Hugging Face's logo

ig1
/
NuExtract-2.0-8B-FP8-Dynamic

Image-Text-to-Text
Transformers
Safetensors
qwen2_5_vl
conversational
text-generation-inference
compressed-tensors
Model card Files
xet
 Community
ig1sa commited on
Commit
249614f
·
verified ·
1 Parent(s): db84fea

Add files using upload-large-folder tool

Browse files
Files changed (17) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +24 -0
  3. chat_template.jinja +138 -0
  4. config.json +344 -0
  5. generation_config.json +13 -0
  6. merges.txt +0 -0
  7. model-00001-of-00003.safetensors +3 -0
  8. model-00002-of-00003.safetensors +3 -0
  9. model-00003-of-00003.safetensors +3 -0
  10. model.safetensors.index.json +933 -0
  11. preprocessor_config.json +39 -0
  12. recipe.yaml +6 -0
  13. special_tokens_map.json +31 -0
  14. tokenizer.json +3 -0
  15. tokenizer_config.json +215 -0
  16. video_preprocessor_config.json +43 -0
  17. vocab.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 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|box_end|>": 151649,
5
+ "<|box_start|>": 151648,
6
+ "<|endoftext|>": 151643,
7
+ "<|file_sep|>": 151664,
8
+ "<|fim_middle|>": 151660,
9
+ "<|fim_pad|>": 151662,
10
+ "<|fim_prefix|>": 151659,
11
+ "<|fim_suffix|>": 151661,
12
+ "<|im_end|>": 151645,
13
+ "<|im_start|>": 151644,
14
+ "<|image_pad|>": 151655,
15
+ "<|object_ref_end|>": 151647,
16
+ "<|object_ref_start|>": 151646,
17
+ "<|quad_end|>": 151651,
18
+ "<|quad_start|>": 151650,
19
+ "<|repo_name|>": 151663,
20
+ "<|video_pad|>": 151656,
21
+ "<|vision_end|>": 151653,
22
+ "<|vision_pad|>": 151654,
23
+ "<|vision_start|>": 151652
24
+ }
chat_template.jinja ADDED
@@ -0,0 +1,138 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- set image_placeholder = '<|vision_start|><|image_pad|><|vision_end|>' -%}
2
+ {%- for message in messages -%}
3
+ {%- if message['role'] == 'system' -%}
4
+ {{- '<|im_start|>system
5
+ ' -}}
6
+ {%- if message['content'] is string -%}
7
+ {{- message['content'] | trim -}}
8
+ {%- endif -%}
9
+ {{- '<|im_end|>
10
+ ' -}}
11
+ {%- elif message['role'] == 'user' -%}
12
+ {%- if loop.first -%}
13
+ {{- '<|im_start|>system
14
+ ' -}}
15
+ {%- if template -%}
16
+ {#--- If template, extraction task ---#}
17
+ {{- 'You are NuExtract, an information extraction tool created by NuMind.' -}}
18
+ {%- else -%}
19
+ {#--- Else, template generation task ---#}
20
+ {{- 'You are a helpful assistant.' -}}
21
+ {%- endif -%}
22
+ {{ '<|im_end|>
23
+ ' }}
24
+ {%- endif -%}
25
+ {{- '<|im_start|>' + message['role'] + '
26
+ ' -}}
27
+ {%- if template -%}
28
+ {#--- Template Section ---#}
29
+ {{- '# Template:
30
+ ' -}}
31
+ {{- template -}}
32
+ {{- '
33
+ ' -}}
34
+
35
+ {%- if examples -%}
36
+ {#--- Examples can only exist in the extraction task ---#}
37
+ {{- '# Examples:
38
+ ' -}}
39
+ {%- for example in examples -%}
40
+ {{- '## Input:
41
+ ' -}}
42
+ {%- if example['input'] is mapping and (example['input']['type'] == 'image' or example['input']['type'] == 'image_url') -%}
43
+ {{- image_placeholder | trim -}}
44
+ {%- elif example['input'] == '<image>' -%}
45
+ {#--- Keep compatibility with <image> for now ---#}
46
+ {{- image_placeholder | trim -}}
47
+ {%- else -%}
48
+ {#--- Text input example ---#}
49
+ {{- example['input'] -}}
50
+ {%- endif -%}
51
+ {{- '
52
+ ' -}}
53
+ {{- '## Output:
54
+ ' -}}
55
+ {{- example['output'] -}}
56
+ {{- '
57
+ ' -}}
58
+ {%- endfor -%}
59
+ {%- endif -%}
60
+ {{- '# Context:
61
+ ' -}}
62
+ {%- endif -%}
63
+
64
+ {%- if message['content'] is string -%}
65
+ {#--- Simple string content ---#}
66
+ {{- message['content'] | trim -}}
67
+ {%- elif message['content'] is mapping and (message['content']['type'] == 'image' or message['content']['type'] == 'image_url') -%}
68
+ {{- image_placeholder | trim -}}
69
+ {%- else -%}
70
+ {#--- List of content items (mixed text/images) ---#}
71
+ {#--- First, determine what the actual input content is (not ICL images) ---#}
72
+ {%- set ns = namespace(has_text_input=false, text_content='') -%}
73
+
74
+ {#--- Count content types and identify actual input document ---#}
75
+ {%- for content in message['content'] -%}
76
+ {%- if content is mapping and content.get('type') == 'text' -%}
77
+ {%- if content.get('text') != '<image>' -%}
78
+ {#--- Keep compatibility with <image> for now ---#}
79
+ {%- set ns.has_text_input = true -%}
80
+ {%- set ns.text_content = content['text'] -%}
81
+ {%- endif -%}
82
+ {%- elif content is string -%}
83
+ {%- if content != '<image>' -%}
84
+ {#--- Keep compatibility with <image> for now ---#}
85
+ {%- set ns.has_text_input = true -%}
86
+ {%- set ns.text_content = content -%}
87
+ {%- endif -%}
88
+ {%- endif -%}
89
+ {%- endfor -%}
90
+
91
+ {#--- Determine what to output based on actual input type ---#}
92
+ {%- if ns.has_text_input -%}
93
+ {#--- Main input is text, so output the text content ---#}
94
+ {{- ns.text_content | trim -}}
95
+ {%- else -%}
96
+ {#--- Main input is image or <image> placeholder ---#}
97
+ {%- set ns2 = namespace(found_image=false) -%}
98
+ {%- for content in message['content'] -%}
99
+ {%- if content is mapping and (content.get('type') == 'image' or content.get('type') == 'image_url') and not ns2.found_image -%}
100
+ {{- image_placeholder | trim -}}
101
+ {%- set ns2.found_image = true -%}
102
+ {%- elif content is mapping and content.get('type') == 'text' and content.get('text') == '<image>' and not ns2.found_image -%}
103
+ {#--- Keep compatibility with <image> for now ---#}
104
+ {{- image_placeholder | trim -}}
105
+ {%- set ns2.found_image = true -%}
106
+ {%- elif content is string and content == '<image>' and not ns2.found_image -%}
107
+ {#--- Keep compatibility with <image> for now ---#}
108
+ {{- image_placeholder | trim -}}
109
+ {%- set ns2.found_image = true -%}
110
+ {%- endif -%}
111
+ {%- endfor -%}
112
+ {%- endif -%}
113
+ {%- endif -%}
114
+ {{- '<|im_end|>
115
+ '}}
116
+
117
+ {%- elif message['role'] == 'assistant' -%}
118
+ {{- '<|im_start|>assistant
119
+ ' -}}
120
+ {%- if message['content'] is string -%}
121
+ {{- message['content'] | trim -}}
122
+ {%- elif message['content'] is iterable and message['content'] is not string -%}
123
+ {%- for content in message['content'] -%}
124
+ {%- if content is mapping and content.get('type') == 'text' -%}
125
+ {{- content['text'] | trim -}}
126
+ {%- elif content is string -%}
127
+ {{- content | trim -}}
128
+ {%- endif -%}
129
+ {%- endfor -%}
130
+ {%- endif -%}
131
+ {{- '<|im_end|>
132
+ ' -}}
133
+ {%- endif -%}
134
+ {%- endfor -%}
135
+ {%- if add_generation_prompt -%}
136
+ {{- '<|im_start|>assistant
137
+ ' -}}
138
+ {%- endif -%}
config.json ADDED
@@ -0,0 +1,344 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2_5_VLForConditionalGeneration"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "dtype": "bfloat16",
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
+ "image_token_id": 151655,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 18944,
14
+ "max_position_embeddings": 128000,
15
+ "max_window_layers": 28,
16
+ "model_type": "qwen2_5_vl",
17
+ "num_attention_heads": 28,
18
+ "num_hidden_layers": 28,
19
+ "num_key_value_heads": 4,
20
+ "quantization_config": {
21
+ "config_groups": {
22
+ "group_0": {
23
+ "format": "float-quantized",
24
+ "input_activations": {
25
+ "actorder": null,
26
+ "block_structure": null,
27
+ "dynamic": true,
28
+ "group_size": null,
29
+ "num_bits": 8,
30
+ "observer": null,
31
+ "observer_kwargs": {},
32
+ "scale_dtype": null,
33
+ "strategy": "token",
34
+ "symmetric": true,
35
+ "type": "float",
36
+ "zp_dtype": null
37
+ },
38
+ "output_activations": null,
39
+ "targets": [
40
+ "Linear"
41
+ ],
42
+ "weights": {
43
+ "actorder": null,
44
+ "block_structure": null,
45
+ "dynamic": false,
46
+ "group_size": null,
47
+ "num_bits": 8,
48
+ "observer": "minmax",
49
+ "observer_kwargs": {},
50
+ "scale_dtype": null,
51
+ "strategy": "channel",
52
+ "symmetric": true,
53
+ "type": "float",
54
+ "zp_dtype": null
55
+ }
56
+ }
57
+ },
58
+ "format": "float-quantized",
59
+ "global_compression_ratio": null,
60
+ "ignore": [
61
+ "model.visual.blocks.0.attn.qkv",
62
+ "model.visual.blocks.0.attn.proj",
63
+ "model.visual.blocks.0.mlp.gate_proj",
64
+ "model.visual.blocks.0.mlp.up_proj",
65
+ "model.visual.blocks.0.mlp.down_proj",
66
+ "model.visual.blocks.1.attn.qkv",
67
+ "model.visual.blocks.1.attn.proj",
68
+ "model.visual.blocks.1.mlp.gate_proj",
69
+ "model.visual.blocks.1.mlp.up_proj",
70
+ "model.visual.blocks.1.mlp.down_proj",
71
+ "model.visual.blocks.2.attn.qkv",
72
+ "model.visual.blocks.2.attn.proj",
73
+ "model.visual.blocks.2.mlp.gate_proj",
74
+ "model.visual.blocks.2.mlp.up_proj",
75
+ "model.visual.blocks.2.mlp.down_proj",
76
+ "model.visual.blocks.3.attn.qkv",
77
+ "model.visual.blocks.3.attn.proj",
78
+ "model.visual.blocks.3.mlp.gate_proj",
79
+ "model.visual.blocks.3.mlp.up_proj",
80
+ "model.visual.blocks.3.mlp.down_proj",
81
+ "model.visual.blocks.4.attn.qkv",
82
+ "model.visual.blocks.4.attn.proj",
83
+ "model.visual.blocks.4.mlp.gate_proj",
84
+ "model.visual.blocks.4.mlp.up_proj",
85
+ "model.visual.blocks.4.mlp.down_proj",
86
+ "model.visual.blocks.5.attn.qkv",
87
+ "model.visual.blocks.5.attn.proj",
88
+ "model.visual.blocks.5.mlp.gate_proj",
89
+ "model.visual.blocks.5.mlp.up_proj",
90
+ "model.visual.blocks.5.mlp.down_proj",
91
+ "model.visual.blocks.6.attn.qkv",
92
+ "model.visual.blocks.6.attn.proj",
93
+ "model.visual.blocks.6.mlp.gate_proj",
94
+ "model.visual.blocks.6.mlp.up_proj",
95
+ "model.visual.blocks.6.mlp.down_proj",
96
+ "model.visual.blocks.7.attn.qkv",
97
+ "model.visual.blocks.7.attn.proj",
98
+ "model.visual.blocks.7.mlp.gate_proj",
99
+ "model.visual.blocks.7.mlp.up_proj",
100
+ "model.visual.blocks.7.mlp.down_proj",
101
+ "model.visual.blocks.8.attn.qkv",
102
+ "model.visual.blocks.8.attn.proj",
103
+ "model.visual.blocks.8.mlp.gate_proj",
104
+ "model.visual.blocks.8.mlp.up_proj",
105
+ "model.visual.blocks.8.mlp.down_proj",
106
+ "model.visual.blocks.9.attn.qkv",
107
+ "model.visual.blocks.9.attn.proj",
108
+ "model.visual.blocks.9.mlp.gate_proj",
109
+ "model.visual.blocks.9.mlp.up_proj",
110
+ "model.visual.blocks.9.mlp.down_proj",
111
+ "model.visual.blocks.10.attn.qkv",
112
+ "model.visual.blocks.10.attn.proj",
113
+ "model.visual.blocks.10.mlp.gate_proj",
114
+ "model.visual.blocks.10.mlp.up_proj",
115
+ "model.visual.blocks.10.mlp.down_proj",
116
+ "model.visual.blocks.11.attn.qkv",
117
+ "model.visual.blocks.11.attn.proj",
118
+ "model.visual.blocks.11.mlp.gate_proj",
119
+ "model.visual.blocks.11.mlp.up_proj",
120
+ "model.visual.blocks.11.mlp.down_proj",
121
+ "model.visual.blocks.12.attn.qkv",
122
+ "model.visual.blocks.12.attn.proj",
123
+ "model.visual.blocks.12.mlp.gate_proj",
124
+ "model.visual.blocks.12.mlp.up_proj",
125
+ "model.visual.blocks.12.mlp.down_proj",
126
+ "model.visual.blocks.13.attn.qkv",
127
+ "model.visual.blocks.13.attn.proj",
128
+ "model.visual.blocks.13.mlp.gate_proj",
129
+ "model.visual.blocks.13.mlp.up_proj",
130
+ "model.visual.blocks.13.mlp.down_proj",
131
+ "model.visual.blocks.14.attn.qkv",
132
+ "model.visual.blocks.14.attn.proj",
133
+ "model.visual.blocks.14.mlp.gate_proj",
134
+ "model.visual.blocks.14.mlp.up_proj",
135
+ "model.visual.blocks.14.mlp.down_proj",
136
+ "model.visual.blocks.15.attn.qkv",
137
+ "model.visual.blocks.15.attn.proj",
138
+ "model.visual.blocks.15.mlp.gate_proj",
139
+ "model.visual.blocks.15.mlp.up_proj",
140
+ "model.visual.blocks.15.mlp.down_proj",
141
+ "model.visual.blocks.16.attn.qkv",
142
+ "model.visual.blocks.16.attn.proj",
143
+ "model.visual.blocks.16.mlp.gate_proj",
144
+ "model.visual.blocks.16.mlp.up_proj",
145
+ "model.visual.blocks.16.mlp.down_proj",
146
+ "model.visual.blocks.17.attn.qkv",
147
+ "model.visual.blocks.17.attn.proj",
148
+ "model.visual.blocks.17.mlp.gate_proj",
149
+ "model.visual.blocks.17.mlp.up_proj",
150
+ "model.visual.blocks.17.mlp.down_proj",
151
+ "model.visual.blocks.18.attn.qkv",
152
+ "model.visual.blocks.18.attn.proj",
153
+ "model.visual.blocks.18.mlp.gate_proj",
154
+ "model.visual.blocks.18.mlp.up_proj",
155
+ "model.visual.blocks.18.mlp.down_proj",
156
+ "model.visual.blocks.19.attn.qkv",
157
+ "model.visual.blocks.19.attn.proj",
158
+ "model.visual.blocks.19.mlp.gate_proj",
159
+ "model.visual.blocks.19.mlp.up_proj",
160
+ "model.visual.blocks.19.mlp.down_proj",
161
+ "model.visual.blocks.20.attn.qkv",
162
+ "model.visual.blocks.20.attn.proj",
163
+ "model.visual.blocks.20.mlp.gate_proj",
164
+ "model.visual.blocks.20.mlp.up_proj",
165
+ "model.visual.blocks.20.mlp.down_proj",
166
+ "model.visual.blocks.21.attn.qkv",
167
+ "model.visual.blocks.21.attn.proj",
168
+ "model.visual.blocks.21.mlp.gate_proj",
169
+ "model.visual.blocks.21.mlp.up_proj",
170
+ "model.visual.blocks.21.mlp.down_proj",
171
+ "model.visual.blocks.22.attn.qkv",
172
+ "model.visual.blocks.22.attn.proj",
173
+ "model.visual.blocks.22.mlp.gate_proj",
174
+ "model.visual.blocks.22.mlp.up_proj",
175
+ "model.visual.blocks.22.mlp.down_proj",
176
+ "model.visual.blocks.23.attn.qkv",
177
+ "model.visual.blocks.23.attn.proj",
178
+ "model.visual.blocks.23.mlp.gate_proj",
179
+ "model.visual.blocks.23.mlp.up_proj",
180
+ "model.visual.blocks.23.mlp.down_proj",
181
+ "model.visual.blocks.24.attn.qkv",
182
+ "model.visual.blocks.24.attn.proj",
183
+ "model.visual.blocks.24.mlp.gate_proj",
184
+ "model.visual.blocks.24.mlp.up_proj",
185
+ "model.visual.blocks.24.mlp.down_proj",
186
+ "model.visual.blocks.25.attn.qkv",
187
+ "model.visual.blocks.25.attn.proj",
188
+ "model.visual.blocks.25.mlp.gate_proj",
189
+ "model.visual.blocks.25.mlp.up_proj",
190
+ "model.visual.blocks.25.mlp.down_proj",
191
+ "model.visual.blocks.26.attn.qkv",
192
+ "model.visual.blocks.26.attn.proj",
193
+ "model.visual.blocks.26.mlp.gate_proj",
194
+ "model.visual.blocks.26.mlp.up_proj",
195
+ "model.visual.blocks.26.mlp.down_proj",
196
+ "model.visual.blocks.27.attn.qkv",
197
+ "model.visual.blocks.27.attn.proj",
198
+ "model.visual.blocks.27.mlp.gate_proj",
199
+ "model.visual.blocks.27.mlp.up_proj",
200
+ "model.visual.blocks.27.mlp.down_proj",
201
+ "model.visual.blocks.28.attn.qkv",
202
+ "model.visual.blocks.28.attn.proj",
203
+ "model.visual.blocks.28.mlp.gate_proj",
204
+ "model.visual.blocks.28.mlp.up_proj",
205
+ "model.visual.blocks.28.mlp.down_proj",
206
+ "model.visual.blocks.29.attn.qkv",
207
+ "model.visual.blocks.29.attn.proj",
208
+ "model.visual.blocks.29.mlp.gate_proj",
209
+ "model.visual.blocks.29.mlp.up_proj",
210
+ "model.visual.blocks.29.mlp.down_proj",
211
+ "model.visual.blocks.30.attn.qkv",
212
+ "model.visual.blocks.30.attn.proj",
213
+ "model.visual.blocks.30.mlp.gate_proj",
214
+ "model.visual.blocks.30.mlp.up_proj",
215
+ "model.visual.blocks.30.mlp.down_proj",
216
+ "model.visual.blocks.31.attn.qkv",
217
+ "model.visual.blocks.31.attn.proj",
218
+ "model.visual.blocks.31.mlp.gate_proj",
219
+ "model.visual.blocks.31.mlp.up_proj",
220
+ "model.visual.blocks.31.mlp.down_proj",
221
+ "model.visual.merger.mlp.0",
222
+ "model.visual.merger.mlp.2",
223
+ "lm_head"
224
+ ],
225
+ "kv_cache_scheme": null,
226
+ "quant_method": "compressed-tensors",
227
+ "quantization_status": "compressed",
228
+ "sparsity_config": {},
229
+ "transform_config": {},
230
+ "version": "0.13.0"
231
+ },
232
+ "rms_norm_eps": 1e-06,
233
+ "rope_scaling": {
234
+ "mrope_section": [
235
+ 16,
236
+ 24,
237
+ 24
238
+ ],
239
+ "rope_type": "default",
240
+ "type": "default"
241
+ },
242
+ "rope_theta": 1000000.0,
243
+ "sliding_window": 32768,
244
+ "text_config": {
245
+ "_name_or_path": "numind/NuExtract-2.0-8B",
246
+ "architectures": [
247
+ "Qwen2_5_VLForConditionalGeneration"
248
+ ],
249
+ "attention_dropout": 0.0,
250
+ "bos_token_id": 151643,
251
+ "dtype": "bfloat16",
252
+ "eos_token_id": 151645,
253
+ "hidden_act": "silu",
254
+ "hidden_size": 3584,
255
+ "initializer_range": 0.02,
256
+ "intermediate_size": 18944,
257
+ "layer_types": [
258
+ "full_attention",
259
+ "full_attention",
260
+ "full_attention",
261
+ "full_attention",
262
+ "full_attention",
263
+ "full_attention",
264
+ "full_attention",
265
+ "full_attention",
266
+ "full_attention",
267
+ "full_attention",
268
+ "full_attention",
269
+ "full_attention",
270
+ "full_attention",
271
+ "full_attention",
272
+ "full_attention",
273
+ "full_attention",
274
+ "full_attention",
275
+ "full_attention",
276
+ "full_attention",
277
+ "full_attention",
278
+ "full_attention",
279
+ "full_attention",
280
+ "full_attention",
281
+ "full_attention",
282
+ "full_attention",
283
+ "full_attention",
284
+ "full_attention",
285
+ "full_attention"
286
+ ],
287
+ "max_position_embeddings": 128000,
288
+ "max_window_layers": 28,
289
+ "model_type": "qwen2_5_vl_text",
290
+ "num_attention_heads": 28,
291
+ "num_hidden_layers": 28,
292
+ "num_key_value_heads": 4,
293
+ "rms_norm_eps": 1e-06,
294
+ "rope_scaling": {
295
+ "mrope_section": [
296
+ 16,
297
+ 24,
298
+ 24
299
+ ],
300
+ "rope_type": "default",
301
+ "type": "default"
302
+ },
303
+ "rope_theta": 1000000.0,
304
+ "sliding_window": null,
305
+ "use_cache": true,
306
+ "use_sliding_window": false,
307
+ "vision_token_id": 151654,
308
+ "vocab_size": 152064
309
+ },
310
+ "tie_word_embeddings": false,
311
+ "transformers_version": "4.57.3",
312
+ "use_cache": true,
313
+ "use_sliding_window": false,
314
+ "video_token_id": 151656,
315
+ "vision_config": {
316
+ "depth": 32,
317
+ "dtype": "bfloat16",
318
+ "fullatt_block_indexes": [
319
+ 7,
320
+ 15,
321
+ 23,
322
+ 31
323
+ ],
324
+ "hidden_act": "silu",
325
+ "hidden_size": 1280,
326
+ "in_channels": 3,
327
+ "in_chans": 3,
328
+ "initializer_range": 0.02,
329
+ "intermediate_size": 3420,
330
+ "model_type": "qwen2_5_vl",
331
+ "num_heads": 16,
332
+ "out_hidden_size": 3584,
333
+ "patch_size": 14,
334
+ "spatial_merge_size": 2,
335
+ "spatial_patch_size": 14,
336
+ "temporal_patch_size": 2,
337
+ "tokens_per_second": 2,
338
+ "window_size": 112
339
+ },
340
+ "vision_end_token_id": 151653,
341
+ "vision_start_token_id": 151652,
342
+ "vision_token_id": 151654,
343
+ "vocab_size": 152064
344
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "attn_implementation": "flash_attention_2",
3
+ "bos_token_id": 151643,
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 151645,
7
+ 151643
8
+ ],
9
+ "pad_token_id": 151643,
10
+ "repetition_penalty": 1.05,
11
+ "temperature": 1e-06,
12
+ "transformers_version": "4.57.3"
13
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f163c866c05b82b8689bcb102662089b96ff8e723275d238e1bc454a1c8247c7
3
+ size 4940102568
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f56653272b3c2737268d1249b78527327a2197051e107e86e4dddc5a4068c856
3
+ size 4031832312
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4e8f474e9dbd80762a31f0b7562dcbd4e8223b143b774c39da0156b9c93ad08
3
+ size 1089994880
model.safetensors.index.json ADDED
@@ -0,0 +1,933 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 8293557248,
4
+ "total_size": 10061826048
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.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
18
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.0.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
20
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.0.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
22
+ "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
23
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.0.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
25
+ "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
26
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
27
+ "model.layers.0.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
28
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
29
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
30
+ "model.layers.1.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
31
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
32
+ "model.layers.1.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
33
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
34
+ "model.layers.1.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
35
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
36
+ "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
37
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
38
+ "model.layers.1.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
39
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
40
+ "model.layers.1.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
41
+ "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
42
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
43
+ "model.layers.1.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
44
+ "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
45
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
46
+ "model.layers.1.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
47
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
48
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
49
+ "model.layers.10.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
50
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
51
+ "model.layers.10.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
52
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
53
+ "model.layers.10.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
54
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
55
+ "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
56
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
57
+ "model.layers.10.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
58
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
59
+ "model.layers.10.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
60
+ "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
61
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
62
+ "model.layers.10.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
63
+ "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
64
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
65
+ "model.layers.10.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
66
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
67
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
68
+ "model.layers.11.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
69
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
70
+ "model.layers.11.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
71
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
72
+ "model.layers.11.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
73
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
75
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.11.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
77
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.11.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
79
+ "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
80
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
81
+ "model.layers.11.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
82
+ "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
83
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
84
+ "model.layers.11.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
85
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
87
+ "model.layers.12.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
88
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
89
+ "model.layers.12.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
90
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
91
+ "model.layers.12.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
92
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
93
+ "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
94
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.12.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
96
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
97
+ "model.layers.12.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
98
+ "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
99
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
100
+ "model.layers.12.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
101
+ "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
102
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
103
+ "model.layers.12.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
104
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
105
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.13.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
107
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.13.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
109
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.13.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
111
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
112
+ "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
113
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
114
+ "model.layers.13.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
115
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
116
+ "model.layers.13.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
117
+ "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
118
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
119
+ "model.layers.13.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
120
+ "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
121
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
122
+ "model.layers.13.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
123
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
124
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
125
+ "model.layers.14.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
126
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
127
+ "model.layers.14.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
128
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
129
+ "model.layers.14.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
130
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
131
+ "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
132
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.14.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
134
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
135
+ "model.layers.14.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
136
+ "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
137
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
138
+ "model.layers.14.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
139
+ "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
140
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
141
+ "model.layers.14.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
142
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
143
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
144
+ "model.layers.15.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
145
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
146
+ "model.layers.15.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
147
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
148
+ "model.layers.15.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
149
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
150
+ "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
151
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
152
+ "model.layers.15.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
153
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
154
+ "model.layers.15.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
155
+ "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
156
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
157
+ "model.layers.15.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
158
+ "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
159
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
160
+ "model.layers.15.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
161
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
162
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
163
+ "model.layers.16.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
164
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
165
+ "model.layers.16.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
166
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
167
+ "model.layers.16.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
168
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
169
+ "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
170
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
171
+ "model.layers.16.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
172
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
173
+ "model.layers.16.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
174
+ "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
175
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
176
+ "model.layers.16.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
177
+ "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
178
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
179
+ "model.layers.16.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
180
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
181
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
182
+ "model.layers.17.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
183
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
184
+ "model.layers.17.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
185
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
186
+ "model.layers.17.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
187
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
188
+ "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
189
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
190
+ "model.layers.17.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
191
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
192
+ "model.layers.17.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
193
+ "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
194
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
195
+ "model.layers.17.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
196
+ "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
197
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
198
+ "model.layers.17.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
199
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
200
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
201
+ "model.layers.18.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
202
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
203
+ "model.layers.18.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
204
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
205
+ "model.layers.18.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
206
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
207
+ "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
208
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
209
+ "model.layers.18.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
210
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
211
+ "model.layers.18.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
212
+ "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
213
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
214
+ "model.layers.18.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
215
+ "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
216
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
217
+ "model.layers.18.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
218
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
219
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
220
+ "model.layers.19.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
221
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
222
+ "model.layers.19.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
223
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
224
+ "model.layers.19.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
225
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
226
+ "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
227
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
228
+ "model.layers.19.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
229
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
230
+ "model.layers.19.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
231
+ "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
232
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
233
+ "model.layers.19.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
234
+ "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
235
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
236
+ "model.layers.19.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
237
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
238
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
239
+ "model.layers.2.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
240
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
241
+ "model.layers.2.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
242
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
243
+ "model.layers.2.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
244
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
245
+ "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
246
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
247
+ "model.layers.2.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
248
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
249
+ "model.layers.2.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
250
+ "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
251
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
252
+ "model.layers.2.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
253
+ "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
254
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
255
+ "model.layers.2.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
256
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
257
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
258
+ "model.layers.20.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
259
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
260
+ "model.layers.20.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
261
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
262
+ "model.layers.20.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
263
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
264
+ "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
265
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
266
+ "model.layers.20.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
267
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
268
+ "model.layers.20.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
269
+ "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
270
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
271
+ "model.layers.20.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
272
+ "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
273
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
274
+ "model.layers.20.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
275
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
276
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
277
+ "model.layers.21.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
278
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
279
+ "model.layers.21.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
280
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
281
+ "model.layers.21.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
282
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
283
+ "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
284
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
285
+ "model.layers.21.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
286
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
287
+ "model.layers.21.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
288
+ "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
289
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
290
+ "model.layers.21.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
291
+ "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
292
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
293
+ "model.layers.21.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
294
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
295
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
296
+ "model.layers.22.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
297
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
298
+ "model.layers.22.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
299
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
300
+ "model.layers.22.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
301
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
302
+ "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
303
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
304
+ "model.layers.22.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
305
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
306
+ "model.layers.22.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
307
+ "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
308
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
309
+ "model.layers.22.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
310
+ "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
311
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
312
+ "model.layers.22.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
313
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
314
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
315
+ "model.layers.23.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
316
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
317
+ "model.layers.23.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
318
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
319
+ "model.layers.23.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
320
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
321
+ "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
322
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
323
+ "model.layers.23.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
324
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
325
+ "model.layers.23.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
326
+ "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
327
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
328
+ "model.layers.23.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
329
+ "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
330
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
331
+ "model.layers.23.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
332
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
333
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
334
+ "model.layers.24.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
335
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
336
+ "model.layers.24.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
337
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
338
+ "model.layers.24.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
339
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
340
+ "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
341
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
342
+ "model.layers.24.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
343
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
344
+ "model.layers.24.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
345
+ "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
346
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
347
+ "model.layers.24.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
348
+ "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
349
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
350
+ "model.layers.24.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
351
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
352
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
353
+ "model.layers.25.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
354
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
355
+ "model.layers.25.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
356
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
357
+ "model.layers.25.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
358
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
359
+ "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
360
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
361
+ "model.layers.25.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
362
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
363
+ "model.layers.25.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
364
+ "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
365
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
366
+ "model.layers.25.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
367
+ "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
368
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
369
+ "model.layers.25.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
370
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
371
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
372
+ "model.layers.26.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
373
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
374
+ "model.layers.26.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
375
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
376
+ "model.layers.26.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
377
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
378
+ "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
379
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
380
+ "model.layers.26.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
381
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
382
+ "model.layers.26.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
383
+ "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
384
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
385
+ "model.layers.26.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
386
+ "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
387
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
388
+ "model.layers.26.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
389
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
390
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
391
+ "model.layers.27.mlp.down_proj.weight_scale": "model-00002-of-00003.safetensors",
392
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
393
+ "model.layers.27.mlp.gate_proj.weight_scale": "model-00002-of-00003.safetensors",
394
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
395
+ "model.layers.27.mlp.up_proj.weight_scale": "model-00002-of-00003.safetensors",
396
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
397
+ "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
398
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
399
+ "model.layers.27.self_attn.k_proj.weight_scale": "model-00002-of-00003.safetensors",
400
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
401
+ "model.layers.27.self_attn.o_proj.weight_scale": "model-00002-of-00003.safetensors",
402
+ "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
403
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
404
+ "model.layers.27.self_attn.q_proj.weight_scale": "model-00002-of-00003.safetensors",
405
+ "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
406
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
407
+ "model.layers.27.self_attn.v_proj.weight_scale": "model-00002-of-00003.safetensors",
408
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
409
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
410
+ "model.layers.3.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
411
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
412
+ "model.layers.3.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
413
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
414
+ "model.layers.3.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
415
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
416
+ "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
417
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
418
+ "model.layers.3.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
419
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
420
+ "model.layers.3.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
421
+ "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
422
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
423
+ "model.layers.3.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
424
+ "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
425
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
426
+ "model.layers.3.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
427
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
428
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
429
+ "model.layers.4.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
430
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
431
+ "model.layers.4.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
432
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
433
+ "model.layers.4.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
434
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
435
+ "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
436
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
437
+ "model.layers.4.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
438
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
439
+ "model.layers.4.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
440
+ "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
441
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
442
+ "model.layers.4.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
443
+ "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
444
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
445
+ "model.layers.4.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
446
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
447
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
448
+ "model.layers.5.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
449
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
450
+ "model.layers.5.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
451
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
452
+ "model.layers.5.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
453
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
454
+ "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
455
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
456
+ "model.layers.5.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
457
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
458
+ "model.layers.5.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
459
+ "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
460
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
461
+ "model.layers.5.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
462
+ "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
463
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
464
+ "model.layers.5.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
465
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
466
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
467
+ "model.layers.6.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
468
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
469
+ "model.layers.6.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
470
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
471
+ "model.layers.6.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
472
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
473
+ "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
474
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
475
+ "model.layers.6.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
476
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
477
+ "model.layers.6.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
478
+ "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
479
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
480
+ "model.layers.6.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
481
+ "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
482
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
483
+ "model.layers.6.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
484
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
485
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
486
+ "model.layers.7.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
487
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
488
+ "model.layers.7.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
489
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
490
+ "model.layers.7.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
491
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
492
+ "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
493
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
494
+ "model.layers.7.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
495
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
496
+ "model.layers.7.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
497
+ "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
498
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
499
+ "model.layers.7.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
500
+ "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
501
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
502
+ "model.layers.7.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
503
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
504
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
505
+ "model.layers.8.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
506
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
507
+ "model.layers.8.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
508
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
509
+ "model.layers.8.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
510
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
511
+ "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
512
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
513
+ "model.layers.8.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
514
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
515
+ "model.layers.8.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
516
+ "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
517
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
518
+ "model.layers.8.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
519
+ "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
520
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
521
+ "model.layers.8.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
522
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
523
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
524
+ "model.layers.9.mlp.down_proj.weight_scale": "model-00001-of-00003.safetensors",
525
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
526
+ "model.layers.9.mlp.gate_proj.weight_scale": "model-00001-of-00003.safetensors",
527
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
528
+ "model.layers.9.mlp.up_proj.weight_scale": "model-00001-of-00003.safetensors",
529
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
530
+ "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
531
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
532
+ "model.layers.9.self_attn.k_proj.weight_scale": "model-00001-of-00003.safetensors",
533
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
534
+ "model.layers.9.self_attn.o_proj.weight_scale": "model-00001-of-00003.safetensors",
535
+ "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
536
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
537
+ "model.layers.9.self_attn.q_proj.weight_scale": "model-00001-of-00003.safetensors",
538
+ "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
539
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
540
+ "model.layers.9.self_attn.v_proj.weight_scale": "model-00001-of-00003.safetensors",
541
+ "model.norm.weight": "model-00002-of-00003.safetensors",
542
+ "visual.blocks.0.attn.proj.bias": "model-00001-of-00003.safetensors",
543
+ "visual.blocks.0.attn.proj.weight": "model-00001-of-00003.safetensors",
544
+ "visual.blocks.0.attn.qkv.bias": "model-00001-of-00003.safetensors",
545
+ "visual.blocks.0.attn.qkv.weight": "model-00001-of-00003.safetensors",
546
+ "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
547
+ "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
548
+ "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
549
+ "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
550
+ "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
551
+ "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
552
+ "visual.blocks.0.norm1.weight": "model-00001-of-00003.safetensors",
553
+ "visual.blocks.0.norm2.weight": "model-00001-of-00003.safetensors",
554
+ "visual.blocks.1.attn.proj.bias": "model-00001-of-00003.safetensors",
555
+ "visual.blocks.1.attn.proj.weight": "model-00001-of-00003.safetensors",
556
+ "visual.blocks.1.attn.qkv.bias": "model-00001-of-00003.safetensors",
557
+ "visual.blocks.1.attn.qkv.weight": "model-00001-of-00003.safetensors",
558
+ "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
559
+ "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
560
+ "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
561
+ "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
562
+ "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
563
+ "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
564
+ "visual.blocks.1.norm1.weight": "model-00001-of-00003.safetensors",
565
+ "visual.blocks.1.norm2.weight": "model-00001-of-00003.safetensors",
566
+ "visual.blocks.10.attn.proj.bias": "model-00001-of-00003.safetensors",
567
+ "visual.blocks.10.attn.proj.weight": "model-00001-of-00003.safetensors",
568
+ "visual.blocks.10.attn.qkv.bias": "model-00001-of-00003.safetensors",
569
+ "visual.blocks.10.attn.qkv.weight": "model-00001-of-00003.safetensors",
570
+ "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
571
+ "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
572
+ "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
573
+ "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
574
+ "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
575
+ "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
576
+ "visual.blocks.10.norm1.weight": "model-00001-of-00003.safetensors",
577
+ "visual.blocks.10.norm2.weight": "model-00001-of-00003.safetensors",
578
+ "visual.blocks.11.attn.proj.bias": "model-00001-of-00003.safetensors",
579
+ "visual.blocks.11.attn.proj.weight": "model-00001-of-00003.safetensors",
580
+ "visual.blocks.11.attn.qkv.bias": "model-00001-of-00003.safetensors",
581
+ "visual.blocks.11.attn.qkv.weight": "model-00001-of-00003.safetensors",
582
+ "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
583
+ "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
584
+ "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
585
+ "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
586
+ "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
587
+ "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
588
+ "visual.blocks.11.norm1.weight": "model-00001-of-00003.safetensors",
589
+ "visual.blocks.11.norm2.weight": "model-00001-of-00003.safetensors",
590
+ "visual.blocks.12.attn.proj.bias": "model-00001-of-00003.safetensors",
591
+ "visual.blocks.12.attn.proj.weight": "model-00001-of-00003.safetensors",
592
+ "visual.blocks.12.attn.qkv.bias": "model-00001-of-00003.safetensors",
593
+ "visual.blocks.12.attn.qkv.weight": "model-00001-of-00003.safetensors",
594
+ "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
595
+ "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
596
+ "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
597
+ "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
598
+ "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
599
+ "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
600
+ "visual.blocks.12.norm1.weight": "model-00001-of-00003.safetensors",
601
+ "visual.blocks.12.norm2.weight": "model-00001-of-00003.safetensors",
602
+ "visual.blocks.13.attn.proj.bias": "model-00001-of-00003.safetensors",
603
+ "visual.blocks.13.attn.proj.weight": "model-00001-of-00003.safetensors",
604
+ "visual.blocks.13.attn.qkv.bias": "model-00001-of-00003.safetensors",
605
+ "visual.blocks.13.attn.qkv.weight": "model-00001-of-00003.safetensors",
606
+ "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
607
+ "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
608
+ "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
609
+ "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
610
+ "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
611
+ "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
612
+ "visual.blocks.13.norm1.weight": "model-00001-of-00003.safetensors",
613
+ "visual.blocks.13.norm2.weight": "model-00001-of-00003.safetensors",
614
+ "visual.blocks.14.attn.proj.bias": "model-00001-of-00003.safetensors",
615
+ "visual.blocks.14.attn.proj.weight": "model-00001-of-00003.safetensors",
616
+ "visual.blocks.14.attn.qkv.bias": "model-00001-of-00003.safetensors",
617
+ "visual.blocks.14.attn.qkv.weight": "model-00001-of-00003.safetensors",
618
+ "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
619
+ "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
620
+ "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
621
+ "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
622
+ "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
623
+ "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
624
+ "visual.blocks.14.norm1.weight": "model-00001-of-00003.safetensors",
625
+ "visual.blocks.14.norm2.weight": "model-00001-of-00003.safetensors",
626
+ "visual.blocks.15.attn.proj.bias": "model-00001-of-00003.safetensors",
627
+ "visual.blocks.15.attn.proj.weight": "model-00001-of-00003.safetensors",
628
+ "visual.blocks.15.attn.qkv.bias": "model-00001-of-00003.safetensors",
629
+ "visual.blocks.15.attn.qkv.weight": "model-00001-of-00003.safetensors",
630
+ "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
631
+ "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
632
+ "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
633
+ "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
634
+ "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
635
+ "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
636
+ "visual.blocks.15.norm1.weight": "model-00001-of-00003.safetensors",
637
+ "visual.blocks.15.norm2.weight": "model-00001-of-00003.safetensors",
638
+ "visual.blocks.16.attn.proj.bias": "model-00001-of-00003.safetensors",
639
+ "visual.blocks.16.attn.proj.weight": "model-00001-of-00003.safetensors",
640
+ "visual.blocks.16.attn.qkv.bias": "model-00001-of-00003.safetensors",
641
+ "visual.blocks.16.attn.qkv.weight": "model-00001-of-00003.safetensors",
642
+ "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
643
+ "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
644
+ "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
645
+ "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
646
+ "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
647
+ "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
648
+ "visual.blocks.16.norm1.weight": "model-00001-of-00003.safetensors",
649
+ "visual.blocks.16.norm2.weight": "model-00001-of-00003.safetensors",
650
+ "visual.blocks.17.attn.proj.bias": "model-00001-of-00003.safetensors",
651
+ "visual.blocks.17.attn.proj.weight": "model-00001-of-00003.safetensors",
652
+ "visual.blocks.17.attn.qkv.bias": "model-00001-of-00003.safetensors",
653
+ "visual.blocks.17.attn.qkv.weight": "model-00001-of-00003.safetensors",
654
+ "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
655
+ "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
656
+ "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
657
+ "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
658
+ "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
659
+ "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
660
+ "visual.blocks.17.norm1.weight": "model-00001-of-00003.safetensors",
661
+ "visual.blocks.17.norm2.weight": "model-00001-of-00003.safetensors",
662
+ "visual.blocks.18.attn.proj.bias": "model-00001-of-00003.safetensors",
663
+ "visual.blocks.18.attn.proj.weight": "model-00001-of-00003.safetensors",
664
+ "visual.blocks.18.attn.qkv.bias": "model-00001-of-00003.safetensors",
665
+ "visual.blocks.18.attn.qkv.weight": "model-00001-of-00003.safetensors",
666
+ "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
667
+ "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
668
+ "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
669
+ "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
670
+ "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
671
+ "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
672
+ "visual.blocks.18.norm1.weight": "model-00001-of-00003.safetensors",
673
+ "visual.blocks.18.norm2.weight": "model-00001-of-00003.safetensors",
674
+ "visual.blocks.19.attn.proj.bias": "model-00001-of-00003.safetensors",
675
+ "visual.blocks.19.attn.proj.weight": "model-00001-of-00003.safetensors",
676
+ "visual.blocks.19.attn.qkv.bias": "model-00001-of-00003.safetensors",
677
+ "visual.blocks.19.attn.qkv.weight": "model-00001-of-00003.safetensors",
678
+ "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
679
+ "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
680
+ "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
681
+ "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
682
+ "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
683
+ "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
684
+ "visual.blocks.19.norm1.weight": "model-00001-of-00003.safetensors",
685
+ "visual.blocks.19.norm2.weight": "model-00001-of-00003.safetensors",
686
+ "visual.blocks.2.attn.proj.bias": "model-00001-of-00003.safetensors",
687
+ "visual.blocks.2.attn.proj.weight": "model-00001-of-00003.safetensors",
688
+ "visual.blocks.2.attn.qkv.bias": "model-00001-of-00003.safetensors",
689
+ "visual.blocks.2.attn.qkv.weight": "model-00001-of-00003.safetensors",
690
+ "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
691
+ "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
692
+ "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
693
+ "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
694
+ "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
695
+ "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
696
+ "visual.blocks.2.norm1.weight": "model-00001-of-00003.safetensors",
697
+ "visual.blocks.2.norm2.weight": "model-00001-of-00003.safetensors",
698
+ "visual.blocks.20.attn.proj.bias": "model-00001-of-00003.safetensors",
699
+ "visual.blocks.20.attn.proj.weight": "model-00001-of-00003.safetensors",
700
+ "visual.blocks.20.attn.qkv.bias": "model-00001-of-00003.safetensors",
701
+ "visual.blocks.20.attn.qkv.weight": "model-00001-of-00003.safetensors",
702
+ "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
703
+ "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
704
+ "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
705
+ "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
706
+ "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
707
+ "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
708
+ "visual.blocks.20.norm1.weight": "model-00001-of-00003.safetensors",
709
+ "visual.blocks.20.norm2.weight": "model-00001-of-00003.safetensors",
710
+ "visual.blocks.21.attn.proj.bias": "model-00001-of-00003.safetensors",
711
+ "visual.blocks.21.attn.proj.weight": "model-00001-of-00003.safetensors",
712
+ "visual.blocks.21.attn.qkv.bias": "model-00001-of-00003.safetensors",
713
+ "visual.blocks.21.attn.qkv.weight": "model-00001-of-00003.safetensors",
714
+ "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
715
+ "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
716
+ "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
717
+ "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
718
+ "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
719
+ "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
720
+ "visual.blocks.21.norm1.weight": "model-00001-of-00003.safetensors",
721
+ "visual.blocks.21.norm2.weight": "model-00001-of-00003.safetensors",
722
+ "visual.blocks.22.attn.proj.bias": "model-00001-of-00003.safetensors",
723
+ "visual.blocks.22.attn.proj.weight": "model-00001-of-00003.safetensors",
724
+ "visual.blocks.22.attn.qkv.bias": "model-00001-of-00003.safetensors",
725
+ "visual.blocks.22.attn.qkv.weight": "model-00001-of-00003.safetensors",
726
+ "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
727
+ "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
728
+ "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
729
+ "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
730
+ "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
731
+ "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
732
+ "visual.blocks.22.norm1.weight": "model-00001-of-00003.safetensors",
733
+ "visual.blocks.22.norm2.weight": "model-00001-of-00003.safetensors",
734
+ "visual.blocks.23.attn.proj.bias": "model-00001-of-00003.safetensors",
735
+ "visual.blocks.23.attn.proj.weight": "model-00001-of-00003.safetensors",
736
+ "visual.blocks.23.attn.qkv.bias": "model-00001-of-00003.safetensors",
737
+ "visual.blocks.23.attn.qkv.weight": "model-00001-of-00003.safetensors",
738
+ "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
739
+ "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
740
+ "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
741
+ "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
742
+ "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
743
+ "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
744
+ "visual.blocks.23.norm1.weight": "model-00001-of-00003.safetensors",
745
+ "visual.blocks.23.norm2.weight": "model-00001-of-00003.safetensors",
746
+ "visual.blocks.24.attn.proj.bias": "model-00001-of-00003.safetensors",
747
+ "visual.blocks.24.attn.proj.weight": "model-00001-of-00003.safetensors",
748
+ "visual.blocks.24.attn.qkv.bias": "model-00001-of-00003.safetensors",
749
+ "visual.blocks.24.attn.qkv.weight": "model-00001-of-00003.safetensors",
750
+ "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
751
+ "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
752
+ "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
753
+ "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
754
+ "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
755
+ "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
756
+ "visual.blocks.24.norm1.weight": "model-00001-of-00003.safetensors",
757
+ "visual.blocks.24.norm2.weight": "model-00001-of-00003.safetensors",
758
+ "visual.blocks.25.attn.proj.bias": "model-00001-of-00003.safetensors",
759
+ "visual.blocks.25.attn.proj.weight": "model-00001-of-00003.safetensors",
760
+ "visual.blocks.25.attn.qkv.bias": "model-00001-of-00003.safetensors",
761
+ "visual.blocks.25.attn.qkv.weight": "model-00001-of-00003.safetensors",
762
+ "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
763
+ "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
764
+ "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
765
+ "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
766
+ "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
767
+ "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
768
+ "visual.blocks.25.norm1.weight": "model-00001-of-00003.safetensors",
769
+ "visual.blocks.25.norm2.weight": "model-00001-of-00003.safetensors",
770
+ "visual.blocks.26.attn.proj.bias": "model-00001-of-00003.safetensors",
771
+ "visual.blocks.26.attn.proj.weight": "model-00001-of-00003.safetensors",
772
+ "visual.blocks.26.attn.qkv.bias": "model-00001-of-00003.safetensors",
773
+ "visual.blocks.26.attn.qkv.weight": "model-00001-of-00003.safetensors",
774
+ "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
775
+ "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
776
+ "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
777
+ "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
778
+ "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
779
+ "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
780
+ "visual.blocks.26.norm1.weight": "model-00001-of-00003.safetensors",
781
+ "visual.blocks.26.norm2.weight": "model-00001-of-00003.safetensors",
782
+ "visual.blocks.27.attn.proj.bias": "model-00001-of-00003.safetensors",
783
+ "visual.blocks.27.attn.proj.weight": "model-00001-of-00003.safetensors",
784
+ "visual.blocks.27.attn.qkv.bias": "model-00001-of-00003.safetensors",
785
+ "visual.blocks.27.attn.qkv.weight": "model-00001-of-00003.safetensors",
786
+ "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
787
+ "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
788
+ "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
789
+ "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
790
+ "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
791
+ "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
792
+ "visual.blocks.27.norm1.weight": "model-00001-of-00003.safetensors",
793
+ "visual.blocks.27.norm2.weight": "model-00001-of-00003.safetensors",
794
+ "visual.blocks.28.attn.proj.bias": "model-00001-of-00003.safetensors",
795
+ "visual.blocks.28.attn.proj.weight": "model-00001-of-00003.safetensors",
796
+ "visual.blocks.28.attn.qkv.bias": "model-00001-of-00003.safetensors",
797
+ "visual.blocks.28.attn.qkv.weight": "model-00001-of-00003.safetensors",
798
+ "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
799
+ "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
800
+ "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
801
+ "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
802
+ "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
803
+ "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
804
+ "visual.blocks.28.norm1.weight": "model-00001-of-00003.safetensors",
805
+ "visual.blocks.28.norm2.weight": "model-00001-of-00003.safetensors",
806
+ "visual.blocks.29.attn.proj.bias": "model-00001-of-00003.safetensors",
807
+ "visual.blocks.29.attn.proj.weight": "model-00001-of-00003.safetensors",
808
+ "visual.blocks.29.attn.qkv.bias": "model-00001-of-00003.safetensors",
809
+ "visual.blocks.29.attn.qkv.weight": "model-00001-of-00003.safetensors",
810
+ "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
811
+ "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
812
+ "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
813
+ "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
814
+ "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
815
+ "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
816
+ "visual.blocks.29.norm1.weight": "model-00001-of-00003.safetensors",
817
+ "visual.blocks.29.norm2.weight": "model-00001-of-00003.safetensors",
818
+ "visual.blocks.3.attn.proj.bias": "model-00001-of-00003.safetensors",
819
+ "visual.blocks.3.attn.proj.weight": "model-00001-of-00003.safetensors",
820
+ "visual.blocks.3.attn.qkv.bias": "model-00001-of-00003.safetensors",
821
+ "visual.blocks.3.attn.qkv.weight": "model-00001-of-00003.safetensors",
822
+ "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
823
+ "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
824
+ "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
825
+ "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
826
+ "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
827
+ "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
828
+ "visual.blocks.3.norm1.weight": "model-00001-of-00003.safetensors",
829
+ "visual.blocks.3.norm2.weight": "model-00001-of-00003.safetensors",
830
+ "visual.blocks.30.attn.proj.bias": "model-00001-of-00003.safetensors",
831
+ "visual.blocks.30.attn.proj.weight": "model-00001-of-00003.safetensors",
832
+ "visual.blocks.30.attn.qkv.bias": "model-00001-of-00003.safetensors",
833
+ "visual.blocks.30.attn.qkv.weight": "model-00001-of-00003.safetensors",
834
+ "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
835
+ "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
836
+ "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
837
+ "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
838
+ "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
839
+ "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
840
+ "visual.blocks.30.norm1.weight": "model-00001-of-00003.safetensors",
841
+ "visual.blocks.30.norm2.weight": "model-00001-of-00003.safetensors",
842
+ "visual.blocks.31.attn.proj.bias": "model-00001-of-00003.safetensors",
843
+ "visual.blocks.31.attn.proj.weight": "model-00001-of-00003.safetensors",
844
+ "visual.blocks.31.attn.qkv.bias": "model-00001-of-00003.safetensors",
845
+ "visual.blocks.31.attn.qkv.weight": "model-00001-of-00003.safetensors",
846
+ "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
847
+ "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
848
+ "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
849
+ "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
850
+ "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
851
+ "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
852
+ "visual.blocks.31.norm1.weight": "model-00001-of-00003.safetensors",
853
+ "visual.blocks.31.norm2.weight": "model-00001-of-00003.safetensors",
854
+ "visual.blocks.4.attn.proj.bias": "model-00001-of-00003.safetensors",
855
+ "visual.blocks.4.attn.proj.weight": "model-00001-of-00003.safetensors",
856
+ "visual.blocks.4.attn.qkv.bias": "model-00001-of-00003.safetensors",
857
+ "visual.blocks.4.attn.qkv.weight": "model-00001-of-00003.safetensors",
858
+ "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
859
+ "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
860
+ "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
861
+ "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
862
+ "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
863
+ "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
864
+ "visual.blocks.4.norm1.weight": "model-00001-of-00003.safetensors",
865
+ "visual.blocks.4.norm2.weight": "model-00001-of-00003.safetensors",
866
+ "visual.blocks.5.attn.proj.bias": "model-00001-of-00003.safetensors",
867
+ "visual.blocks.5.attn.proj.weight": "model-00001-of-00003.safetensors",
868
+ "visual.blocks.5.attn.qkv.bias": "model-00001-of-00003.safetensors",
869
+ "visual.blocks.5.attn.qkv.weight": "model-00001-of-00003.safetensors",
870
+ "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
871
+ "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
872
+ "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
873
+ "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
874
+ "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
875
+ "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
876
+ "visual.blocks.5.norm1.weight": "model-00001-of-00003.safetensors",
877
+ "visual.blocks.5.norm2.weight": "model-00001-of-00003.safetensors",
878
+ "visual.blocks.6.attn.proj.bias": "model-00001-of-00003.safetensors",
879
+ "visual.blocks.6.attn.proj.weight": "model-00001-of-00003.safetensors",
880
+ "visual.blocks.6.attn.qkv.bias": "model-00001-of-00003.safetensors",
881
+ "visual.blocks.6.attn.qkv.weight": "model-00001-of-00003.safetensors",
882
+ "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
883
+ "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
884
+ "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
885
+ "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
886
+ "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
887
+ "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
888
+ "visual.blocks.6.norm1.weight": "model-00001-of-00003.safetensors",
889
+ "visual.blocks.6.norm2.weight": "model-00001-of-00003.safetensors",
890
+ "visual.blocks.7.attn.proj.bias": "model-00001-of-00003.safetensors",
891
+ "visual.blocks.7.attn.proj.weight": "model-00001-of-00003.safetensors",
892
+ "visual.blocks.7.attn.qkv.bias": "model-00001-of-00003.safetensors",
893
+ "visual.blocks.7.attn.qkv.weight": "model-00001-of-00003.safetensors",
894
+ "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
895
+ "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
896
+ "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
897
+ "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
898
+ "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
899
+ "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
900
+ "visual.blocks.7.norm1.weight": "model-00001-of-00003.safetensors",
901
+ "visual.blocks.7.norm2.weight": "model-00001-of-00003.safetensors",
902
+ "visual.blocks.8.attn.proj.bias": "model-00001-of-00003.safetensors",
903
+ "visual.blocks.8.attn.proj.weight": "model-00001-of-00003.safetensors",
904
+ "visual.blocks.8.attn.qkv.bias": "model-00001-of-00003.safetensors",
905
+ "visual.blocks.8.attn.qkv.weight": "model-00001-of-00003.safetensors",
906
+ "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
907
+ "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
908
+ "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
909
+ "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
910
+ "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
911
+ "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
912
+ "visual.blocks.8.norm1.weight": "model-00001-of-00003.safetensors",
913
+ "visual.blocks.8.norm2.weight": "model-00001-of-00003.safetensors",
914
+ "visual.blocks.9.attn.proj.bias": "model-00001-of-00003.safetensors",
915
+ "visual.blocks.9.attn.proj.weight": "model-00001-of-00003.safetensors",
916
+ "visual.blocks.9.attn.qkv.bias": "model-00001-of-00003.safetensors",
917
+ "visual.blocks.9.attn.qkv.weight": "model-00001-of-00003.safetensors",
918
+ "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
919
+ "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
920
+ "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
921
+ "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
922
+ "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
923
+ "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
924
+ "visual.blocks.9.norm1.weight": "model-00001-of-00003.safetensors",
925
+ "visual.blocks.9.norm2.weight": "model-00001-of-00003.safetensors",
926
+ "visual.merger.ln_q.weight": "model-00001-of-00003.safetensors",
927
+ "visual.merger.mlp.0.bias": "model-00001-of-00003.safetensors",
928
+ "visual.merger.mlp.0.weight": "model-00001-of-00003.safetensors",
929
+ "visual.merger.mlp.2.bias": "model-00001-of-00003.safetensors",
930
+ "visual.merger.mlp.2.weight": "model-00001-of-00003.safetensors",
931
+ "visual.patch_embed.proj.weight": "model-00001-of-00003.safetensors"
932
+ }
933
+ }
preprocessor_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "disable_grouping": null,
7
+ "do_center_crop": null,
8
+ "do_convert_rgb": true,
9
+ "do_normalize": true,
10
+ "do_pad": null,
11
+ "do_rescale": true,
12
+ "do_resize": true,
13
+ "image_mean": [
14
+ 0.48145466,
15
+ 0.4578275,
16
+ 0.40821073
17
+ ],
18
+ "image_processor_type": "Qwen2VLImageProcessorFast",
19
+ "image_std": [
20
+ 0.26862954,
21
+ 0.26130258,
22
+ 0.27577711
23
+ ],
24
+ "input_data_format": null,
25
+ "max_pixels": 23000000,
26
+ "merge_size": 2,
27
+ "min_pixels": 200704,
28
+ "pad_size": null,
29
+ "patch_size": 14,
30
+ "processor_class": "Qwen2_5_VLProcessor",
31
+ "resample": 3,
32
+ "rescale_factor": 0.00392156862745098,
33
+ "return_tensors": null,
34
+ "size": {
35
+ "longest_edge": 23000000,
36
+ "shortest_edge": 200704
37
+ },
38
+ "temporal_patch_size": 2
39
+ }
recipe.yaml ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ default_stage:
2
+ default_modifiers:
3
+ QuantizationModifier:
4
+ targets: [Linear]
5
+ ignore: [lm_head, 're:visual.*', 're:model.visual.*']
6
+ scheme: FP8_DYNAMIC
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:913950e4971737031da511cdd1b410daae4566f62eb845b3975bca5a102323d8
3
+ size 11421995
tokenizer_config.json ADDED
@@ -0,0 +1,215 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "add_bos_token": false,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "151643": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "151644": {
15
+ "content": "<|im_start|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "151645": {
23
+ "content": "<|im_end|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "151646": {
31
+ "content": "<|object_ref_start|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "151647": {
39
+ "content": "<|object_ref_end|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "151648": {
47
+ "content": "<|box_start|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "151649": {
55
+ "content": "<|box_end|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "151650": {
63
+ "content": "<|quad_start|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "151651": {
71
+ "content": "<|quad_end|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "151652": {
79
+ "content": "<|vision_start|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "151653": {
87
+ "content": "<|vision_end|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ },
94
+ "151654": {
95
+ "content": "<|vision_pad|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false,
100
+ "special": true
101
+ },
102
+ "151655": {
103
+ "content": "<|image_pad|>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false,
108
+ "special": true
109
+ },
110
+ "151656": {
111
+ "content": "<|video_pad|>",
112
+ "lstrip": false,
113
+ "normalized": false,
114
+ "rstrip": false,
115
+ "single_word": false,
116
+ "special": true
117
+ },
118
+ "151657": {
119
+ "content": "<tool_call>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false,
124
+ "special": false
125
+ },
126
+ "151658": {
127
+ "content": "</tool_call>",
128
+ "lstrip": false,
129
+ "normalized": false,
130
+ "rstrip": false,
131
+ "single_word": false,
132
+ "special": false
133
+ },
134
+ "151659": {
135
+ "content": "<|fim_prefix|>",
136
+ "lstrip": false,
137
+ "normalized": false,
138
+ "rstrip": false,
139
+ "single_word": false,
140
+ "special": false
141
+ },
142
+ "151660": {
143
+ "content": "<|fim_middle|>",
144
+ "lstrip": false,
145
+ "normalized": false,
146
+ "rstrip": false,
147
+ "single_word": false,
148
+ "special": false
149
+ },
150
+ "151661": {
151
+ "content": "<|fim_suffix|>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false,
156
+ "special": false
157
+ },
158
+ "151662": {
159
+ "content": "<|fim_pad|>",
160
+ "lstrip": false,
161
+ "normalized": false,
162
+ "rstrip": false,
163
+ "single_word": false,
164
+ "special": false
165
+ },
166
+ "151663": {
167
+ "content": "<|repo_name|>",
168
+ "lstrip": false,
169
+ "normalized": false,
170
+ "rstrip": false,
171
+ "single_word": false,
172
+ "special": false
173
+ },
174
+ "151664": {
175
+ "content": "<|file_sep|>",
176
+ "lstrip": false,
177
+ "normalized": false,
178
+ "rstrip": false,
179
+ "single_word": false,
180
+ "special": false
181
+ }
182
+ },
183
+ "additional_special_tokens": [
184
+ "<|im_start|>",
185
+ "<|im_end|>",
186
+ "<|object_ref_start|>",
187
+ "<|object_ref_end|>",
188
+ "<|box_start|>",
189
+ "<|box_end|>",
190
+ "<|quad_start|>",
191
+ "<|quad_end|>",
192
+ "<|vision_start|>",
193
+ "<|vision_end|>",
194
+ "<|vision_pad|>",
195
+ "<|image_pad|>",
196
+ "<|video_pad|>"
197
+ ],
198
+ "bos_token": null,
199
+ "clean_up_tokenization_spaces": false,
200
+ "eos_token": "<|im_end|>",
201
+ "errors": "replace",
202
+ "extra_special_tokens": {},
203
+ "max_length": null,
204
+ "max_pixels": 23000000,
205
+ "min_pixels": 200704,
206
+ "model_max_length": 131072,
207
+ "pad_to_multiple_of": null,
208
+ "pad_token": "<|endoftext|>",
209
+ "pad_token_type_id": 0,
210
+ "padding_side": "right",
211
+ "processor_class": "Qwen2_5_VLProcessor",
212
+ "split_special_tokens": false,
213
+ "tokenizer_class": "Qwen2Tokenizer",
214
+ "unk_token": null
215
+ }
video_preprocessor_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "do_center_crop": null,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "do_sample_frames": false,
12
+ "fps": null,
13
+ "image_mean": [
14
+ 0.48145466,
15
+ 0.4578275,
16
+ 0.40821073
17
+ ],
18
+ "image_std": [
19
+ 0.26862954,
20
+ 0.26130258,
21
+ 0.27577711
22
+ ],
23
+ "input_data_format": null,
24
+ "max_frames": 768,
25
+ "max_pixels": 23000000,
26
+ "merge_size": 2,
27
+ "min_frames": 4,
28
+ "min_pixels": 200704,
29
+ "num_frames": null,
30
+ "pad_size": null,
31
+ "patch_size": 14,
32
+ "processor_class": "Qwen2_5_VLProcessor",
33
+ "resample": 3,
34
+ "rescale_factor": 0.00392156862745098,
35
+ "return_metadata": false,
36
+ "size": {
37
+ "longest_edge": 23000000,
38
+ "shortest_edge": 200704
39
+ },
40
+ "temporal_patch_size": 2,
41
+ "video_metadata": null,
42
+ "video_processor_type": "Qwen2VLVideoProcessor"
43
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff