Hugging Face's logo

numind
/
NuExtract3-W4A16

Image-Text-to-Text
Transformers
Safetensors
qwen3_5
vision-language
vlm
document-understanding
structured-extraction
information-extraction
ocr
document-to-markdown
markdown
rag
reasoning
multilingual
conversational
compressed-tensors
Model card Files
xet
 Community
SorenDreano commited on
Commit
d992f4d
·
verified ·
1 Parent(s): 18968f5

Upload folder using huggingface_hub

Browse files
Files changed (11) hide show
  1. .gitattributes +1 -0
  2. chat_template.jinja +120 -0
  3. config.json +372 -0
  4. generation_config.json +6 -0
  5. model-00001-of-00002.safetensors +3 -0
  6. model-00002-of-00002.safetensors +3 -0
  7. model.safetensors.index.json +987 -0
  8. processor_config.json +63 -0
  9. recipe.yaml +11 -0
  10. tokenizer.json +3 -0
  11. tokenizer_config.json +32 -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
chat_template.jinja ADDED
@@ -0,0 +1,120 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if not messages %}
2
+ {{- raise_exception('No messages provided.') }}
3
+ {%- endif %}
4
+ {%- set image_count = namespace(value=0) %}
5
+ {%- set image_placeholder = '<|vision_start|><|image_pad|><|vision_end|>' -%}
6
+ {%- set mode = mode | default('content') -%}
7
+ {%- if template -%}{%- set mode = 'structured' -%}{%- endif -%}
8
+ {%- if not template and mode == 'structured' %}
9
+ {{- raise_exception('`structured` mode specified but no `template` provided.') }}
10
+ {%- endif %}
11
+ {%- if mode not in ['structured', 'content', 'template-generation', 'document-detection', 'markdown'] -%}{%- set mode = 'content' -%}{%- endif -%}
12
+ {%- if mode == 'markdown' %}{%- set mode = 'content' -%}{%- endif %}
13
+ {%- set enable_thinking = enable_thinking | default(False) -%}
14
+ {%- if mode not in ['structured', 'content'] and enable_thinking %}
15
+ {{- raise_exception('`enable_thinking` can only be `True` for `structured` and `content` modes.') }}
16
+ {%- endif %}
17
+ {%- set has_examples = namespace(flag=false) -%}
18
+ {%- if mode != 'structured' -%}{%- set has_examples = false -%}{%- endif -%}
19
+ {# MACRO TO RENDER MESSAGE CONTENT #}
20
+ {%- macro render_content(content, do_vision_count, is_system_content=false) %}
21
+ {%- if content is string %}
22
+ {{- content }}
23
+ {%- elif content is iterable and content is not mapping %}
24
+ {%- for item in content %}
25
+ {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
26
+ {%- if is_system_content %}
27
+ {{- raise_exception('System message cannot contain images.') }}
28
+ {%- endif %}
29
+ {%- if do_vision_count %}
30
+ {%- set image_count.value = image_count.value + 1 %}
31
+ {%- endif %}
32
+ {%- if add_vision_id %}
33
+ {{- 'Picture ' ~ image_count.value ~ ': ' }}
34
+ {%- endif %}
35
+ {{- '<|vision_start|><|image_pad|><|vision_end|>\n' }}
36
+ {%- elif 'text' in item %}
37
+ {{- item.text + '\n' }}
38
+ {%- else %}
39
+ {{- raise_exception('Unexpected item type in content.') }}
40
+ {%- endif %}
41
+ {%- endfor %}
42
+ {%- elif content is none or content is undefined %}
43
+ {{- '' }}
44
+ {%- else %}
45
+ {{- raise_exception('Unexpected content type.') }}
46
+ {%- endif %}
47
+ {%- endmacro %}
48
+ {# SYSTEM MESSAGE #}
49
+ {%- if messages[0].role == 'system' %}
50
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
51
+ {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
52
+ {%- endif %}
53
+ {# USER MESSAGE #}
54
+ {{- '<|im_start|>user\n' -}}
55
+ {{- '【task】' + mode|replace("-", " ") + '\n' -}}
56
+ {# Template Section (for structured task): specifies template, instructions, examples, previous_output #}
57
+ {%- if mode == 'structured' -%}
58
+ {{- '【template_start】' + template + '【template_end】\n' -}}
59
+ {# Instructions Section #}
60
+ {%- if instructions -%}
61
+ {{- '【instructions_start】' + instructions + '【instructions_end】\n'-}}
62
+ {%- endif -%}
63
+ {# Examples Section (only for extraction tasks) #}
64
+ {%- if examples -%}
65
+ {{- '【examples_start】\n' -}}
66
+ {%- for example in examples -%}
67
+ {{- '【example_input_start】' + render_content(example.input, true)|trim + '【example_input_end】\n' -}}
68
+ {{- '【example_output_start】' + example.output|trim + '【example_output_end】\n' -}}
69
+ {%- endfor -%}
70
+ {{- '【examples_end】\n' -}}
71
+ {%- endif -%}
72
+ {# Previous Output Section #}
73
+ {%- if previous_output -%}
74
+ {{- '【previous_output_start】' + previous_output + '【previous_output_end】\n' -}}
75
+ {%- endif -%}
76
+ {%- endif -%}
77
+ {{- '【document_start】\n' -}}
78
+ {# PROCESS PROVIDED USER MESSAGES (RENDERED INTO A SINGLE ONE) #}
79
+ {%- for message in messages -%}
80
+ {%- if message.role == "system" %}
81
+ {%- if not loop.first %}
82
+ {{- raise_exception('System message must be at the beginning.') }}
83
+ {%- endif %}
84
+ {%- elif message.role == 'user' and message.name != "example" -%}
85
+ {%- set content = render_content(message.content, true)|trim %}
86
+ {{- content + '\n' -}}
87
+ {%- elif message.role == 'assistant' and not loop.last %}
88
+ {{- raise_exception('Assistant message must be at the end.') }}
89
+ {%- endif %}
90
+ {%- endfor -%}
91
+ {{- '【document_end】<|im_end|>\n' -}}
92
+ {# ASSISTANT MESSAGE #}
93
+ {%- if messages[-1].role == 'assistant' %}
94
+ {%- if add_generation_prompt -%}
95
+ {{- raise_exception('`add_generation_prompt` can only be `True` when no assistant message is provided.') }}
96
+ {%- endif %}
97
+ {%- set content = render_content(messages[-1].content, true)|trim %}
98
+ {%- set reasoning_content = '' %}
99
+ {%- if messages[-1].reasoning_content is string %}
100
+ {%- set reasoning_content = messages[-1].reasoning_content %}
101
+ {%- else %}
102
+ {%- if '</think>' in content %}
103
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
104
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
105
+ {%- endif %}
106
+ {%- endif %}
107
+ {%- set reasoning_content = reasoning_content|trim %}
108
+ {% generation %}
109
+ {{- '<|im_start|>assistant\n<think>\n' + reasoning_content + '\n</think>\n\n' + content + '<|im_end|>\n' -}}
110
+ {% endgeneration %}
111
+ {%- endif -%}
112
+ {# GENERATION PROMPT #}
113
+ {%- if add_generation_prompt -%}
114
+ {{- '<|im_start|>assistant\n' -}}
115
+ {%- if not enable_thinking -%}
116
+ {{- '<think>\n\n</think>\n\n' -}}
117
+ {%- else %}
118
+ {{- '<think>\n' -}}
119
+ {%- endif %}
120
+ {%- endif -%}
config.json ADDED
@@ -0,0 +1,372 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5ForConditionalGeneration"
4
+ ],
5
+ "bos_token_id": null,
6
+ "dtype": "bfloat16",
7
+ "eos_token_id": 248046,
8
+ "head_dim": 256,
9
+ "hidden_size": 2560,
10
+ "image_token_id": 248056,
11
+ "model_type": "qwen3_5",
12
+ "num_attention_heads": 16,
13
+ "num_hidden_layers": 32,
14
+ "num_key_value_heads": 4,
15
+ "pad_token_id": 248044,
16
+ "quantization_config": {
17
+ "config_groups": {
18
+ "group_0": {
19
+ "format": "pack-quantized",
20
+ "input_activations": null,
21
+ "output_activations": null,
22
+ "targets": [
23
+ "Linear"
24
+ ],
25
+ "weights": {
26
+ "actorder": "static",
27
+ "block_structure": null,
28
+ "dynamic": false,
29
+ "group_size": 128,
30
+ "num_bits": 4,
31
+ "observer": "memoryless_minmax",
32
+ "observer_kwargs": {},
33
+ "scale_dtype": null,
34
+ "strategy": "group",
35
+ "symmetric": true,
36
+ "type": "int",
37
+ "zp_dtype": null
38
+ }
39
+ }
40
+ },
41
+ "format": "pack-quantized",
42
+ "global_compression_ratio": null,
43
+ "ignore": [
44
+ "model.visual.blocks.0.attn.qkv",
45
+ "model.visual.blocks.0.attn.proj",
46
+ "model.visual.blocks.0.mlp.linear_fc1",
47
+ "model.visual.blocks.0.mlp.linear_fc2",
48
+ "model.visual.blocks.1.attn.qkv",
49
+ "model.visual.blocks.1.attn.proj",
50
+ "model.visual.blocks.1.mlp.linear_fc1",
51
+ "model.visual.blocks.1.mlp.linear_fc2",
52
+ "model.visual.blocks.2.attn.qkv",
53
+ "model.visual.blocks.2.attn.proj",
54
+ "model.visual.blocks.2.mlp.linear_fc1",
55
+ "model.visual.blocks.2.mlp.linear_fc2",
56
+ "model.visual.blocks.3.attn.qkv",
57
+ "model.visual.blocks.3.attn.proj",
58
+ "model.visual.blocks.3.mlp.linear_fc1",
59
+ "model.visual.blocks.3.mlp.linear_fc2",
60
+ "model.visual.blocks.4.attn.qkv",
61
+ "model.visual.blocks.4.attn.proj",
62
+ "model.visual.blocks.4.mlp.linear_fc1",
63
+ "model.visual.blocks.4.mlp.linear_fc2",
64
+ "model.visual.blocks.5.attn.qkv",
65
+ "model.visual.blocks.5.attn.proj",
66
+ "model.visual.blocks.5.mlp.linear_fc1",
67
+ "model.visual.blocks.5.mlp.linear_fc2",
68
+ "model.visual.blocks.6.attn.qkv",
69
+ "model.visual.blocks.6.attn.proj",
70
+ "model.visual.blocks.6.mlp.linear_fc1",
71
+ "model.visual.blocks.6.mlp.linear_fc2",
72
+ "model.visual.blocks.7.attn.qkv",
73
+ "model.visual.blocks.7.attn.proj",
74
+ "model.visual.blocks.7.mlp.linear_fc1",
75
+ "model.visual.blocks.7.mlp.linear_fc2",
76
+ "model.visual.blocks.8.attn.qkv",
77
+ "model.visual.blocks.8.attn.proj",
78
+ "model.visual.blocks.8.mlp.linear_fc1",
79
+ "model.visual.blocks.8.mlp.linear_fc2",
80
+ "model.visual.blocks.9.attn.qkv",
81
+ "model.visual.blocks.9.attn.proj",
82
+ "model.visual.blocks.9.mlp.linear_fc1",
83
+ "model.visual.blocks.9.mlp.linear_fc2",
84
+ "model.visual.blocks.10.attn.qkv",
85
+ "model.visual.blocks.10.attn.proj",
86
+ "model.visual.blocks.10.mlp.linear_fc1",
87
+ "model.visual.blocks.10.mlp.linear_fc2",
88
+ "model.visual.blocks.11.attn.qkv",
89
+ "model.visual.blocks.11.attn.proj",
90
+ "model.visual.blocks.11.mlp.linear_fc1",
91
+ "model.visual.blocks.11.mlp.linear_fc2",
92
+ "model.visual.blocks.12.attn.qkv",
93
+ "model.visual.blocks.12.attn.proj",
94
+ "model.visual.blocks.12.mlp.linear_fc1",
95
+ "model.visual.blocks.12.mlp.linear_fc2",
96
+ "model.visual.blocks.13.attn.qkv",
97
+ "model.visual.blocks.13.attn.proj",
98
+ "model.visual.blocks.13.mlp.linear_fc1",
99
+ "model.visual.blocks.13.mlp.linear_fc2",
100
+ "model.visual.blocks.14.attn.qkv",
101
+ "model.visual.blocks.14.attn.proj",
102
+ "model.visual.blocks.14.mlp.linear_fc1",
103
+ "model.visual.blocks.14.mlp.linear_fc2",
104
+ "model.visual.blocks.15.attn.qkv",
105
+ "model.visual.blocks.15.attn.proj",
106
+ "model.visual.blocks.15.mlp.linear_fc1",
107
+ "model.visual.blocks.15.mlp.linear_fc2",
108
+ "model.visual.blocks.16.attn.qkv",
109
+ "model.visual.blocks.16.attn.proj",
110
+ "model.visual.blocks.16.mlp.linear_fc1",
111
+ "model.visual.blocks.16.mlp.linear_fc2",
112
+ "model.visual.blocks.17.attn.qkv",
113
+ "model.visual.blocks.17.attn.proj",
114
+ "model.visual.blocks.17.mlp.linear_fc1",
115
+ "model.visual.blocks.17.mlp.linear_fc2",
116
+ "model.visual.blocks.18.attn.qkv",
117
+ "model.visual.blocks.18.attn.proj",
118
+ "model.visual.blocks.18.mlp.linear_fc1",
119
+ "model.visual.blocks.18.mlp.linear_fc2",
120
+ "model.visual.blocks.19.attn.qkv",
121
+ "model.visual.blocks.19.attn.proj",
122
+ "model.visual.blocks.19.mlp.linear_fc1",
123
+ "model.visual.blocks.19.mlp.linear_fc2",
124
+ "model.visual.blocks.20.attn.qkv",
125
+ "model.visual.blocks.20.attn.proj",
126
+ "model.visual.blocks.20.mlp.linear_fc1",
127
+ "model.visual.blocks.20.mlp.linear_fc2",
128
+ "model.visual.blocks.21.attn.qkv",
129
+ "model.visual.blocks.21.attn.proj",
130
+ "model.visual.blocks.21.mlp.linear_fc1",
131
+ "model.visual.blocks.21.mlp.linear_fc2",
132
+ "model.visual.blocks.22.attn.qkv",
133
+ "model.visual.blocks.22.attn.proj",
134
+ "model.visual.blocks.22.mlp.linear_fc1",
135
+ "model.visual.blocks.22.mlp.linear_fc2",
136
+ "model.visual.blocks.23.attn.qkv",
137
+ "model.visual.blocks.23.attn.proj",
138
+ "model.visual.blocks.23.mlp.linear_fc1",
139
+ "model.visual.blocks.23.mlp.linear_fc2",
140
+ "model.visual.merger.linear_fc1",
141
+ "model.visual.merger.linear_fc2",
142
+ "model.language_model.layers.0.linear_attn.out_proj",
143
+ "model.language_model.layers.0.linear_attn.in_proj_qkv",
144
+ "model.language_model.layers.0.linear_attn.in_proj_z",
145
+ "model.language_model.layers.0.linear_attn.in_proj_b",
146
+ "model.language_model.layers.0.linear_attn.in_proj_a",
147
+ "model.language_model.layers.1.linear_attn.out_proj",
148
+ "model.language_model.layers.1.linear_attn.in_proj_qkv",
149
+ "model.language_model.layers.1.linear_attn.in_proj_z",
150
+ "model.language_model.layers.1.linear_attn.in_proj_b",
151
+ "model.language_model.layers.1.linear_attn.in_proj_a",
152
+ "model.language_model.layers.2.linear_attn.out_proj",
153
+ "model.language_model.layers.2.linear_attn.in_proj_qkv",
154
+ "model.language_model.layers.2.linear_attn.in_proj_z",
155
+ "model.language_model.layers.2.linear_attn.in_proj_b",
156
+ "model.language_model.layers.2.linear_attn.in_proj_a",
157
+ "model.language_model.layers.4.linear_attn.out_proj",
158
+ "model.language_model.layers.4.linear_attn.in_proj_qkv",
159
+ "model.language_model.layers.4.linear_attn.in_proj_z",
160
+ "model.language_model.layers.4.linear_attn.in_proj_b",
161
+ "model.language_model.layers.4.linear_attn.in_proj_a",
162
+ "model.language_model.layers.5.linear_attn.out_proj",
163
+ "model.language_model.layers.5.linear_attn.in_proj_qkv",
164
+ "model.language_model.layers.5.linear_attn.in_proj_z",
165
+ "model.language_model.layers.5.linear_attn.in_proj_b",
166
+ "model.language_model.layers.5.linear_attn.in_proj_a",
167
+ "model.language_model.layers.6.linear_attn.out_proj",
168
+ "model.language_model.layers.6.linear_attn.in_proj_qkv",
169
+ "model.language_model.layers.6.linear_attn.in_proj_z",
170
+ "model.language_model.layers.6.linear_attn.in_proj_b",
171
+ "model.language_model.layers.6.linear_attn.in_proj_a",
172
+ "model.language_model.layers.8.linear_attn.out_proj",
173
+ "model.language_model.layers.8.linear_attn.in_proj_qkv",
174
+ "model.language_model.layers.8.linear_attn.in_proj_z",
175
+ "model.language_model.layers.8.linear_attn.in_proj_b",
176
+ "model.language_model.layers.8.linear_attn.in_proj_a",
177
+ "model.language_model.layers.9.linear_attn.out_proj",
178
+ "model.language_model.layers.9.linear_attn.in_proj_qkv",
179
+ "model.language_model.layers.9.linear_attn.in_proj_z",
180
+ "model.language_model.layers.9.linear_attn.in_proj_b",
181
+ "model.language_model.layers.9.linear_attn.in_proj_a",
182
+ "model.language_model.layers.10.linear_attn.out_proj",
183
+ "model.language_model.layers.10.linear_attn.in_proj_qkv",
184
+ "model.language_model.layers.10.linear_attn.in_proj_z",
185
+ "model.language_model.layers.10.linear_attn.in_proj_b",
186
+ "model.language_model.layers.10.linear_attn.in_proj_a",
187
+ "model.language_model.layers.12.linear_attn.out_proj",
188
+ "model.language_model.layers.12.linear_attn.in_proj_qkv",
189
+ "model.language_model.layers.12.linear_attn.in_proj_z",
190
+ "model.language_model.layers.12.linear_attn.in_proj_b",
191
+ "model.language_model.layers.12.linear_attn.in_proj_a",
192
+ "model.language_model.layers.13.linear_attn.out_proj",
193
+ "model.language_model.layers.13.linear_attn.in_proj_qkv",
194
+ "model.language_model.layers.13.linear_attn.in_proj_z",
195
+ "model.language_model.layers.13.linear_attn.in_proj_b",
196
+ "model.language_model.layers.13.linear_attn.in_proj_a",
197
+ "model.language_model.layers.14.linear_attn.out_proj",
198
+ "model.language_model.layers.14.linear_attn.in_proj_qkv",
199
+ "model.language_model.layers.14.linear_attn.in_proj_z",
200
+ "model.language_model.layers.14.linear_attn.in_proj_b",
201
+ "model.language_model.layers.14.linear_attn.in_proj_a",
202
+ "model.language_model.layers.16.linear_attn.out_proj",
203
+ "model.language_model.layers.16.linear_attn.in_proj_qkv",
204
+ "model.language_model.layers.16.linear_attn.in_proj_z",
205
+ "model.language_model.layers.16.linear_attn.in_proj_b",
206
+ "model.language_model.layers.16.linear_attn.in_proj_a",
207
+ "model.language_model.layers.17.linear_attn.out_proj",
208
+ "model.language_model.layers.17.linear_attn.in_proj_qkv",
209
+ "model.language_model.layers.17.linear_attn.in_proj_z",
210
+ "model.language_model.layers.17.linear_attn.in_proj_b",
211
+ "model.language_model.layers.17.linear_attn.in_proj_a",
212
+ "model.language_model.layers.18.linear_attn.out_proj",
213
+ "model.language_model.layers.18.linear_attn.in_proj_qkv",
214
+ "model.language_model.layers.18.linear_attn.in_proj_z",
215
+ "model.language_model.layers.18.linear_attn.in_proj_b",
216
+ "model.language_model.layers.18.linear_attn.in_proj_a",
217
+ "model.language_model.layers.20.linear_attn.out_proj",
218
+ "model.language_model.layers.20.linear_attn.in_proj_qkv",
219
+ "model.language_model.layers.20.linear_attn.in_proj_z",
220
+ "model.language_model.layers.20.linear_attn.in_proj_b",
221
+ "model.language_model.layers.20.linear_attn.in_proj_a",
222
+ "model.language_model.layers.21.linear_attn.out_proj",
223
+ "model.language_model.layers.21.linear_attn.in_proj_qkv",
224
+ "model.language_model.layers.21.linear_attn.in_proj_z",
225
+ "model.language_model.layers.21.linear_attn.in_proj_b",
226
+ "model.language_model.layers.21.linear_attn.in_proj_a",
227
+ "model.language_model.layers.22.linear_attn.out_proj",
228
+ "model.language_model.layers.22.linear_attn.in_proj_qkv",
229
+ "model.language_model.layers.22.linear_attn.in_proj_z",
230
+ "model.language_model.layers.22.linear_attn.in_proj_b",
231
+ "model.language_model.layers.22.linear_attn.in_proj_a",
232
+ "model.language_model.layers.24.linear_attn.out_proj",
233
+ "model.language_model.layers.24.linear_attn.in_proj_qkv",
234
+ "model.language_model.layers.24.linear_attn.in_proj_z",
235
+ "model.language_model.layers.24.linear_attn.in_proj_b",
236
+ "model.language_model.layers.24.linear_attn.in_proj_a",
237
+ "model.language_model.layers.25.linear_attn.out_proj",
238
+ "model.language_model.layers.25.linear_attn.in_proj_qkv",
239
+ "model.language_model.layers.25.linear_attn.in_proj_z",
240
+ "model.language_model.layers.25.linear_attn.in_proj_b",
241
+ "model.language_model.layers.25.linear_attn.in_proj_a",
242
+ "model.language_model.layers.26.linear_attn.out_proj",
243
+ "model.language_model.layers.26.linear_attn.in_proj_qkv",
244
+ "model.language_model.layers.26.linear_attn.in_proj_z",
245
+ "model.language_model.layers.26.linear_attn.in_proj_b",
246
+ "model.language_model.layers.26.linear_attn.in_proj_a",
247
+ "model.language_model.layers.28.linear_attn.out_proj",
248
+ "model.language_model.layers.28.linear_attn.in_proj_qkv",
249
+ "model.language_model.layers.28.linear_attn.in_proj_z",
250
+ "model.language_model.layers.28.linear_attn.in_proj_b",
251
+ "model.language_model.layers.28.linear_attn.in_proj_a",
252
+ "model.language_model.layers.29.linear_attn.out_proj",
253
+ "model.language_model.layers.29.linear_attn.in_proj_qkv",
254
+ "model.language_model.layers.29.linear_attn.in_proj_z",
255
+ "model.language_model.layers.29.linear_attn.in_proj_b",
256
+ "model.language_model.layers.29.linear_attn.in_proj_a",
257
+ "model.language_model.layers.30.linear_attn.out_proj",
258
+ "model.language_model.layers.30.linear_attn.in_proj_qkv",
259
+ "model.language_model.layers.30.linear_attn.in_proj_z",
260
+ "model.language_model.layers.30.linear_attn.in_proj_b",
261
+ "model.language_model.layers.30.linear_attn.in_proj_a",
262
+ "lm_head"
263
+ ],
264
+ "kv_cache_scheme": null,
265
+ "quant_method": "compressed-tensors",
266
+ "quantization_status": "compressed",
267
+ "sparsity_config": {},
268
+ "transform_config": {},
269
+ "version": "0.15.1.a20260503"
270
+ },
271
+ "text_config": {
272
+ "attention_bias": false,
273
+ "attention_dropout": 0.0,
274
+ "attn_output_gate": true,
275
+ "bos_token_id": null,
276
+ "dtype": "bfloat16",
277
+ "eos_token_id": 248044,
278
+ "full_attention_interval": 4,
279
+ "head_dim": 256,
280
+ "hidden_act": "silu",
281
+ "hidden_size": 2560,
282
+ "initializer_range": 0.02,
283
+ "intermediate_size": 9216,
284
+ "layer_types": [
285
+ "linear_attention",
286
+ "linear_attention",
287
+ "linear_attention",
288
+ "full_attention",
289
+ "linear_attention",
290
+ "linear_attention",
291
+ "linear_attention",
292
+ "full_attention",
293
+ "linear_attention",
294
+ "linear_attention",
295
+ "linear_attention",
296
+ "full_attention",
297
+ "linear_attention",
298
+ "linear_attention",
299
+ "linear_attention",
300
+ "full_attention",
301
+ "linear_attention",
302
+ "linear_attention",
303
+ "linear_attention",
304
+ "full_attention",
305
+ "linear_attention",
306
+ "linear_attention",
307
+ "linear_attention",
308
+ "full_attention",
309
+ "linear_attention",
310
+ "linear_attention",
311
+ "linear_attention",
312
+ "full_attention",
313
+ "linear_attention",
314
+ "linear_attention",
315
+ "linear_attention",
316
+ "full_attention"
317
+ ],
318
+ "linear_conv_kernel_dim": 4,
319
+ "linear_key_head_dim": 128,
320
+ "linear_num_key_heads": 16,
321
+ "linear_num_value_heads": 32,
322
+ "linear_value_head_dim": 128,
323
+ "mamba_ssm_dtype": "float32",
324
+ "max_position_embeddings": 262144,
325
+ "mlp_only_layers": [],
326
+ "model_type": "qwen3_5_text",
327
+ "mtp_num_hidden_layers": 1,
328
+ "mtp_use_dedicated_embeddings": false,
329
+ "num_attention_heads": 16,
330
+ "num_hidden_layers": 32,
331
+ "num_key_value_heads": 4,
332
+ "pad_token_id": null,
333
+ "partial_rotary_factor": 0.25,
334
+ "rms_norm_eps": 1e-06,
335
+ "rope_parameters": {
336
+ "mrope_interleaved": true,
337
+ "mrope_section": [
338
+ 11,
339
+ 11,
340
+ 10
341
+ ],
342
+ "partial_rotary_factor": 0.25,
343
+ "rope_theta": 10000000,
344
+ "rope_type": "default"
345
+ },
346
+ "tie_word_embeddings": true,
347
+ "use_cache": true,
348
+ "vocab_size": 248320
349
+ },
350
+ "tie_word_embeddings": true,
351
+ "transformers_version": "5.3.0",
352
+ "video_token_id": 248057,
353
+ "vision_config": {
354
+ "deepstack_visual_indexes": [],
355
+ "depth": 24,
356
+ "dtype": "bfloat16",
357
+ "hidden_act": "gelu_pytorch_tanh",
358
+ "hidden_size": 1024,
359
+ "in_channels": 3,
360
+ "initializer_range": 0.02,
361
+ "intermediate_size": 4096,
362
+ "model_type": "qwen3_5",
363
+ "num_heads": 16,
364
+ "num_position_embeddings": 2304,
365
+ "out_hidden_size": 2560,
366
+ "patch_size": 16,
367
+ "spatial_merge_size": 2,
368
+ "temporal_patch_size": 2
369
+ },
370
+ "vision_end_token_id": 248054,
371
+ "vision_start_token_id": 248053
372
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": 248044,
4
+ "transformers_version": "5.3.0",
5
+ "use_cache": true
6
+ }
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5deef73494892e4ec02cb513e7cc2a31fc93065ce50baa30cc02c914788edcf
3
+ size 5000094080
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:796472a195deb7a1c3032e6ce4ed0b0d11af94697c6a05bb7fa2e7dc25c8d485
3
+ size 280749200
model.safetensors.index.json ADDED
@@ -0,0 +1,987 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 2320544512,
4
+ "total_size": 5280721920
5
+ },
6
+ "weight_map": {
7
+ "model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
+ "model.language_model.layers.0.linear_attn.A_log": "model-00001-of-00002.safetensors",
10
+ "model.language_model.layers.0.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
11
+ "model.language_model.layers.0.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
12
+ "model.language_model.layers.0.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
13
+ "model.language_model.layers.0.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
14
+ "model.language_model.layers.0.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
15
+ "model.language_model.layers.0.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
16
+ "model.language_model.layers.0.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
17
+ "model.language_model.layers.0.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
18
+ "model.language_model.layers.0.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
19
+ "model.language_model.layers.0.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
20
+ "model.language_model.layers.0.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
21
+ "model.language_model.layers.0.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
22
+ "model.language_model.layers.0.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
23
+ "model.language_model.layers.0.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
24
+ "model.language_model.layers.0.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
25
+ "model.language_model.layers.0.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
26
+ "model.language_model.layers.0.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
27
+ "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
28
+ "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
29
+ "model.language_model.layers.1.linear_attn.A_log": "model-00001-of-00002.safetensors",
30
+ "model.language_model.layers.1.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
31
+ "model.language_model.layers.1.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
32
+ "model.language_model.layers.1.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
33
+ "model.language_model.layers.1.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
34
+ "model.language_model.layers.1.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
35
+ "model.language_model.layers.1.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
36
+ "model.language_model.layers.1.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
37
+ "model.language_model.layers.1.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.language_model.layers.1.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
39
+ "model.language_model.layers.1.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
40
+ "model.language_model.layers.1.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
41
+ "model.language_model.layers.1.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
42
+ "model.language_model.layers.1.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
43
+ "model.language_model.layers.1.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
44
+ "model.language_model.layers.1.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
45
+ "model.language_model.layers.1.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
46
+ "model.language_model.layers.1.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
47
+ "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
48
+ "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
49
+ "model.language_model.layers.10.linear_attn.A_log": "model-00001-of-00002.safetensors",
50
+ "model.language_model.layers.10.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
51
+ "model.language_model.layers.10.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
52
+ "model.language_model.layers.10.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
53
+ "model.language_model.layers.10.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
54
+ "model.language_model.layers.10.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
55
+ "model.language_model.layers.10.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
56
+ "model.language_model.layers.10.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
57
+ "model.language_model.layers.10.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
58
+ "model.language_model.layers.10.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
59
+ "model.language_model.layers.10.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
60
+ "model.language_model.layers.10.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
61
+ "model.language_model.layers.10.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
62
+ "model.language_model.layers.10.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
63
+ "model.language_model.layers.10.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
64
+ "model.language_model.layers.10.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
65
+ "model.language_model.layers.10.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
66
+ "model.language_model.layers.10.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
67
+ "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
68
+ "model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
69
+ "model.language_model.layers.11.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
70
+ "model.language_model.layers.11.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
71
+ "model.language_model.layers.11.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
72
+ "model.language_model.layers.11.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
73
+ "model.language_model.layers.11.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
74
+ "model.language_model.layers.11.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
75
+ "model.language_model.layers.11.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
76
+ "model.language_model.layers.11.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
77
+ "model.language_model.layers.11.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
78
+ "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
79
+ "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
80
+ "model.language_model.layers.11.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
81
+ "model.language_model.layers.11.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
82
+ "model.language_model.layers.11.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
83
+ "model.language_model.layers.11.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
84
+ "model.language_model.layers.11.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
85
+ "model.language_model.layers.11.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
86
+ "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
87
+ "model.language_model.layers.11.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
88
+ "model.language_model.layers.11.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
89
+ "model.language_model.layers.11.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
90
+ "model.language_model.layers.11.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
91
+ "model.language_model.layers.11.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
92
+ "model.language_model.layers.11.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
93
+ "model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
94
+ "model.language_model.layers.12.linear_attn.A_log": "model-00001-of-00002.safetensors",
95
+ "model.language_model.layers.12.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
96
+ "model.language_model.layers.12.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
97
+ "model.language_model.layers.12.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
98
+ "model.language_model.layers.12.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
99
+ "model.language_model.layers.12.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
100
+ "model.language_model.layers.12.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
101
+ "model.language_model.layers.12.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
102
+ "model.language_model.layers.12.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
103
+ "model.language_model.layers.12.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
104
+ "model.language_model.layers.12.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
105
+ "model.language_model.layers.12.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
106
+ "model.language_model.layers.12.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
107
+ "model.language_model.layers.12.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
108
+ "model.language_model.layers.12.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
109
+ "model.language_model.layers.12.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
110
+ "model.language_model.layers.12.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
111
+ "model.language_model.layers.12.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
112
+ "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
113
+ "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
114
+ "model.language_model.layers.13.linear_attn.A_log": "model-00001-of-00002.safetensors",
115
+ "model.language_model.layers.13.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
116
+ "model.language_model.layers.13.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
117
+ "model.language_model.layers.13.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
118
+ "model.language_model.layers.13.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
119
+ "model.language_model.layers.13.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
120
+ "model.language_model.layers.13.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
121
+ "model.language_model.layers.13.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
122
+ "model.language_model.layers.13.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.language_model.layers.13.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
124
+ "model.language_model.layers.13.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
125
+ "model.language_model.layers.13.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
126
+ "model.language_model.layers.13.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
127
+ "model.language_model.layers.13.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
128
+ "model.language_model.layers.13.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
129
+ "model.language_model.layers.13.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
130
+ "model.language_model.layers.13.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
131
+ "model.language_model.layers.13.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
132
+ "model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
133
+ "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
134
+ "model.language_model.layers.14.linear_attn.A_log": "model-00001-of-00002.safetensors",
135
+ "model.language_model.layers.14.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
136
+ "model.language_model.layers.14.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
137
+ "model.language_model.layers.14.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
138
+ "model.language_model.layers.14.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
139
+ "model.language_model.layers.14.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
140
+ "model.language_model.layers.14.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
141
+ "model.language_model.layers.14.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
142
+ "model.language_model.layers.14.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
143
+ "model.language_model.layers.14.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
144
+ "model.language_model.layers.14.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
145
+ "model.language_model.layers.14.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
146
+ "model.language_model.layers.14.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
147
+ "model.language_model.layers.14.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
148
+ "model.language_model.layers.14.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
149
+ "model.language_model.layers.14.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
150
+ "model.language_model.layers.14.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
151
+ "model.language_model.layers.14.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
152
+ "model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
153
+ "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
154
+ "model.language_model.layers.15.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
155
+ "model.language_model.layers.15.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
156
+ "model.language_model.layers.15.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
157
+ "model.language_model.layers.15.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
158
+ "model.language_model.layers.15.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
159
+ "model.language_model.layers.15.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
160
+ "model.language_model.layers.15.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
161
+ "model.language_model.layers.15.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
162
+ "model.language_model.layers.15.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
163
+ "model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
164
+ "model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
165
+ "model.language_model.layers.15.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
166
+ "model.language_model.layers.15.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
167
+ "model.language_model.layers.15.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
168
+ "model.language_model.layers.15.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
169
+ "model.language_model.layers.15.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
170
+ "model.language_model.layers.15.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
171
+ "model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
172
+ "model.language_model.layers.15.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
173
+ "model.language_model.layers.15.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
174
+ "model.language_model.layers.15.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
175
+ "model.language_model.layers.15.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
176
+ "model.language_model.layers.15.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
177
+ "model.language_model.layers.15.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
178
+ "model.language_model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
179
+ "model.language_model.layers.16.linear_attn.A_log": "model-00001-of-00002.safetensors",
180
+ "model.language_model.layers.16.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
181
+ "model.language_model.layers.16.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
182
+ "model.language_model.layers.16.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
183
+ "model.language_model.layers.16.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
184
+ "model.language_model.layers.16.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
185
+ "model.language_model.layers.16.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
186
+ "model.language_model.layers.16.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
187
+ "model.language_model.layers.16.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
188
+ "model.language_model.layers.16.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
189
+ "model.language_model.layers.16.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
190
+ "model.language_model.layers.16.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
191
+ "model.language_model.layers.16.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
192
+ "model.language_model.layers.16.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
193
+ "model.language_model.layers.16.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
194
+ "model.language_model.layers.16.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
195
+ "model.language_model.layers.16.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
196
+ "model.language_model.layers.16.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
197
+ "model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
198
+ "model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
199
+ "model.language_model.layers.17.linear_attn.A_log": "model-00001-of-00002.safetensors",
200
+ "model.language_model.layers.17.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
201
+ "model.language_model.layers.17.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
202
+ "model.language_model.layers.17.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
203
+ "model.language_model.layers.17.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
204
+ "model.language_model.layers.17.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
205
+ "model.language_model.layers.17.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
206
+ "model.language_model.layers.17.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
207
+ "model.language_model.layers.17.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
208
+ "model.language_model.layers.17.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
209
+ "model.language_model.layers.17.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
210
+ "model.language_model.layers.17.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
211
+ "model.language_model.layers.17.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
212
+ "model.language_model.layers.17.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
213
+ "model.language_model.layers.17.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
214
+ "model.language_model.layers.17.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
215
+ "model.language_model.layers.17.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
216
+ "model.language_model.layers.17.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
217
+ "model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
218
+ "model.language_model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
219
+ "model.language_model.layers.18.linear_attn.A_log": "model-00001-of-00002.safetensors",
220
+ "model.language_model.layers.18.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
221
+ "model.language_model.layers.18.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
222
+ "model.language_model.layers.18.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
223
+ "model.language_model.layers.18.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
224
+ "model.language_model.layers.18.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
225
+ "model.language_model.layers.18.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
226
+ "model.language_model.layers.18.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
227
+ "model.language_model.layers.18.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
228
+ "model.language_model.layers.18.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
229
+ "model.language_model.layers.18.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
230
+ "model.language_model.layers.18.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
231
+ "model.language_model.layers.18.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
232
+ "model.language_model.layers.18.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
233
+ "model.language_model.layers.18.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
234
+ "model.language_model.layers.18.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
235
+ "model.language_model.layers.18.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
236
+ "model.language_model.layers.18.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
237
+ "model.language_model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
238
+ "model.language_model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
239
+ "model.language_model.layers.19.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
240
+ "model.language_model.layers.19.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
241
+ "model.language_model.layers.19.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
242
+ "model.language_model.layers.19.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
243
+ "model.language_model.layers.19.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
244
+ "model.language_model.layers.19.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
245
+ "model.language_model.layers.19.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
246
+ "model.language_model.layers.19.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
247
+ "model.language_model.layers.19.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
248
+ "model.language_model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
249
+ "model.language_model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
250
+ "model.language_model.layers.19.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
251
+ "model.language_model.layers.19.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
252
+ "model.language_model.layers.19.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
253
+ "model.language_model.layers.19.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
254
+ "model.language_model.layers.19.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
255
+ "model.language_model.layers.19.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
256
+ "model.language_model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
257
+ "model.language_model.layers.19.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
258
+ "model.language_model.layers.19.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
259
+ "model.language_model.layers.19.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
260
+ "model.language_model.layers.19.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
261
+ "model.language_model.layers.19.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
262
+ "model.language_model.layers.19.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
263
+ "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
264
+ "model.language_model.layers.2.linear_attn.A_log": "model-00001-of-00002.safetensors",
265
+ "model.language_model.layers.2.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
266
+ "model.language_model.layers.2.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
267
+ "model.language_model.layers.2.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
268
+ "model.language_model.layers.2.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
269
+ "model.language_model.layers.2.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
270
+ "model.language_model.layers.2.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
271
+ "model.language_model.layers.2.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
272
+ "model.language_model.layers.2.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
273
+ "model.language_model.layers.2.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
274
+ "model.language_model.layers.2.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
275
+ "model.language_model.layers.2.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
276
+ "model.language_model.layers.2.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
277
+ "model.language_model.layers.2.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
278
+ "model.language_model.layers.2.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
279
+ "model.language_model.layers.2.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
280
+ "model.language_model.layers.2.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
281
+ "model.language_model.layers.2.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
282
+ "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
283
+ "model.language_model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
284
+ "model.language_model.layers.20.linear_attn.A_log": "model-00001-of-00002.safetensors",
285
+ "model.language_model.layers.20.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
286
+ "model.language_model.layers.20.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
287
+ "model.language_model.layers.20.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
288
+ "model.language_model.layers.20.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
289
+ "model.language_model.layers.20.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
290
+ "model.language_model.layers.20.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
291
+ "model.language_model.layers.20.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
292
+ "model.language_model.layers.20.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
293
+ "model.language_model.layers.20.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
294
+ "model.language_model.layers.20.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
295
+ "model.language_model.layers.20.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
296
+ "model.language_model.layers.20.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
297
+ "model.language_model.layers.20.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
298
+ "model.language_model.layers.20.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
299
+ "model.language_model.layers.20.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
300
+ "model.language_model.layers.20.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
301
+ "model.language_model.layers.20.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
302
+ "model.language_model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
303
+ "model.language_model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
304
+ "model.language_model.layers.21.linear_attn.A_log": "model-00001-of-00002.safetensors",
305
+ "model.language_model.layers.21.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
306
+ "model.language_model.layers.21.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
307
+ "model.language_model.layers.21.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
308
+ "model.language_model.layers.21.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
309
+ "model.language_model.layers.21.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
310
+ "model.language_model.layers.21.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
311
+ "model.language_model.layers.21.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
312
+ "model.language_model.layers.21.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
313
+ "model.language_model.layers.21.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
314
+ "model.language_model.layers.21.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
315
+ "model.language_model.layers.21.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
316
+ "model.language_model.layers.21.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
317
+ "model.language_model.layers.21.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
318
+ "model.language_model.layers.21.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
319
+ "model.language_model.layers.21.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
320
+ "model.language_model.layers.21.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
321
+ "model.language_model.layers.21.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
322
+ "model.language_model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
323
+ "model.language_model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
324
+ "model.language_model.layers.22.linear_attn.A_log": "model-00001-of-00002.safetensors",
325
+ "model.language_model.layers.22.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
326
+ "model.language_model.layers.22.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
327
+ "model.language_model.layers.22.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
328
+ "model.language_model.layers.22.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
329
+ "model.language_model.layers.22.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
330
+ "model.language_model.layers.22.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
331
+ "model.language_model.layers.22.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
332
+ "model.language_model.layers.22.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
333
+ "model.language_model.layers.22.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
334
+ "model.language_model.layers.22.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
335
+ "model.language_model.layers.22.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
336
+ "model.language_model.layers.22.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
337
+ "model.language_model.layers.22.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
338
+ "model.language_model.layers.22.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
339
+ "model.language_model.layers.22.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
340
+ "model.language_model.layers.22.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
341
+ "model.language_model.layers.22.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
342
+ "model.language_model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
343
+ "model.language_model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
344
+ "model.language_model.layers.23.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
345
+ "model.language_model.layers.23.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
346
+ "model.language_model.layers.23.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
347
+ "model.language_model.layers.23.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
348
+ "model.language_model.layers.23.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
349
+ "model.language_model.layers.23.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
350
+ "model.language_model.layers.23.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
351
+ "model.language_model.layers.23.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
352
+ "model.language_model.layers.23.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
353
+ "model.language_model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
354
+ "model.language_model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
355
+ "model.language_model.layers.23.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
356
+ "model.language_model.layers.23.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
357
+ "model.language_model.layers.23.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
358
+ "model.language_model.layers.23.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
359
+ "model.language_model.layers.23.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
360
+ "model.language_model.layers.23.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
361
+ "model.language_model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
362
+ "model.language_model.layers.23.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
363
+ "model.language_model.layers.23.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
364
+ "model.language_model.layers.23.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
365
+ "model.language_model.layers.23.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
366
+ "model.language_model.layers.23.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
367
+ "model.language_model.layers.23.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
368
+ "model.language_model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
369
+ "model.language_model.layers.24.linear_attn.A_log": "model-00001-of-00002.safetensors",
370
+ "model.language_model.layers.24.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
371
+ "model.language_model.layers.24.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
372
+ "model.language_model.layers.24.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
373
+ "model.language_model.layers.24.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
374
+ "model.language_model.layers.24.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
375
+ "model.language_model.layers.24.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
376
+ "model.language_model.layers.24.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
377
+ "model.language_model.layers.24.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
378
+ "model.language_model.layers.24.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
379
+ "model.language_model.layers.24.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
380
+ "model.language_model.layers.24.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
381
+ "model.language_model.layers.24.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
382
+ "model.language_model.layers.24.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
383
+ "model.language_model.layers.24.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
384
+ "model.language_model.layers.24.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
385
+ "model.language_model.layers.24.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
386
+ "model.language_model.layers.24.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
387
+ "model.language_model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
388
+ "model.language_model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
389
+ "model.language_model.layers.25.linear_attn.A_log": "model-00001-of-00002.safetensors",
390
+ "model.language_model.layers.25.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
391
+ "model.language_model.layers.25.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
392
+ "model.language_model.layers.25.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
393
+ "model.language_model.layers.25.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
394
+ "model.language_model.layers.25.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
395
+ "model.language_model.layers.25.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
396
+ "model.language_model.layers.25.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
397
+ "model.language_model.layers.25.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
398
+ "model.language_model.layers.25.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
399
+ "model.language_model.layers.25.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
400
+ "model.language_model.layers.25.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
401
+ "model.language_model.layers.25.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
402
+ "model.language_model.layers.25.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
403
+ "model.language_model.layers.25.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
404
+ "model.language_model.layers.25.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
405
+ "model.language_model.layers.25.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
406
+ "model.language_model.layers.25.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
407
+ "model.language_model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
408
+ "model.language_model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
409
+ "model.language_model.layers.26.linear_attn.A_log": "model-00001-of-00002.safetensors",
410
+ "model.language_model.layers.26.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
411
+ "model.language_model.layers.26.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
412
+ "model.language_model.layers.26.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
413
+ "model.language_model.layers.26.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
414
+ "model.language_model.layers.26.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
415
+ "model.language_model.layers.26.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
416
+ "model.language_model.layers.26.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
417
+ "model.language_model.layers.26.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
418
+ "model.language_model.layers.26.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
419
+ "model.language_model.layers.26.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
420
+ "model.language_model.layers.26.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
421
+ "model.language_model.layers.26.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
422
+ "model.language_model.layers.26.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
423
+ "model.language_model.layers.26.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
424
+ "model.language_model.layers.26.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
425
+ "model.language_model.layers.26.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
426
+ "model.language_model.layers.26.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
427
+ "model.language_model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
428
+ "model.language_model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
429
+ "model.language_model.layers.27.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
430
+ "model.language_model.layers.27.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
431
+ "model.language_model.layers.27.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
432
+ "model.language_model.layers.27.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
433
+ "model.language_model.layers.27.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
434
+ "model.language_model.layers.27.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
435
+ "model.language_model.layers.27.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
436
+ "model.language_model.layers.27.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
437
+ "model.language_model.layers.27.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
438
+ "model.language_model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
439
+ "model.language_model.layers.27.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
440
+ "model.language_model.layers.27.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
441
+ "model.language_model.layers.27.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
442
+ "model.language_model.layers.27.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
443
+ "model.language_model.layers.27.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
444
+ "model.language_model.layers.27.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
445
+ "model.language_model.layers.27.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
446
+ "model.language_model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
447
+ "model.language_model.layers.27.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
448
+ "model.language_model.layers.27.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
449
+ "model.language_model.layers.27.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
450
+ "model.language_model.layers.27.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
451
+ "model.language_model.layers.27.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
452
+ "model.language_model.layers.27.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
453
+ "model.language_model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
454
+ "model.language_model.layers.28.linear_attn.A_log": "model-00001-of-00002.safetensors",
455
+ "model.language_model.layers.28.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
456
+ "model.language_model.layers.28.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
457
+ "model.language_model.layers.28.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
458
+ "model.language_model.layers.28.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
459
+ "model.language_model.layers.28.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
460
+ "model.language_model.layers.28.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
461
+ "model.language_model.layers.28.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
462
+ "model.language_model.layers.28.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
463
+ "model.language_model.layers.28.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
464
+ "model.language_model.layers.28.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
465
+ "model.language_model.layers.28.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
466
+ "model.language_model.layers.28.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
467
+ "model.language_model.layers.28.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
468
+ "model.language_model.layers.28.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
469
+ "model.language_model.layers.28.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
470
+ "model.language_model.layers.28.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
471
+ "model.language_model.layers.28.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
472
+ "model.language_model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
473
+ "model.language_model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
474
+ "model.language_model.layers.29.linear_attn.A_log": "model-00001-of-00002.safetensors",
475
+ "model.language_model.layers.29.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
476
+ "model.language_model.layers.29.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
477
+ "model.language_model.layers.29.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
478
+ "model.language_model.layers.29.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
479
+ "model.language_model.layers.29.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
480
+ "model.language_model.layers.29.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
481
+ "model.language_model.layers.29.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
482
+ "model.language_model.layers.29.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
483
+ "model.language_model.layers.29.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
484
+ "model.language_model.layers.29.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
485
+ "model.language_model.layers.29.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
486
+ "model.language_model.layers.29.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
487
+ "model.language_model.layers.29.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
488
+ "model.language_model.layers.29.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
489
+ "model.language_model.layers.29.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
490
+ "model.language_model.layers.29.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
491
+ "model.language_model.layers.29.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
492
+ "model.language_model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
493
+ "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
494
+ "model.language_model.layers.3.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
495
+ "model.language_model.layers.3.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
496
+ "model.language_model.layers.3.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
497
+ "model.language_model.layers.3.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
498
+ "model.language_model.layers.3.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
499
+ "model.language_model.layers.3.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
500
+ "model.language_model.layers.3.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
501
+ "model.language_model.layers.3.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
502
+ "model.language_model.layers.3.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
503
+ "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
504
+ "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
505
+ "model.language_model.layers.3.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
506
+ "model.language_model.layers.3.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
507
+ "model.language_model.layers.3.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
508
+ "model.language_model.layers.3.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
509
+ "model.language_model.layers.3.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
510
+ "model.language_model.layers.3.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
511
+ "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
512
+ "model.language_model.layers.3.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
513
+ "model.language_model.layers.3.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
514
+ "model.language_model.layers.3.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
515
+ "model.language_model.layers.3.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
516
+ "model.language_model.layers.3.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
517
+ "model.language_model.layers.3.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
518
+ "model.language_model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
519
+ "model.language_model.layers.30.linear_attn.A_log": "model-00001-of-00002.safetensors",
520
+ "model.language_model.layers.30.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
521
+ "model.language_model.layers.30.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
522
+ "model.language_model.layers.30.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
523
+ "model.language_model.layers.30.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
524
+ "model.language_model.layers.30.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
525
+ "model.language_model.layers.30.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
526
+ "model.language_model.layers.30.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
527
+ "model.language_model.layers.30.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
528
+ "model.language_model.layers.30.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
529
+ "model.language_model.layers.30.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
530
+ "model.language_model.layers.30.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
531
+ "model.language_model.layers.30.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
532
+ "model.language_model.layers.30.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
533
+ "model.language_model.layers.30.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
534
+ "model.language_model.layers.30.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
535
+ "model.language_model.layers.30.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
536
+ "model.language_model.layers.30.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
537
+ "model.language_model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
538
+ "model.language_model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
539
+ "model.language_model.layers.31.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
540
+ "model.language_model.layers.31.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
541
+ "model.language_model.layers.31.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
542
+ "model.language_model.layers.31.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
543
+ "model.language_model.layers.31.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
544
+ "model.language_model.layers.31.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
545
+ "model.language_model.layers.31.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
546
+ "model.language_model.layers.31.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
547
+ "model.language_model.layers.31.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
548
+ "model.language_model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
549
+ "model.language_model.layers.31.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
550
+ "model.language_model.layers.31.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
551
+ "model.language_model.layers.31.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
552
+ "model.language_model.layers.31.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
553
+ "model.language_model.layers.31.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
554
+ "model.language_model.layers.31.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
555
+ "model.language_model.layers.31.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
556
+ "model.language_model.layers.31.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
557
+ "model.language_model.layers.31.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
558
+ "model.language_model.layers.31.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
559
+ "model.language_model.layers.31.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
560
+ "model.language_model.layers.31.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
561
+ "model.language_model.layers.31.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
562
+ "model.language_model.layers.31.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
563
+ "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
564
+ "model.language_model.layers.4.linear_attn.A_log": "model-00001-of-00002.safetensors",
565
+ "model.language_model.layers.4.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
566
+ "model.language_model.layers.4.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
567
+ "model.language_model.layers.4.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
568
+ "model.language_model.layers.4.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
569
+ "model.language_model.layers.4.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
570
+ "model.language_model.layers.4.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
571
+ "model.language_model.layers.4.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
572
+ "model.language_model.layers.4.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
573
+ "model.language_model.layers.4.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
574
+ "model.language_model.layers.4.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
575
+ "model.language_model.layers.4.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
576
+ "model.language_model.layers.4.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
577
+ "model.language_model.layers.4.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
578
+ "model.language_model.layers.4.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
579
+ "model.language_model.layers.4.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
580
+ "model.language_model.layers.4.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
581
+ "model.language_model.layers.4.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
582
+ "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
583
+ "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
584
+ "model.language_model.layers.5.linear_attn.A_log": "model-00001-of-00002.safetensors",
585
+ "model.language_model.layers.5.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
586
+ "model.language_model.layers.5.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
587
+ "model.language_model.layers.5.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
588
+ "model.language_model.layers.5.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
589
+ "model.language_model.layers.5.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
590
+ "model.language_model.layers.5.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
591
+ "model.language_model.layers.5.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
592
+ "model.language_model.layers.5.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
593
+ "model.language_model.layers.5.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
594
+ "model.language_model.layers.5.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
595
+ "model.language_model.layers.5.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
596
+ "model.language_model.layers.5.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
597
+ "model.language_model.layers.5.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
598
+ "model.language_model.layers.5.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
599
+ "model.language_model.layers.5.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
600
+ "model.language_model.layers.5.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
601
+ "model.language_model.layers.5.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
602
+ "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
603
+ "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
604
+ "model.language_model.layers.6.linear_attn.A_log": "model-00001-of-00002.safetensors",
605
+ "model.language_model.layers.6.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
606
+ "model.language_model.layers.6.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
607
+ "model.language_model.layers.6.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
608
+ "model.language_model.layers.6.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
609
+ "model.language_model.layers.6.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
610
+ "model.language_model.layers.6.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
611
+ "model.language_model.layers.6.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
612
+ "model.language_model.layers.6.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
613
+ "model.language_model.layers.6.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
614
+ "model.language_model.layers.6.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
615
+ "model.language_model.layers.6.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
616
+ "model.language_model.layers.6.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
617
+ "model.language_model.layers.6.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
618
+ "model.language_model.layers.6.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
619
+ "model.language_model.layers.6.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
620
+ "model.language_model.layers.6.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
621
+ "model.language_model.layers.6.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
622
+ "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
623
+ "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
624
+ "model.language_model.layers.7.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
625
+ "model.language_model.layers.7.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
626
+ "model.language_model.layers.7.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
627
+ "model.language_model.layers.7.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
628
+ "model.language_model.layers.7.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
629
+ "model.language_model.layers.7.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
630
+ "model.language_model.layers.7.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
631
+ "model.language_model.layers.7.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
632
+ "model.language_model.layers.7.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
633
+ "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
634
+ "model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
635
+ "model.language_model.layers.7.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
636
+ "model.language_model.layers.7.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
637
+ "model.language_model.layers.7.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
638
+ "model.language_model.layers.7.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
639
+ "model.language_model.layers.7.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
640
+ "model.language_model.layers.7.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
641
+ "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
642
+ "model.language_model.layers.7.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
643
+ "model.language_model.layers.7.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
644
+ "model.language_model.layers.7.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
645
+ "model.language_model.layers.7.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
646
+ "model.language_model.layers.7.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
647
+ "model.language_model.layers.7.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
648
+ "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
649
+ "model.language_model.layers.8.linear_attn.A_log": "model-00001-of-00002.safetensors",
650
+ "model.language_model.layers.8.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
651
+ "model.language_model.layers.8.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
652
+ "model.language_model.layers.8.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
653
+ "model.language_model.layers.8.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
654
+ "model.language_model.layers.8.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
655
+ "model.language_model.layers.8.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
656
+ "model.language_model.layers.8.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
657
+ "model.language_model.layers.8.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
658
+ "model.language_model.layers.8.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
659
+ "model.language_model.layers.8.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
660
+ "model.language_model.layers.8.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
661
+ "model.language_model.layers.8.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
662
+ "model.language_model.layers.8.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
663
+ "model.language_model.layers.8.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
664
+ "model.language_model.layers.8.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
665
+ "model.language_model.layers.8.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
666
+ "model.language_model.layers.8.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
667
+ "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
668
+ "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
669
+ "model.language_model.layers.9.linear_attn.A_log": "model-00001-of-00002.safetensors",
670
+ "model.language_model.layers.9.linear_attn.conv1d.weight": "model-00001-of-00002.safetensors",
671
+ "model.language_model.layers.9.linear_attn.dt_bias": "model-00001-of-00002.safetensors",
672
+ "model.language_model.layers.9.linear_attn.in_proj_a.weight": "model-00001-of-00002.safetensors",
673
+ "model.language_model.layers.9.linear_attn.in_proj_b.weight": "model-00001-of-00002.safetensors",
674
+ "model.language_model.layers.9.linear_attn.in_proj_qkv.weight": "model-00001-of-00002.safetensors",
675
+ "model.language_model.layers.9.linear_attn.in_proj_z.weight": "model-00001-of-00002.safetensors",
676
+ "model.language_model.layers.9.linear_attn.norm.weight": "model-00001-of-00002.safetensors",
677
+ "model.language_model.layers.9.linear_attn.out_proj.weight": "model-00001-of-00002.safetensors",
678
+ "model.language_model.layers.9.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
679
+ "model.language_model.layers.9.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
680
+ "model.language_model.layers.9.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
681
+ "model.language_model.layers.9.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
682
+ "model.language_model.layers.9.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
683
+ "model.language_model.layers.9.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
684
+ "model.language_model.layers.9.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
685
+ "model.language_model.layers.9.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
686
+ "model.language_model.layers.9.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
687
+ "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
688
+ "model.language_model.norm.weight": "model-00001-of-00002.safetensors",
689
+ "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
690
+ "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
691
+ "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
692
+ "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
693
+ "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
694
+ "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
695
+ "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
696
+ "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
697
+ "model.visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
698
+ "model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
699
+ "model.visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
700
+ "model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
701
+ "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
702
+ "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
703
+ "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
704
+ "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
705
+ "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
706
+ "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
707
+ "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
708
+ "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
709
+ "model.visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
710
+ "model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
711
+ "model.visual.blocks.1.norm2.bias": "model-00001-of-00002.safetensors",
712
+ "model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
713
+ "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
714
+ "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
715
+ "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
716
+ "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
717
+ "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
718
+ "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
719
+ "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
720
+ "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
721
+ "model.visual.blocks.10.norm1.bias": "model-00001-of-00002.safetensors",
722
+ "model.visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
723
+ "model.visual.blocks.10.norm2.bias": "model-00001-of-00002.safetensors",
724
+ "model.visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
725
+ "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
726
+ "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
727
+ "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
728
+ "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
729
+ "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
730
+ "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
731
+ "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
732
+ "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
733
+ "model.visual.blocks.11.norm1.bias": "model-00001-of-00002.safetensors",
734
+ "model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
735
+ "model.visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
736
+ "model.visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
737
+ "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
738
+ "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
739
+ "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
740
+ "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
741
+ "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
742
+ "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
743
+ "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
744
+ "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
745
+ "model.visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors",
746
+ "model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
747
+ "model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
748
+ "model.visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
749
+ "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
750
+ "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
751
+ "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
752
+ "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
753
+ "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
754
+ "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
755
+ "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
756
+ "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
757
+ "model.visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors",
758
+ "model.visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
759
+ "model.visual.blocks.13.norm2.bias": "model-00001-of-00002.safetensors",
760
+ "model.visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
761
+ "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
762
+ "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
763
+ "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
764
+ "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
765
+ "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
766
+ "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
767
+ "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
768
+ "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
769
+ "model.visual.blocks.14.norm1.bias": "model-00001-of-00002.safetensors",
770
+ "model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
771
+ "model.visual.blocks.14.norm2.bias": "model-00001-of-00002.safetensors",
772
+ "model.visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
773
+ "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
774
+ "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
775
+ "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
776
+ "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
777
+ "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
778
+ "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
779
+ "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
780
+ "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
781
+ "model.visual.blocks.15.norm1.bias": "model-00002-of-00002.safetensors",
782
+ "model.visual.blocks.15.norm1.weight": "model-00002-of-00002.safetensors",
783
+ "model.visual.blocks.15.norm2.bias": "model-00002-of-00002.safetensors",
784
+ "model.visual.blocks.15.norm2.weight": "model-00002-of-00002.safetensors",
785
+ "model.visual.blocks.16.attn.proj.bias": "model-00002-of-00002.safetensors",
786
+ "model.visual.blocks.16.attn.proj.weight": "model-00002-of-00002.safetensors",
787
+ "model.visual.blocks.16.attn.qkv.bias": "model-00002-of-00002.safetensors",
788
+ "model.visual.blocks.16.attn.qkv.weight": "model-00002-of-00002.safetensors",
789
+ "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
790
+ "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
791
+ "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
792
+ "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
793
+ "model.visual.blocks.16.norm1.bias": "model-00002-of-00002.safetensors",
794
+ "model.visual.blocks.16.norm1.weight": "model-00002-of-00002.safetensors",
795
+ "model.visual.blocks.16.norm2.bias": "model-00002-of-00002.safetensors",
796
+ "model.visual.blocks.16.norm2.weight": "model-00002-of-00002.safetensors",
797
+ "model.visual.blocks.17.attn.proj.bias": "model-00002-of-00002.safetensors",
798
+ "model.visual.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors",
799
+ "model.visual.blocks.17.attn.qkv.bias": "model-00002-of-00002.safetensors",
800
+ "model.visual.blocks.17.attn.qkv.weight": "model-00002-of-00002.safetensors",
801
+ "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
802
+ "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
803
+ "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
804
+ "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
805
+ "model.visual.blocks.17.norm1.bias": "model-00002-of-00002.safetensors",
806
+ "model.visual.blocks.17.norm1.weight": "model-00002-of-00002.safetensors",
807
+ "model.visual.blocks.17.norm2.bias": "model-00002-of-00002.safetensors",
808
+ "model.visual.blocks.17.norm2.weight": "model-00002-of-00002.safetensors",
809
+ "model.visual.blocks.18.attn.proj.bias": "model-00002-of-00002.safetensors",
810
+ "model.visual.blocks.18.attn.proj.weight": "model-00002-of-00002.safetensors",
811
+ "model.visual.blocks.18.attn.qkv.bias": "model-00002-of-00002.safetensors",
812
+ "model.visual.blocks.18.attn.qkv.weight": "model-00002-of-00002.safetensors",
813
+ "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
814
+ "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
815
+ "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
816
+ "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
817
+ "model.visual.blocks.18.norm1.bias": "model-00002-of-00002.safetensors",
818
+ "model.visual.blocks.18.norm1.weight": "model-00002-of-00002.safetensors",
819
+ "model.visual.blocks.18.norm2.bias": "model-00002-of-00002.safetensors",
820
+ "model.visual.blocks.18.norm2.weight": "model-00002-of-00002.safetensors",
821
+ "model.visual.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors",
822
+ "model.visual.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors",
823
+ "model.visual.blocks.19.attn.qkv.bias": "model-00002-of-00002.safetensors",
824
+ "model.visual.blocks.19.attn.qkv.weight": "model-00002-of-00002.safetensors",
825
+ "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
826
+ "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
827
+ "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
828
+ "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
829
+ "model.visual.blocks.19.norm1.bias": "model-00002-of-00002.safetensors",
830
+ "model.visual.blocks.19.norm1.weight": "model-00002-of-00002.safetensors",
831
+ "model.visual.blocks.19.norm2.bias": "model-00002-of-00002.safetensors",
832
+ "model.visual.blocks.19.norm2.weight": "model-00002-of-00002.safetensors",
833
+ "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
834
+ "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
835
+ "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
836
+ "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
837
+ "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
838
+ "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
839
+ "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
840
+ "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
841
+ "model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
842
+ "model.visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
843
+ "model.visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
844
+ "model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
845
+ "model.visual.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors",
846
+ "model.visual.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors",
847
+ "model.visual.blocks.20.attn.qkv.bias": "model-00002-of-00002.safetensors",
848
+ "model.visual.blocks.20.attn.qkv.weight": "model-00002-of-00002.safetensors",
849
+ "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
850
+ "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
851
+ "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
852
+ "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
853
+ "model.visual.blocks.20.norm1.bias": "model-00002-of-00002.safetensors",
854
+ "model.visual.blocks.20.norm1.weight": "model-00002-of-00002.safetensors",
855
+ "model.visual.blocks.20.norm2.bias": "model-00002-of-00002.safetensors",
856
+ "model.visual.blocks.20.norm2.weight": "model-00002-of-00002.safetensors",
857
+ "model.visual.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors",
858
+ "model.visual.blocks.21.attn.proj.weight": "model-00002-of-00002.safetensors",
859
+ "model.visual.blocks.21.attn.qkv.bias": "model-00002-of-00002.safetensors",
860
+ "model.visual.blocks.21.attn.qkv.weight": "model-00002-of-00002.safetensors",
861
+ "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
862
+ "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
863
+ "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
864
+ "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
865
+ "model.visual.blocks.21.norm1.bias": "model-00002-of-00002.safetensors",
866
+ "model.visual.blocks.21.norm1.weight": "model-00002-of-00002.safetensors",
867
+ "model.visual.blocks.21.norm2.bias": "model-00002-of-00002.safetensors",
868
+ "model.visual.blocks.21.norm2.weight": "model-00002-of-00002.safetensors",
869
+ "model.visual.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors",
870
+ "model.visual.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors",
871
+ "model.visual.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors",
872
+ "model.visual.blocks.22.attn.qkv.weight": "model-00002-of-00002.safetensors",
873
+ "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
874
+ "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
875
+ "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
876
+ "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
877
+ "model.visual.blocks.22.norm1.bias": "model-00002-of-00002.safetensors",
878
+ "model.visual.blocks.22.norm1.weight": "model-00002-of-00002.safetensors",
879
+ "model.visual.blocks.22.norm2.bias": "model-00002-of-00002.safetensors",
880
+ "model.visual.blocks.22.norm2.weight": "model-00002-of-00002.safetensors",
881
+ "model.visual.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors",
882
+ "model.visual.blocks.23.attn.proj.weight": "model-00002-of-00002.safetensors",
883
+ "model.visual.blocks.23.attn.qkv.bias": "model-00002-of-00002.safetensors",
884
+ "model.visual.blocks.23.attn.qkv.weight": "model-00002-of-00002.safetensors",
885
+ "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
886
+ "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
887
+ "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
888
+ "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
889
+ "model.visual.blocks.23.norm1.bias": "model-00002-of-00002.safetensors",
890
+ "model.visual.blocks.23.norm1.weight": "model-00002-of-00002.safetensors",
891
+ "model.visual.blocks.23.norm2.bias": "model-00002-of-00002.safetensors",
892
+ "model.visual.blocks.23.norm2.weight": "model-00002-of-00002.safetensors",
893
+ "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
894
+ "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
895
+ "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
896
+ "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
897
+ "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
898
+ "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
899
+ "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
900
+ "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
901
+ "model.visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
902
+ "model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
903
+ "model.visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
904
+ "model.visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
905
+ "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
906
+ "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
907
+ "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
908
+ "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
909
+ "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
910
+ "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
911
+ "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
912
+ "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
913
+ "model.visual.blocks.4.norm1.bias": "model-00001-of-00002.safetensors",
914
+ "model.visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
915
+ "model.visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
916
+ "model.visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
917
+ "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
918
+ "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
919
+ "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
920
+ "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
921
+ "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
922
+ "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
923
+ "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
924
+ "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
925
+ "model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
926
+ "model.visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
927
+ "model.visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
928
+ "model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
929
+ "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
930
+ "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
931
+ "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
932
+ "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
933
+ "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
934
+ "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
935
+ "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
936
+ "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
937
+ "model.visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
938
+ "model.visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
939
+ "model.visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
940
+ "model.visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
941
+ "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
942
+ "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
943
+ "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
944
+ "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
945
+ "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
946
+ "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
947
+ "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
948
+ "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
949
+ "model.visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors",
950
+ "model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
951
+ "model.visual.blocks.7.norm2.bias": "model-00001-of-00002.safetensors",
952
+ "model.visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
953
+ "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
954
+ "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
955
+ "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
956
+ "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
957
+ "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
958
+ "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
959
+ "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
960
+ "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
961
+ "model.visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
962
+ "model.visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
963
+ "model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
964
+ "model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
965
+ "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
966
+ "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
967
+ "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
968
+ "model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
969
+ "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
970
+ "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
971
+ "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
972
+ "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
973
+ "model.visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
974
+ "model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
975
+ "model.visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
976
+ "model.visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
977
+ "model.visual.merger.linear_fc1.bias": "model-00002-of-00002.safetensors",
978
+ "model.visual.merger.linear_fc1.weight": "model-00002-of-00002.safetensors",
979
+ "model.visual.merger.linear_fc2.bias": "model-00002-of-00002.safetensors",
980
+ "model.visual.merger.linear_fc2.weight": "model-00002-of-00002.safetensors",
981
+ "model.visual.merger.norm.bias": "model-00002-of-00002.safetensors",
982
+ "model.visual.merger.norm.weight": "model-00002-of-00002.safetensors",
983
+ "model.visual.patch_embed.proj.bias": "model-00002-of-00002.safetensors",
984
+ "model.visual.patch_embed.proj.weight": "model-00002-of-00002.safetensors",
985
+ "model.visual.pos_embed.weight": "model-00002-of-00002.safetensors"
986
+ }
987
+ }
processor_config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "data_format": "channels_first",
4
+ "do_convert_rgb": true,
5
+ "do_normalize": true,
6
+ "do_rescale": true,
7
+ "do_resize": true,
8
+ "image_mean": [
9
+ 0.5,
10
+ 0.5,
11
+ 0.5
12
+ ],
13
+ "image_processor_type": "Qwen2VLImageProcessorFast",
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "merge_size": 2,
20
+ "patch_size": 16,
21
+ "resample": 3,
22
+ "rescale_factor": 0.00392156862745098,
23
+ "size": {
24
+ "longest_edge": 16777216,
25
+ "shortest_edge": 65536
26
+ },
27
+ "temporal_patch_size": 2
28
+ },
29
+ "processor_class": "Qwen3VLProcessor",
30
+ "video_processor": {
31
+ "data_format": "channels_first",
32
+ "default_to_square": true,
33
+ "do_convert_rgb": true,
34
+ "do_normalize": true,
35
+ "do_rescale": true,
36
+ "do_resize": true,
37
+ "do_sample_frames": true,
38
+ "fps": 2,
39
+ "image_mean": [
40
+ 0.5,
41
+ 0.5,
42
+ 0.5
43
+ ],
44
+ "image_std": [
45
+ 0.5,
46
+ 0.5,
47
+ 0.5
48
+ ],
49
+ "max_frames": 768,
50
+ "merge_size": 2,
51
+ "min_frames": 4,
52
+ "patch_size": 16,
53
+ "resample": 3,
54
+ "rescale_factor": 0.00392156862745098,
55
+ "return_metadata": false,
56
+ "size": {
57
+ "longest_edge": 25165824,
58
+ "shortest_edge": 4096
59
+ },
60
+ "temporal_patch_size": 2,
61
+ "video_processor_type": "Qwen3VLVideoProcessor"
62
+ }
63
+ }
recipe.yaml ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ default_stage:
2
+ default_modifiers:
3
+ GPTQModifier:
4
+ targets: [Linear]
5
+ ignore: [lm_head, 're:.*visual.*', 're:.*linear_attn.*']
6
+ scheme: W4A16
7
+ bypass_divisibility_checks: false
8
+ block_size: 128
9
+ dampening_frac: 0.01
10
+ actorder: static
11
+ offload_hessians: false
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
3
+ size 19989325
tokenizer_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "audio_bos_token": "<|audio_start|>",
4
+ "audio_eos_token": "<|audio_end|>",
5
+ "audio_token": "<|audio_pad|>",
6
+ "backend": "tokenizers",
7
+ "bos_token": null,
8
+ "clean_up_tokenization_spaces": false,
9
+ "eos_token": "<|im_end|>",
10
+ "errors": "replace",
11
+ "image_token": "<|image_pad|>",
12
+ "is_local": false,
13
+ "model_max_length": 262144,
14
+ "model_specific_special_tokens": {
15
+ "audio_bos_token": "<|audio_start|>",
16
+ "audio_eos_token": "<|audio_end|>",
17
+ "audio_token": "<|audio_pad|>",
18
+ "image_token": "<|image_pad|>",
19
+ "video_token": "<|video_pad|>",
20
+ "vision_bos_token": "<|vision_start|>",
21
+ "vision_eos_token": "<|vision_end|>"
22
+ },
23
+ "pad_token": "<|endoftext|>",
24
+ "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
25
+ "processor_class": "Qwen3VLProcessor",
26
+ "split_special_tokens": false,
27
+ "tokenizer_class": "Qwen2Tokenizer",
28
+ "unk_token": null,
29
+ "video_token": "<|video_pad|>",
30
+ "vision_bos_token": "<|vision_start|>",
31
+ "vision_eos_token": "<|vision_end|>"
32
+ }