104
+ "type": "float"
105
+ }
106
+ }
107
+ },
108
+ "format": "float-quantized",
109
+ "global_compression_ratio": null,
110
+ "ignore": [
111
+ "lm_head"
112
+ ],
113
+ "kv_cache_scheme": null,
114
+ "quant_method": "compressed-tensors",
115
+ "quantization_status": "compressed",
116
+ "sparsity_config": {},
117
+ "transform_config": {},
118
+ "version": "0.11.0"
119
+ },
120
+ "query_pre_attn_scalar": 256,
121
+ "rms_norm_eps": 1e-06,
122
+ "rope_local_base_freq": 10000.0,
123
+ "rope_scaling": {
124
+ "factor": 8.0,
125
+ "rope_type": "linear"
126
+ },
127
+ "rope_theta": 1000000.0,
128
+ "sliding_window": 1024,
129
+ "tie_word_embeddings": false,
130
+ "torch_dtype": "bfloat16",
131
+ "transformers_version": "4.55.0",
132
+ "use_cache": false,
133
+ "vocab_size": 262145
134
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 2,
3
+ "cache_implementation": "hybrid",
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 1,
7
+ 106
8
+ ],
9
+ "pad_token_id": 0,
10
+ "top_k": 64,
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.55.0"
13
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9751a3acd05092bce0172447a8d35a60e391f210adb16ae04a395bc7ac2b07f
3
+ size 4975871288
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10601ea13126ac2d2eede40aa57332776def2613eaa4ab68bbd263385db3cf95
3
+ size 4992740792
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28758c78ea81b839dac464a50cb68ecb0d30350855b62e91dbaf357816d3c260
3
+ size 4822441496
model.safetensors.index.json ADDED
@@ -0,0 +1,971 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 12774665472,
4
+ "total_size": 14790941184
5
+ },
6
+ "weight_map": {
7
+ "lm_head.weight": "model-00003-of-00003.safetensors",
8
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
16
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.0.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
22
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.0.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
24
+ "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
26
+ "model.layers.0.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
27
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
28
+ "model.layers.0.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
29
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
30
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
31
+ "model.layers.1.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
32
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
33
+ "model.layers.1.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
34
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
35
+ "model.layers.1.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
36
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
37
+ "model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
38
+ "model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
39
+ "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
40
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
41
+ "model.layers.1.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
42
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
43
+ "model.layers.1.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
44
+ "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
45
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
46
+ "model.layers.1.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
47
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
48
+ "model.layers.1.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
49
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
50
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
51
+ "model.layers.10.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
52
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
53
+ "model.layers.10.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
54
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
55
+ "model.layers.10.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
56
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
57
+ "model.layers.10.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
58
+ "model.layers.10.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
59
+ "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
60
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
61
+ "model.layers.10.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
62
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
63
+ "model.layers.10.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
64
+ "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
65
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
66
+ "model.layers.10.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
67
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
68
+ "model.layers.10.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
69
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
70
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
71
+ "model.layers.11.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
72
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
73
+ "model.layers.11.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
74
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
75
+ "model.layers.11.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
76
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
77
+ "model.layers.11.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
78
+ "model.layers.11.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
79
+ "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
80
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
81
+ "model.layers.11.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
82
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
83
+ "model.layers.11.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
84
+ "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
85
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
86
+ "model.layers.11.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
87
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
88
+ "model.layers.11.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
89
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
90
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
91
+ "model.layers.12.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
92
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
93
+ "model.layers.12.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
94
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
95
+ "model.layers.12.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
96
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
97
+ "model.layers.12.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
98
+ "model.layers.12.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
99
+ "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
100
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
101
+ "model.layers.12.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
102
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
103
+ "model.layers.12.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
104
+ "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
105
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
106
+ "model.layers.12.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
107
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
108
+ "model.layers.12.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
109
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.13.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
112
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.13.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
114
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.13.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
116
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
117
+ "model.layers.13.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
118
+ "model.layers.13.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
119
+ "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
120
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
121
+ "model.layers.13.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
122
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
123
+ "model.layers.13.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
124
+ "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
125
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
126
+ "model.layers.13.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
127
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
128
+ "model.layers.13.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
129
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
130
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
131
+ "model.layers.14.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
132
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.14.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
134
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
135
+ "model.layers.14.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
136
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
137
+ "model.layers.14.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
138
+ "model.layers.14.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
139
+ "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
140
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
141
+ "model.layers.14.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
142
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
143
+ "model.layers.14.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
144
+ "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
145
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
146
+ "model.layers.14.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
147
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
148
+ "model.layers.14.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
149
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
150
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
151
+ "model.layers.15.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
152
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
153
+ "model.layers.15.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
154
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
155
+ "model.layers.15.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
156
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
157
+ "model.layers.15.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
158
+ "model.layers.15.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
159
+ "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
160
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
161
+ "model.layers.15.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
162
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
163
+ "model.layers.15.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
164
+ "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
165
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
166
+ "model.layers.15.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
167
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
168
+ "model.layers.15.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
169
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
170
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
171
+ "model.layers.16.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
172
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
173
+ "model.layers.16.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
174
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
175
+ "model.layers.16.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
176
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
177
+ "model.layers.16.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
178
+ "model.layers.16.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
179
+ "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
180
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
181
+ "model.layers.16.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
182
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
183
+ "model.layers.16.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
184
+ "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
185
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
186
+ "model.layers.16.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
187
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
188
+ "model.layers.16.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
189
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
190
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
191
+ "model.layers.17.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
192
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
193
+ "model.layers.17.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
194
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
195
+ "model.layers.17.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
196
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
197
+ "model.layers.17.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
198
+ "model.layers.17.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
199
+ "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
200
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
201
+ "model.layers.17.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
202
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
203
+ "model.layers.17.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
204
+ "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
205
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
206
+ "model.layers.17.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
207
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
208
+ "model.layers.17.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
209
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
210
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
211
+ "model.layers.18.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
212
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
213
+ "model.layers.18.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
214
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
215
+ "model.layers.18.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
216
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
217
+ "model.layers.18.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
218
+ "model.layers.18.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
219
+ "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
220
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
221
+ "model.layers.18.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
222
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
223
+ "model.layers.18.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
224
+ "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
225
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
226
+ "model.layers.18.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
227
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
228
+ "model.layers.18.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
229
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
230
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
231
+ "model.layers.19.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
232
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
233
+ "model.layers.19.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
234
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
235
+ "model.layers.19.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
236
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
237
+ "model.layers.19.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
238
+ "model.layers.19.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
239
+ "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
240
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
241
+ "model.layers.19.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
242
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
243
+ "model.layers.19.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
244
+ "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
245
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
246
+ "model.layers.19.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
247
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
248
+ "model.layers.19.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
249
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
250
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
251
+ "model.layers.2.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
252
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
253
+ "model.layers.2.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
254
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
255
+ "model.layers.2.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
256
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
257
+ "model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
258
+ "model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
259
+ "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
260
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
261
+ "model.layers.2.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
262
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
263
+ "model.layers.2.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
264
+ "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
265
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
266
+ "model.layers.2.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
267
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
268
+ "model.layers.2.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
269
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
270
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
271
+ "model.layers.20.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
272
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
273
+ "model.layers.20.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
274
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
275
+ "model.layers.20.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
276
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
277
+ "model.layers.20.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
278
+ "model.layers.20.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
279
+ "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
280
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
281
+ "model.layers.20.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
282
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
283
+ "model.layers.20.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
284
+ "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
285
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
286
+ "model.layers.20.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
287
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
288
+ "model.layers.20.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
289
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
290
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
291
+ "model.layers.21.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
292
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
293
+ "model.layers.21.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
294
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
295
+ "model.layers.21.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
296
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
297
+ "model.layers.21.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
298
+ "model.layers.21.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
299
+ "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
300
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
301
+ "model.layers.21.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
302
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
303
+ "model.layers.21.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
304
+ "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
305
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
306
+ "model.layers.21.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
307
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
308
+ "model.layers.21.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
309
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
310
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
311
+ "model.layers.22.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
312
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
313
+ "model.layers.22.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
314
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
315
+ "model.layers.22.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
316
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
317
+ "model.layers.22.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
318
+ "model.layers.22.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
319
+ "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
320
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
321
+ "model.layers.22.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
322
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
323
+ "model.layers.22.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
324
+ "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
325
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
326
+ "model.layers.22.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
327
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
328
+ "model.layers.22.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
329
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
330
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
331
+ "model.layers.23.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
332
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
333
+ "model.layers.23.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
334
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
335
+ "model.layers.23.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
336
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
337
+ "model.layers.23.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
338
+ "model.layers.23.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
339
+ "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
340
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
341
+ "model.layers.23.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
342
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
343
+ "model.layers.23.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
344
+ "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
345
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
346
+ "model.layers.23.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
347
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
348
+ "model.layers.23.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
349
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
350
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
351
+ "model.layers.24.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
352
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
353
+ "model.layers.24.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
354
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
355
+ "model.layers.24.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
356
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
357
+ "model.layers.24.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
358
+ "model.layers.24.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
359
+ "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
360
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
361
+ "model.layers.24.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
362
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
363
+ "model.layers.24.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
364
+ "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
365
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
366
+ "model.layers.24.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
367
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
368
+ "model.layers.24.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
369
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
370
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
371
+ "model.layers.25.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
372
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
373
+ "model.layers.25.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
374
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
375
+ "model.layers.25.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
376
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
377
+ "model.layers.25.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
378
+ "model.layers.25.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
379
+ "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
380
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
381
+ "model.layers.25.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
382
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
383
+ "model.layers.25.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
384
+ "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
385
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
386
+ "model.layers.25.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
387
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
388
+ "model.layers.25.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
389
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
390
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
391
+ "model.layers.26.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
392
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
393
+ "model.layers.26.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
394
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
395
+ "model.layers.26.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
396
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
397
+ "model.layers.26.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
398
+ "model.layers.26.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
399
+ "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
400
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
401
+ "model.layers.26.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
402
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
403
+ "model.layers.26.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
404
+ "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
405
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
406
+ "model.layers.26.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
407
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
408
+ "model.layers.26.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
409
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
410
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
411
+ "model.layers.27.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
412
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
413
+ "model.layers.27.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
414
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
415
+ "model.layers.27.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
416
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
417
+ "model.layers.27.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
418
+ "model.layers.27.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
419
+ "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
420
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
421
+ "model.layers.27.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
422
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
423
+ "model.layers.27.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
424
+ "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
425
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
426
+ "model.layers.27.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
427
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
428
+ "model.layers.27.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
429
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
430
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
431
+ "model.layers.28.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
432
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
433
+ "model.layers.28.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
434
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
435
+ "model.layers.28.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
436
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
437
+ "model.layers.28.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
438
+ "model.layers.28.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
439
+ "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
440
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
441
+ "model.layers.28.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
442
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
443
+ "model.layers.28.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
444
+ "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
445
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
446
+ "model.layers.28.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
447
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
448
+ "model.layers.28.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
449
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
450
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
451
+ "model.layers.29.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
452
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
453
+ "model.layers.29.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
454
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
455
+ "model.layers.29.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
456
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
457
+ "model.layers.29.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
458
+ "model.layers.29.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
459
+ "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
460
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
461
+ "model.layers.29.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
462
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
463
+ "model.layers.29.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
464
+ "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
465
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
466
+ "model.layers.29.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
467
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
468
+ "model.layers.29.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
469
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
470
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
471
+ "model.layers.3.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
472
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
473
+ "model.layers.3.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
474
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
475
+ "model.layers.3.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
476
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
477
+ "model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
478
+ "model.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
479
+ "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
480
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
481
+ "model.layers.3.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
482
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
483
+ "model.layers.3.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
484
+ "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
485
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
486
+ "model.layers.3.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
487
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
488
+ "model.layers.3.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
489
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors",
490
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
491
+ "model.layers.30.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
492
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
493
+ "model.layers.30.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
494
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
495
+ "model.layers.30.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
496
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
497
+ "model.layers.30.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
498
+ "model.layers.30.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
499
+ "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
500
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
501
+ "model.layers.30.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
502
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
503
+ "model.layers.30.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
504
+ "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
505
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
506
+ "model.layers.30.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
507
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
508
+ "model.layers.30.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
509
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors",
510
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
511
+ "model.layers.31.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
512
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
513
+ "model.layers.31.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
514
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
515
+ "model.layers.31.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
516
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
517
+ "model.layers.31.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
518
+ "model.layers.31.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
519
+ "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
520
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
521
+ "model.layers.31.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
522
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
523
+ "model.layers.31.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
524
+ "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
525
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
526
+ "model.layers.31.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
527
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
528
+ "model.layers.31.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
529
+ "model.layers.32.input_layernorm.weight": "model-00002-of-00003.safetensors",
530
+ "model.layers.32.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
531
+ "model.layers.32.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
532
+ "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
533
+ "model.layers.32.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
534
+ "model.layers.32.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
535
+ "model.layers.32.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
536
+ "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
537
+ "model.layers.32.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
538
+ "model.layers.32.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
539
+ "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
540
+ "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
541
+ "model.layers.32.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
542
+ "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
543
+ "model.layers.32.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
544
+ "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
545
+ "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
546
+ "model.layers.32.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
547
+ "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
548
+ "model.layers.32.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
549
+ "model.layers.33.input_layernorm.weight": "model-00002-of-00003.safetensors",
550
+ "model.layers.33.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
551
+ "model.layers.33.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
552
+ "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
553
+ "model.layers.33.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
554
+ "model.layers.33.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
555
+ "model.layers.33.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
556
+ "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
557
+ "model.layers.33.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
558
+ "model.layers.33.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
559
+ "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
560
+ "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
561
+ "model.layers.33.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
562
+ "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
563
+ "model.layers.33.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
564
+ "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
565
+ "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
566
+ "model.layers.33.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
567
+ "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
568
+ "model.layers.33.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
569
+ "model.layers.34.input_layernorm.weight": "model-00002-of-00003.safetensors",
570
+ "model.layers.34.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
571
+ "model.layers.34.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
572
+ "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
573
+ "model.layers.34.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
574
+ "model.layers.34.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
575
+ "model.layers.34.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
576
+ "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
577
+ "model.layers.34.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
578
+ "model.layers.34.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
579
+ "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
580
+ "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
581
+ "model.layers.34.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
582
+ "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
583
+ "model.layers.34.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
584
+ "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
585
+ "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
586
+ "model.layers.34.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
587
+ "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
588
+ "model.layers.34.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
589
+ "model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
590
+ "model.layers.35.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
591
+ "model.layers.35.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
592
+ "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
593
+ "model.layers.35.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
594
+ "model.layers.35.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
595
+ "model.layers.35.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
596
+ "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
597
+ "model.layers.35.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
598
+ "model.layers.35.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
599
+ "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
600
+ "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
601
+ "model.layers.35.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
602
+ "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
603
+ "model.layers.35.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
604
+ "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
605
+ "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
606
+ "model.layers.35.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
607
+ "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
608
+ "model.layers.35.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
609
+ "model.layers.36.input_layernorm.weight": "model-00003-of-00003.safetensors",
610
+ "model.layers.36.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
611
+ "model.layers.36.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
612
+ "model.layers.36.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
613
+ "model.layers.36.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
614
+ "model.layers.36.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
615
+ "model.layers.36.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
616
+ "model.layers.36.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
617
+ "model.layers.36.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
618
+ "model.layers.36.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
619
+ "model.layers.36.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
620
+ "model.layers.36.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
621
+ "model.layers.36.self_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
622
+ "model.layers.36.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
623
+ "model.layers.36.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
624
+ "model.layers.36.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
625
+ "model.layers.36.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
626
+ "model.layers.36.self_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
627
+ "model.layers.36.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
628
+ "model.layers.36.self_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
629
+ "model.layers.37.input_layernorm.weight": "model-00003-of-00003.safetensors",
630
+ "model.layers.37.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
631
+ "model.layers.37.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
632
+ "model.layers.37.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
633
+ "model.layers.37.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
634
+ "model.layers.37.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
635
+ "model.layers.37.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
636
+ "model.layers.37.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
637
+ "model.layers.37.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
638
+ "model.layers.37.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
639
+ "model.layers.37.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
640
+ "model.layers.37.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
641
+ "model.layers.37.self_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
642
+ "model.layers.37.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
643
+ "model.layers.37.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
644
+ "model.layers.37.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
645
+ "model.layers.37.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
646
+ "model.layers.37.self_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
647
+ "model.layers.37.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
648
+ "model.layers.37.self_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
649
+ "model.layers.38.input_layernorm.weight": "model-00003-of-00003.safetensors",
650
+ "model.layers.38.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
651
+ "model.layers.38.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
652
+ "model.layers.38.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
653
+ "model.layers.38.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
654
+ "model.layers.38.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
655
+ "model.layers.38.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
656
+ "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
657
+ "model.layers.38.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
658
+ "model.layers.38.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
659
+ "model.layers.38.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
660
+ "model.layers.38.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
661
+ "model.layers.38.self_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
662
+ "model.layers.38.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
663
+ "model.layers.38.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
664
+ "model.layers.38.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
665
+ "model.layers.38.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
666
+ "model.layers.38.self_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
667
+ "model.layers.38.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
668
+ "model.layers.38.self_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
669
+ "model.layers.39.input_layernorm.weight": "model-00003-of-00003.safetensors",
670
+ "model.layers.39.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
671
+ "model.layers.39.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
672
+ "model.layers.39.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
673
+ "model.layers.39.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
674
+ "model.layers.39.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
675
+ "model.layers.39.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
676
+ "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
677
+ "model.layers.39.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
678
+ "model.layers.39.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
679
+ "model.layers.39.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
680
+ "model.layers.39.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
681
+ "model.layers.39.self_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
682
+ "model.layers.39.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
683
+ "model.layers.39.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
684
+ "model.layers.39.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
685
+ "model.layers.39.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
686
+ "model.layers.39.self_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
687
+ "model.layers.39.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
688
+ "model.layers.39.self_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
689
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
690
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
691
+ "model.layers.4.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
692
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
693
+ "model.layers.4.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
694
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
695
+ "model.layers.4.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
696
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
697
+ "model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
698
+ "model.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
699
+ "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
700
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
701
+ "model.layers.4.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
702
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
703
+ "model.layers.4.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
704
+ "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
705
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
706
+ "model.layers.4.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
707
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
708
+ "model.layers.4.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
709
+ "model.layers.40.input_layernorm.weight": "model-00003-of-00003.safetensors",
710
+ "model.layers.40.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
711
+ "model.layers.40.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
712
+ "model.layers.40.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
713
+ "model.layers.40.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
714
+ "model.layers.40.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
715
+ "model.layers.40.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
716
+ "model.layers.40.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
717
+ "model.layers.40.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
718
+ "model.layers.40.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
719
+ "model.layers.40.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
720
+ "model.layers.40.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
721
+ "model.layers.40.self_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
722
+ "model.layers.40.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
723
+ "model.layers.40.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
724
+ "model.layers.40.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
725
+ "model.layers.40.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
726
+ "model.layers.40.self_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
727
+ "model.layers.40.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
728
+ "model.layers.40.self_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
729
+ "model.layers.41.input_layernorm.weight": "model-00003-of-00003.safetensors",
730
+ "model.layers.41.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
731
+ "model.layers.41.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
732
+ "model.layers.41.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
733
+ "model.layers.41.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
734
+ "model.layers.41.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
735
+ "model.layers.41.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
736
+ "model.layers.41.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
737
+ "model.layers.41.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
738
+ "model.layers.41.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
739
+ "model.layers.41.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
740
+ "model.layers.41.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
741
+ "model.layers.41.self_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
742
+ "model.layers.41.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
743
+ "model.layers.41.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
744
+ "model.layers.41.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
745
+ "model.layers.41.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
746
+ "model.layers.41.self_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
747
+ "model.layers.41.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
748
+ "model.layers.41.self_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
749
+ "model.layers.42.input_layernorm.weight": "model-00003-of-00003.safetensors",
750
+ "model.layers.42.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
751
+ "model.layers.42.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
752
+ "model.layers.42.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
753
+ "model.layers.42.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
754
+ "model.layers.42.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
755
+ "model.layers.42.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
756
+ "model.layers.42.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
757
+ "model.layers.42.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
758
+ "model.layers.42.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
759
+ "model.layers.42.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
760
+ "model.layers.42.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
761
+ "model.layers.42.self_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
762
+ "model.layers.42.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
763
+ "model.layers.42.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
764
+ "model.layers.42.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
765
+ "model.layers.42.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
766
+ "model.layers.42.self_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
767
+ "model.layers.42.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
768
+ "model.layers.42.self_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
769
+ "model.layers.43.input_layernorm.weight": "model-00003-of-00003.safetensors",
770
+ "model.layers.43.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
771
+ "model.layers.43.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
772
+ "model.layers.43.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
773
+ "model.layers.43.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
774
+ "model.layers.43.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
775
+ "model.layers.43.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
776
+ "model.layers.43.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
777
+ "model.layers.43.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
778
+ "model.layers.43.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
779
+ "model.layers.43.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
780
+ "model.layers.43.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
781
+ "model.layers.43.self_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
782
+ "model.layers.43.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
783
+ "model.layers.43.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
784
+ "model.layers.43.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
785
+ "model.layers.43.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
786
+ "model.layers.43.self_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
787
+ "model.layers.43.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
788
+ "model.layers.43.self_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
789
+ "model.layers.44.input_layernorm.weight": "model-00003-of-00003.safetensors",
790
+ "model.layers.44.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
791
+ "model.layers.44.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
792
+ "model.layers.44.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
793
+ "model.layers.44.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
794
+ "model.layers.44.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
795
+ "model.layers.44.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
796
+ "model.layers.44.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
797
+ "model.layers.44.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
798
+ "model.layers.44.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
799
+ "model.layers.44.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
800
+ "model.layers.44.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
801
+ "model.layers.44.self_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
802
+ "model.layers.44.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
803
+ "model.layers.44.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
804
+ "model.layers.44.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
805
+ "model.layers.44.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
806
+ "model.layers.44.self_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
807
+ "model.layers.44.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
808
+ "model.layers.44.self_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
809
+ "model.layers.45.input_layernorm.weight": "model-00003-of-00003.safetensors",
810
+ "model.layers.45.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
811
+ "model.layers.45.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
812
+ "model.layers.45.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
813
+ "model.layers.45.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
814
+ "model.layers.45.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
815
+ "model.layers.45.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
816
+ "model.layers.45.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
817
+ "model.layers.45.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
818
+ "model.layers.45.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
819
+ "model.layers.45.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
820
+ "model.layers.45.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
821
+ "model.layers.45.self_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
822
+ "model.layers.45.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
823
+ "model.layers.45.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
824
+ "model.layers.45.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
825
+ "model.layers.45.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
826
+ "model.layers.45.self_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
827
+ "model.layers.45.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
828
+ "model.layers.45.self_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
829
+ "model.layers.46.input_layernorm.weight": "model-00003-of-00003.safetensors",
830
+ "model.layers.46.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
831
+ "model.layers.46.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
832
+ "model.layers.46.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
833
+ "model.layers.46.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
834
+ "model.layers.46.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
835
+ "model.layers.46.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
836
+ "model.layers.46.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
837
+ "model.layers.46.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
838
+ "model.layers.46.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
839
+ "model.layers.46.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
840
+ "model.layers.46.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
841
+ "model.layers.46.self_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
842
+ "model.layers.46.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
843
+ "model.layers.46.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
844
+ "model.layers.46.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
845
+ "model.layers.46.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
846
+ "model.layers.46.self_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
847
+ "model.layers.46.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
848
+ "model.layers.46.self_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
849
+ "model.layers.47.input_layernorm.weight": "model-00003-of-00003.safetensors",
850
+ "model.layers.47.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
851
+ "model.layers.47.mlp.down_proj.weight_scale": "model-00003-of-00003.safetensors",
852
+ "model.layers.47.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
853
+ "model.layers.47.mlp.gate_proj.weight_scale": "model-00003-of-00003.safetensors",
854
+ "model.layers.47.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
855
+ "model.layers.47.mlp.up_proj.weight_scale": "model-00003-of-00003.safetensors",
856
+ "model.layers.47.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
857
+ "model.layers.47.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
858
+ "model.layers.47.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
859
+ "model.layers.47.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
860
+ "model.layers.47.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
861
+ "model.layers.47.self_attn.k_proj.weight_scale": "model-00003-of-00003.safetensors",
862
+ "model.layers.47.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
863
+ "model.layers.47.self_attn.o_proj.weight_scale": "model-00003-of-00003.safetensors",
864
+ "model.layers.47.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
865
+ "model.layers.47.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
866
+ "model.layers.47.self_attn.q_proj.weight_scale": "model-00003-of-00003.safetensors",
867
+ "model.layers.47.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
868
+ "model.layers.47.self_attn.v_proj.weight_scale": "model-00003-of-00003.safetensors",
869
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
870
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
871
+ "model.layers.5.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
872
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
873
+ "model.layers.5.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
874
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
875
+ "model.layers.5.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
876
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
877
+ "model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
878
+ "model.layers.5.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
879
+ "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
880
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
881
+ "model.layers.5.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
882
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
883
+ "model.layers.5.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
884
+ "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
885
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
886
+ "model.layers.5.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
887
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
888
+ "model.layers.5.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
889
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
890
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
891
+ "model.layers.6.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
892
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
893
+ "model.layers.6.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
894
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
895
+ "model.layers.6.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
896
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
897
+ "model.layers.6.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
898
+ "model.layers.6.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
899
+ "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
900
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
901
+ "model.layers.6.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
902
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
903
+ "model.layers.6.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
904
+ "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
905
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
906
+ "model.layers.6.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
907
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
908
+ "model.layers.6.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
909
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
910
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
911
+ "model.layers.7.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
912
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
913
+ "model.layers.7.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
914
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
915
+ "model.layers.7.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
916
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
917
+ "model.layers.7.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
918
+ "model.layers.7.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
919
+ "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
920
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
921
+ "model.layers.7.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
922
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
923
+ "model.layers.7.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
924
+ "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
925
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
926
+ "model.layers.7.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
927
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
928
+ "model.layers.7.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
929
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
930
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
931
+ "model.layers.8.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
932
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
933
+ "model.layers.8.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
934
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
935
+ "model.layers.8.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
936
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
937
+ "model.layers.8.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
938
+ "model.layers.8.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
939
+ "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
940
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
941
+ "model.layers.8.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
942
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
943
+ "model.layers.8.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
944
+ "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
945
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
946
+ "model.layers.8.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
947
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
948
+ "model.layers.8.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
949
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
950
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
951
+ "model.layers.9.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
952
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
953
+ "model.layers.9.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
954
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
955
+ "model.layers.9.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
956
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
957
+ "model.layers.9.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
958
+ "model.layers.9.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
959
+ "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
960
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
961
+ "model.layers.9.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
962
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
963
+ "model.layers.9.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
964
+ "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
965
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
966
+ "model.layers.9.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
967
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
968
+ "model.layers.9.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
969
+ "model.norm.weight": "model-00003-of-00003.safetensors"
970
+ }
971
+ }
recipe.yaml ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ default_stage:
2
+ default_modifiers:
3
+ QuantizationModifier:
4
+ targets: [Linear]
5
+ ignore: [lm_head]
6
+ scheme: FP8_DYNAMIC
special_tokens_map.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "boi_token": "<start_of_image>",
3
+ "bos_token": {
4
+ "content": "<bos>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "eoi_token": "<end_of_image>",
11
+ "eos_token": {
12
+ "content": "<end_of_turn>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false
17
+ },
18
+ "image_token": "<image_soft_token>",
19
+ "pad_token": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "unk_token": {
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a872e3bb510a751b26bd65f61aad05f948c9cf78fe4f787aebd197b393cc4081
3
+ size 33384667
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
3
+ size 4689074
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff