Hugging Face's logo

Inferact
/
Qwen3.8-Flash-Next-NVFP4

Image-Text-to-Text
Transformers
Safetensors
qwen4_exp
conversational
8-bit precision
modelopt
Model card Files
xet
 Community
2
Isotr0py commited on
Commit
98e6a6f
·
verified ·
1 Parent(s): 34f5b9a

Upload folder using huggingface_hub

Browse files
Files changed (33) hide show
  1. .gitattributes +2 -0
  2. README.md +3 -0
  3. chat_template.jinja +170 -0
  4. config.json +1460 -0
  5. generation_config.json +12 -0
  6. merges.txt +0 -0
  7. model-00001-of-00004.safetensors +3 -0
  8. model-00002-of-00004.safetensors +3 -0
  9. model-00003-of-00004.safetensors +3 -0
  10. model-00004-of-00004.safetensors +3 -0
  11. model.safetensors.index.json +3 -0
  12. nvfp4_experts-00001-of-00016.safetensors +3 -0
  13. nvfp4_experts-00002-of-00016.safetensors +3 -0
  14. nvfp4_experts-00003-of-00016.safetensors +3 -0
  15. nvfp4_experts-00004-of-00016.safetensors +3 -0
  16. nvfp4_experts-00005-of-00016.safetensors +3 -0
  17. nvfp4_experts-00006-of-00016.safetensors +3 -0
  18. nvfp4_experts-00007-of-00016.safetensors +3 -0
  19. nvfp4_experts-00008-of-00016.safetensors +3 -0
  20. nvfp4_experts-00009-of-00016.safetensors +3 -0
  21. nvfp4_experts-00010-of-00016.safetensors +3 -0
  22. nvfp4_experts-00011-of-00016.safetensors +3 -0
  23. nvfp4_experts-00012-of-00016.safetensors +3 -0
  24. nvfp4_experts-00013-of-00016.safetensors +3 -0
  25. nvfp4_experts-00014-of-00016.safetensors +3 -0
  26. nvfp4_experts-00015-of-00016.safetensors +3 -0
  27. nvfp4_experts-00016-of-00016.safetensors +3 -0
  28. nvfp4_experts_mtp.safetensors +3 -0
  29. preprocessor_config.json +21 -0
  30. tokenizer.json +3 -0
  31. tokenizer_config.json +305 -0
  32. video_preprocessor_config.json +21 -0
  33. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,5 @@ 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
37
+ model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ ---
chat_template.jinja ADDED
@@ -0,0 +1,170 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- set image_count = namespace(value=0) %}
2
+ {%- set video_count = namespace(value=0) %}
3
+ {%- macro render_content(content, do_vision_count, is_system_content=false) %}
4
+ {%- if content is string %}
5
+ {{- content }}
6
+ {%- elif content is iterable and content is not mapping %}
7
+ {%- for item in content %}
8
+ {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
9
+ {%- if is_system_content %}
10
+ {{- raise_exception('System message cannot contain images.') }}
11
+ {%- endif %}
12
+ {%- if do_vision_count %}
13
+ {%- set image_count.value = image_count.value + 1 %}
14
+ {%- endif %}
15
+ {%- if add_vision_id %}
16
+ {{- 'Picture ' ~ image_count.value ~ ': ' }}
17
+ {%- endif %}
18
+ {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
19
+ {%- elif 'video' in item or item.type == 'video' %}
20
+ {%- if is_system_content %}
21
+ {{- raise_exception('System message cannot contain videos.') }}
22
+ {%- endif %}
23
+ {%- if do_vision_count %}
24
+ {%- set video_count.value = video_count.value + 1 %}
25
+ {%- endif %}
26
+ {%- if add_vision_id %}
27
+ {{- 'Video ' ~ video_count.value ~ ': ' }}
28
+ {%- endif %}
29
+ {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
30
+ {%- elif 'text' in item %}
31
+ {{- item.text }}
32
+ {%- else %}
33
+ {{- raise_exception('Unexpected item type in content.') }}
34
+ {%- endif %}
35
+ {%- endfor %}
36
+ {%- elif content is none or content is undefined %}
37
+ {{- '' }}
38
+ {%- else %}
39
+ {{- raise_exception('Unexpected content type.') }}
40
+ {%- endif %}
41
+ {%- endmacro %}
42
+ {%- if not messages %}
43
+ {{- raise_exception('No messages provided.') }}
44
+ {%- endif %}
45
+ {%- set reasoning_instructions = '' %}
46
+ {%- if enable_thinking is undefined or enable_thinking is true %}
47
+ {%- set resolved_reasoning_effort = reasoning_effort|default('xhigh') %}
48
+ {%- if resolved_reasoning_effort not in ('xhigh', 'medium', 'low') %}
49
+ {{- raise_exception('Unexpected reasoning effort ' ~ reasoning_effort ~ '. Supported types are xhigh (default), medium, and low.') }}
50
+ {%- endif %}
51
+ {%- if resolved_reasoning_effort == 'xhigh' %}
52
+ {%- set reasoning_instructions = 'Reasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.' %}
53
+ {%- elif resolved_reasoning_effort == 'low' %}
54
+ {%- set reasoning_instructions = 'Reasoning effort is set to low. Keep your thinking brief and focused, moving directly to the conclusion without unnecessary elaboration.' %}
55
+ {%- endif %}
56
+ {%- endif %}
57
+ {%- if tools and tools is iterable and tools is not mapping %}
58
+ {{- '<|im_start|>system\n' }}
59
+ {%- if reasoning_instructions %}
60
+ {{- reasoning_instructions + '\n\n' }}
61
+ {%- endif %}
62
+ {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
63
+ {%- for tool in tools %}
64
+ {{- "\n" }}
65
+ {{- tool | tojson }}
66
+ {%- endfor %}
67
+ {{- "\n</tools>" }}
68
+ {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
69
+ {%- if messages[0].role == 'system' %}
70
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
71
+ {%- if content %}
72
+ {{- '\n\n' + content }}
73
+ {%- endif %}
74
+ {%- endif %}
75
+ {{- '<|im_end|>\n' }}
76
+ {%- else %}
77
+ {%- if messages[0].role == 'system' %}
78
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
79
+ {%- if content %}
80
+ {{- '<|im_start|>system\n' + (reasoning_instructions + '\n\n' if reasoning_instructions else '') + content + '<|im_end|>\n' }}
81
+ {%- elif reasoning_instructions %}
82
+ {{- '<|im_start|>system\n' + reasoning_instructions + '<|im_end|>\n' }}
83
+ {%- endif %}
84
+ {%- elif reasoning_instructions %}
85
+ {{- '<|im_start|>system\n' + reasoning_instructions + '<|im_end|>\n' }}
86
+ {%- endif %}
87
+ {%- endif %}
88
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
89
+ {%- for message in messages[::-1] %}
90
+ {%- set index = (messages|length - 1) - loop.index0 %}
91
+ {%- if ns.multi_step_tool and message.role == "user" %}
92
+ {%- set content = render_content(message.content, false)|trim %}
93
+ {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
94
+ {%- set ns.multi_step_tool = false %}
95
+ {%- set ns.last_query_index = index %}
96
+ {%- endif %}
97
+ {%- endif %}
98
+ {%- endfor %}
99
+ {%- if ns.multi_step_tool %}
100
+ {{- raise_exception('No user query found in messages.') }}
101
+ {%- endif %}
102
+ {%- for message in messages %}
103
+ {%- set content = render_content(message.content, true)|trim %}
104
+ {%- if message.role == "system" %}
105
+ {%- if not loop.first %}
106
+ {{- raise_exception('System message must be at the beginning.') }}
107
+ {%- endif %}
108
+ {%- elif message.role == "user" %}
109
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
110
+ {%- elif message.role == "assistant" %}
111
+ {%- set reasoning_content = '' %}
112
+ {%- if message.reasoning_content is string %}
113
+ {%- set reasoning_content = message.reasoning_content %}
114
+ {%- endif %}
115
+ {%- set reasoning_content = reasoning_content|trim %}
116
+ {%- if preserve_thinking is undefined or preserve_thinking is true or loop.index0 > ns.last_query_index %}
117
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
118
+ {%- else %}
119
+ {{- '<|im_start|>' + message.role + '\n' + content }}
120
+ {%- endif %}
121
+ {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
122
+ {%- for tool_call in message.tool_calls %}
123
+ {%- if tool_call.function is defined %}
124
+ {%- set tool_call = tool_call.function %}
125
+ {%- endif %}
126
+ {%- if loop.first %}
127
+ {%- if content|trim %}
128
+ {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
129
+ {%- else %}
130
+ {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
131
+ {%- endif %}
132
+ {%- else %}
133
+ {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
134
+ {%- endif %}
135
+ {%- if tool_call.arguments is defined and tool_call.arguments != '' %}
136
+ {%- for args_name, args_value in tool_call.arguments|items %}
137
+ {{- '<parameter=' + args_name + '>\n' }}
138
+ {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
139
+ {{- args_value }}
140
+ {{- '\n</parameter>\n' }}
141
+ {%- endfor %}
142
+ {%- endif %}
143
+ {{- '</function>\n</tool_call>' }}
144
+ {%- endfor %}
145
+ {%- endif %}
146
+ {{- '<|im_end|>\n' }}
147
+ {%- elif message.role == "tool" %}
148
+ {%- if loop.previtem and loop.previtem.role != "tool" %}
149
+ {{- '<|im_start|>user' }}
150
+ {%- endif %}
151
+ {{- '\n<tool_response>\n' }}
152
+ {{- content }}
153
+ {{- '\n</tool_response>' }}
154
+ {%- if not loop.last and loop.nextitem.role != "tool" %}
155
+ {{- '<|im_end|>\n' }}
156
+ {%- elif loop.last %}
157
+ {{- '<|im_end|>\n' }}
158
+ {%- endif %}
159
+ {%- else %}
160
+ {{- raise_exception('Unexpected message role.') }}
161
+ {%- endif %}
162
+ {%- endfor %}
163
+ {%- if add_generation_prompt %}
164
+ {{- '<|im_start|>assistant\n' }}
165
+ {%- if enable_thinking is defined and enable_thinking is false %}
166
+ {{- '<think>\n\n</think>\n\n' }}
167
+ {%- else %}
168
+ {{- '<think>\n' }}
169
+ {%- endif %}
170
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,1460 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_8FlashNextForConditionalGeneration"
4
+ ],
5
+ "image_token_id": 248056,
6
+ "language_model_only": false,
7
+ "model_type": "qwen3_8_flash_next",
8
+ "text_config": {
9
+ "attention_bias": false,
10
+ "attention_dropout": 0.0,
11
+ "bos_token_id": 248044,
12
+ "dtype": "bfloat16",
13
+ "eos_token_id": 248044,
14
+ "full_attention_interval": 4,
15
+ "hc_count": 4,
16
+ "hc_lowrank": 320,
17
+ "head_dim": 256,
18
+ "heads_per_ngram": 8,
19
+ "hidden_act": "silu",
20
+ "hidden_size": 2560,
21
+ "indexer_budget": 2048,
22
+ "indexer_compress_ratio": 4,
23
+ "indexer_head_dim": 128,
24
+ "indexer_kv_heads": 1,
25
+ "indexer_n_heads": 4,
26
+ "initializer_range": 0.02,
27
+ "layer_types": [
28
+ "linear_attention",
29
+ "linear_attention",
30
+ "linear_attention",
31
+ "full_attention",
32
+ "linear_attention",
33
+ "linear_attention",
34
+ "linear_attention",
35
+ "full_attention",
36
+ "linear_attention",
37
+ "linear_attention",
38
+ "linear_attention",
39
+ "full_attention",
40
+ "linear_attention",
41
+ "linear_attention",
42
+ "linear_attention",
43
+ "full_attention",
44
+ "linear_attention",
45
+ "linear_attention",
46
+ "linear_attention",
47
+ "full_attention",
48
+ "linear_attention",
49
+ "linear_attention",
50
+ "linear_attention",
51
+ "full_attention",
52
+ "linear_attention",
53
+ "linear_attention",
54
+ "linear_attention",
55
+ "full_attention",
56
+ "linear_attention",
57
+ "linear_attention",
58
+ "linear_attention",
59
+ "full_attention",
60
+ "linear_attention",
61
+ "linear_attention",
62
+ "linear_attention",
63
+ "full_attention",
64
+ "linear_attention",
65
+ "linear_attention",
66
+ "linear_attention",
67
+ "full_attention",
68
+ "linear_attention",
69
+ "linear_attention",
70
+ "linear_attention",
71
+ "full_attention",
72
+ "linear_attention",
73
+ "linear_attention",
74
+ "linear_attention",
75
+ "full_attention"
76
+ ],
77
+ "linear_conv_kernel_dim": 4,
78
+ "linear_key_head_dim": 128,
79
+ "linear_num_key_heads": 16,
80
+ "linear_num_value_heads": 48,
81
+ "linear_value_head_dim": 128,
82
+ "make_ngram_vocab_size_divisible_by": 128,
83
+ "mamba_ssm_dtype": "float32",
84
+ "max_position_embeddings": 262144,
85
+ "model_type": "qwen3_8_flash_next_text",
86
+ "moe_intermediate_size": 640,
87
+ "mtp": {
88
+ "hybrid": true,
89
+ "layer_types": [
90
+ "full_attention"
91
+ ],
92
+ "mtp_use_hidden_state_from_layer": null,
93
+ "num_hidden_layers": 1,
94
+ "rope_theta": 10000000
95
+ },
96
+ "mtp_num_hidden_layers": 1,
97
+ "mtp_use_dedicated_embeddings": false,
98
+ "ngram_size": 3,
99
+ "ngram_vocab_size_base": 20000000,
100
+ "num_attention_heads": 24,
101
+ "num_experts": 512,
102
+ "num_experts_per_tok": 10,
103
+ "num_hidden_layers": 48,
104
+ "num_key_value_heads": 2,
105
+ "output_gate_type": "sigmoid",
106
+ "output_router_logits": false,
107
+ "pad_token_id": null,
108
+ "partial_rotary_factor": 0.25,
109
+ "ple_conv_kernel_size": 4,
110
+ "ple_embed_dim": 2560,
111
+ "ple_layer_ids": [
112
+ 2
113
+ ],
114
+ "rms_norm_eps": 1e-06,
115
+ "rope_parameters": {
116
+ "mrope_interleaved": true,
117
+ "mrope_section": [
118
+ 11,
119
+ 11,
120
+ 10
121
+ ],
122
+ "partial_rotary_factor": 0.25,
123
+ "rope_theta": 10000000,
124
+ "rope_type": "default"
125
+ },
126
+ "router_aux_loss_coef": 0.001,
127
+ "shared_expert_intermediate_size": 640,
128
+ "split_ngram_parts": 128,
129
+ "tie_word_embeddings": false,
130
+ "use_cache": true,
131
+ "vocab_size": 248320
132
+ },
133
+ "tie_word_embeddings": false,
134
+ "transformers_version": "5.8.0.dev0",
135
+ "video_token_id": 248057,
136
+ "vision_config": {
137
+ "deepstack_visual_indexes": [],
138
+ "depth": 27,
139
+ "hidden_act": "gelu_pytorch_tanh",
140
+ "hidden_size": 1152,
141
+ "in_channels": 3,
142
+ "initializer_range": 0.02,
143
+ "intermediate_size": 4304,
144
+ "model_type": "qwen4_exp",
145
+ "num_heads": 16,
146
+ "num_position_embeddings": 2304,
147
+ "out_hidden_size": 2560,
148
+ "patch_size": 16,
149
+ "spatial_merge_size": 2,
150
+ "temporal_patch_size": 2
151
+ },
152
+ "vision_end_token_id": 248054,
153
+ "vision_start_token_id": 248053,
154
+ "quantization_config": {
155
+ "rotate": false,
156
+ "actorder": false,
157
+ "damp": 0.01,
158
+ "gptq_block_size": 128,
159
+ "calibration_applied": true,
160
+ "gptq_applied": false,
161
+ "gptq_reconstruction_rounds": 0,
162
+ "smoothquant_alpha": null,
163
+ "smoothquant_salient_ratio": 1.0,
164
+ "smoothquant_dualscale": false,
165
+ "smoothquant_dualscale_round": 1,
166
+ "mse_optimal_clipping": false,
167
+ "quarot_r1_fold": false,
168
+ "quarot_r1_fold_block_size": 32,
169
+ "learned_rotation": false,
170
+ "learned_rotation_objective": null,
171
+ "expert_block_reorder": false,
172
+ "hessian_aware_codec_search": false,
173
+ "cold_expert_hessian_shrinkage": false,
174
+ "gptq_reconstruction_scope": null,
175
+ "num_samples": 128,
176
+ "seq_len": 2048,
177
+ "batch_size": 1,
178
+ "quant_method": "modelopt",
179
+ "quant_algo": "NVFP4",
180
+ "group_size": 16,
181
+ "scale_search": false,
182
+ "activation_scale_search": false,
183
+ "weight_scale_2_search_factors": null,
184
+ "with_input_scale": true,
185
+ "input_scale_granularity": "per-tensor",
186
+ "input_scale_quantile": 0.9999,
187
+ "input_scale_calibration": "streaming_top_tail_4_5_6_proxy",
188
+ "mtp_input_scale_k": 4,
189
+ "mtp_input_scale_quantile": 0.95,
190
+ "ignore": [
191
+ "lm_head",
192
+ "model.language_model.embed_tokens",
193
+ "model.language_model.hyper_connection_mixer.hc_norm",
194
+ "model.language_model.hyper_connection_mixer.input_mix_weight_down",
195
+ "model.language_model.hyper_connection_mixer.input_mix_weight_up",
196
+ "model.language_model.layers.0.attn_hyper_connection.block_inject_weight",
197
+ "model.language_model.layers.0.attn_hyper_connection.hc_norm",
198
+ "model.language_model.layers.0.attn_hyper_connection.input_mix_weight_down",
199
+ "model.language_model.layers.0.attn_hyper_connection.input_mix_weight_up",
200
+ "model.language_model.layers.0.linear_attn.A_log",
201
+ "model.language_model.layers.0.linear_attn.conv1d",
202
+ "model.language_model.layers.0.linear_attn.dt_bias",
203
+ "model.language_model.layers.0.linear_attn.in_proj_a",
204
+ "model.language_model.layers.0.linear_attn.in_proj_b",
205
+ "model.language_model.layers.0.linear_attn.in_proj_qkv",
206
+ "model.language_model.layers.0.linear_attn.in_proj_z",
207
+ "model.language_model.layers.0.linear_attn.norm",
208
+ "model.language_model.layers.0.linear_attn.out_proj",
209
+ "model.language_model.layers.0.mlp.gate",
210
+ "model.language_model.layers.0.mlp.shared_expert.down_proj",
211
+ "model.language_model.layers.0.mlp.shared_expert.gate_proj",
212
+ "model.language_model.layers.0.mlp.shared_expert.up_proj",
213
+ "model.language_model.layers.0.mlp.shared_expert_gate",
214
+ "model.language_model.layers.0.mlp_hyper_connection.block_inject_weight",
215
+ "model.language_model.layers.0.mlp_hyper_connection.hc_norm",
216
+ "model.language_model.layers.0.mlp_hyper_connection.input_mix_weight_down",
217
+ "model.language_model.layers.0.mlp_hyper_connection.input_mix_weight_up",
218
+ "model.language_model.layers.1.attn_hyper_connection.block_inject_weight",
219
+ "model.language_model.layers.1.attn_hyper_connection.hc_norm",
220
+ "model.language_model.layers.1.attn_hyper_connection.input_mix_weight_down",
221
+ "model.language_model.layers.1.attn_hyper_connection.input_mix_weight_up",
222
+ "model.language_model.layers.1.linear_attn.A_log",
223
+ "model.language_model.layers.1.linear_attn.conv1d",
224
+ "model.language_model.layers.1.linear_attn.dt_bias",
225
+ "model.language_model.layers.1.linear_attn.in_proj_a",
226
+ "model.language_model.layers.1.linear_attn.in_proj_b",
227
+ "model.language_model.layers.1.linear_attn.in_proj_qkv",
228
+ "model.language_model.layers.1.linear_attn.in_proj_z",
229
+ "model.language_model.layers.1.linear_attn.norm",
230
+ "model.language_model.layers.1.linear_attn.out_proj",
231
+ "model.language_model.layers.1.mlp.gate",
232
+ "model.language_model.layers.1.mlp.shared_expert.down_proj",
233
+ "model.language_model.layers.1.mlp.shared_expert.gate_proj",
234
+ "model.language_model.layers.1.mlp.shared_expert.up_proj",
235
+ "model.language_model.layers.1.mlp.shared_expert_gate",
236
+ "model.language_model.layers.1.mlp_hyper_connection.block_inject_weight",
237
+ "model.language_model.layers.1.mlp_hyper_connection.hc_norm",
238
+ "model.language_model.layers.1.mlp_hyper_connection.input_mix_weight_down",
239
+ "model.language_model.layers.1.mlp_hyper_connection.input_mix_weight_up",
240
+ "model.language_model.layers.1.ple.conv1d",
241
+ "model.language_model.layers.1.ple.key_proj",
242
+ "model.language_model.layers.1.ple.norm_conv",
243
+ "model.language_model.layers.1.ple.norm_key",
244
+ "model.language_model.layers.1.ple.norm_query",
245
+ "model.language_model.layers.1.ple.ple_embedding.layer_multipliers",
246
+ "model.language_model.layers.1.ple.ple_embedding.ngram_embedding",
247
+ "model.language_model.layers.1.ple.ple_embedding.ngram_heads_offsets",
248
+ "model.language_model.layers.1.ple.ple_embedding.ngram_heads_vocab_sizes",
249
+ "model.language_model.layers.1.ple.value_proj",
250
+ "model.language_model.layers.10.attn_hyper_connection.block_inject_weight",
251
+ "model.language_model.layers.10.attn_hyper_connection.hc_norm",
252
+ "model.language_model.layers.10.attn_hyper_connection.input_mix_weight_down",
253
+ "model.language_model.layers.10.attn_hyper_connection.input_mix_weight_up",
254
+ "model.language_model.layers.10.linear_attn.A_log",
255
+ "model.language_model.layers.10.linear_attn.conv1d",
256
+ "model.language_model.layers.10.linear_attn.dt_bias",
257
+ "model.language_model.layers.10.linear_attn.in_proj_a",
258
+ "model.language_model.layers.10.linear_attn.in_proj_b",
259
+ "model.language_model.layers.10.linear_attn.in_proj_qkv",
260
+ "model.language_model.layers.10.linear_attn.in_proj_z",
261
+ "model.language_model.layers.10.linear_attn.norm",
262
+ "model.language_model.layers.10.linear_attn.out_proj",
263
+ "model.language_model.layers.10.mlp.gate",
264
+ "model.language_model.layers.10.mlp.shared_expert.down_proj",
265
+ "model.language_model.layers.10.mlp.shared_expert.gate_proj",
266
+ "model.language_model.layers.10.mlp.shared_expert.up_proj",
267
+ "model.language_model.layers.10.mlp.shared_expert_gate",
268
+ "model.language_model.layers.10.mlp_hyper_connection.block_inject_weight",
269
+ "model.language_model.layers.10.mlp_hyper_connection.hc_norm",
270
+ "model.language_model.layers.10.mlp_hyper_connection.input_mix_weight_down",
271
+ "model.language_model.layers.10.mlp_hyper_connection.input_mix_weight_up",
272
+ "model.language_model.layers.11.attn_hyper_connection.block_inject_weight",
273
+ "model.language_model.layers.11.attn_hyper_connection.hc_norm",
274
+ "model.language_model.layers.11.attn_hyper_connection.input_mix_weight_down",
275
+ "model.language_model.layers.11.attn_hyper_connection.input_mix_weight_up",
276
+ "model.language_model.layers.11.mlp.gate",
277
+ "model.language_model.layers.11.mlp.shared_expert.down_proj",
278
+ "model.language_model.layers.11.mlp.shared_expert.gate_proj",
279
+ "model.language_model.layers.11.mlp.shared_expert.up_proj",
280
+ "model.language_model.layers.11.mlp.shared_expert_gate",
281
+ "model.language_model.layers.11.mlp_hyper_connection.block_inject_weight",
282
+ "model.language_model.layers.11.mlp_hyper_connection.hc_norm",
283
+ "model.language_model.layers.11.mlp_hyper_connection.input_mix_weight_down",
284
+ "model.language_model.layers.11.mlp_hyper_connection.input_mix_weight_up",
285
+ "model.language_model.layers.11.self_attn.indexer.index_qk_proj",
286
+ "model.language_model.layers.11.self_attn.indexer.k_layernorm",
287
+ "model.language_model.layers.11.self_attn.indexer.q_layernorm",
288
+ "model.language_model.layers.11.self_attn.k_norm",
289
+ "model.language_model.layers.11.self_attn.k_proj",
290
+ "model.language_model.layers.11.self_attn.o_proj",
291
+ "model.language_model.layers.11.self_attn.q_norm",
292
+ "model.language_model.layers.11.self_attn.q_proj",
293
+ "model.language_model.layers.11.self_attn.v_proj",
294
+ "model.language_model.layers.12.attn_hyper_connection.block_inject_weight",
295
+ "model.language_model.layers.12.attn_hyper_connection.hc_norm",
296
+ "model.language_model.layers.12.attn_hyper_connection.input_mix_weight_down",
297
+ "model.language_model.layers.12.attn_hyper_connection.input_mix_weight_up",
298
+ "model.language_model.layers.12.linear_attn.A_log",
299
+ "model.language_model.layers.12.linear_attn.conv1d",
300
+ "model.language_model.layers.12.linear_attn.dt_bias",
301
+ "model.language_model.layers.12.linear_attn.in_proj_a",
302
+ "model.language_model.layers.12.linear_attn.in_proj_b",
303
+ "model.language_model.layers.12.linear_attn.in_proj_qkv",
304
+ "model.language_model.layers.12.linear_attn.in_proj_z",
305
+ "model.language_model.layers.12.linear_attn.norm",
306
+ "model.language_model.layers.12.linear_attn.out_proj",
307
+ "model.language_model.layers.12.mlp.gate",
308
+ "model.language_model.layers.12.mlp.shared_expert.down_proj",
309
+ "model.language_model.layers.12.mlp.shared_expert.gate_proj",
310
+ "model.language_model.layers.12.mlp.shared_expert.up_proj",
311
+ "model.language_model.layers.12.mlp.shared_expert_gate",
312
+ "model.language_model.layers.12.mlp_hyper_connection.block_inject_weight",
313
+ "model.language_model.layers.12.mlp_hyper_connection.hc_norm",
314
+ "model.language_model.layers.12.mlp_hyper_connection.input_mix_weight_down",
315
+ "model.language_model.layers.12.mlp_hyper_connection.input_mix_weight_up",
316
+ "model.language_model.layers.13.attn_hyper_connection.block_inject_weight",
317
+ "model.language_model.layers.13.attn_hyper_connection.hc_norm",
318
+ "model.language_model.layers.13.attn_hyper_connection.input_mix_weight_down",
319
+ "model.language_model.layers.13.attn_hyper_connection.input_mix_weight_up",
320
+ "model.language_model.layers.13.linear_attn.A_log",
321
+ "model.language_model.layers.13.linear_attn.conv1d",
322
+ "model.language_model.layers.13.linear_attn.dt_bias",
323
+ "model.language_model.layers.13.linear_attn.in_proj_a",
324
+ "model.language_model.layers.13.linear_attn.in_proj_b",
325
+ "model.language_model.layers.13.linear_attn.in_proj_qkv",
326
+ "model.language_model.layers.13.linear_attn.in_proj_z",
327
+ "model.language_model.layers.13.linear_attn.norm",
328
+ "model.language_model.layers.13.linear_attn.out_proj",
329
+ "model.language_model.layers.13.mlp.gate",
330
+ "model.language_model.layers.13.mlp.shared_expert.down_proj",
331
+ "model.language_model.layers.13.mlp.shared_expert.gate_proj",
332
+ "model.language_model.layers.13.mlp.shared_expert.up_proj",
333
+ "model.language_model.layers.13.mlp.shared_expert_gate",
334
+ "model.language_model.layers.13.mlp_hyper_connection.block_inject_weight",
335
+ "model.language_model.layers.13.mlp_hyper_connection.hc_norm",
336
+ "model.language_model.layers.13.mlp_hyper_connection.input_mix_weight_down",
337
+ "model.language_model.layers.13.mlp_hyper_connection.input_mix_weight_up",
338
+ "model.language_model.layers.14.attn_hyper_connection.block_inject_weight",
339
+ "model.language_model.layers.14.attn_hyper_connection.hc_norm",
340
+ "model.language_model.layers.14.attn_hyper_connection.input_mix_weight_down",
341
+ "model.language_model.layers.14.attn_hyper_connection.input_mix_weight_up",
342
+ "model.language_model.layers.14.linear_attn.A_log",
343
+ "model.language_model.layers.14.linear_attn.conv1d",
344
+ "model.language_model.layers.14.linear_attn.dt_bias",
345
+ "model.language_model.layers.14.linear_attn.in_proj_a",
346
+ "model.language_model.layers.14.linear_attn.in_proj_b",
347
+ "model.language_model.layers.14.linear_attn.in_proj_qkv",
348
+ "model.language_model.layers.14.linear_attn.in_proj_z",
349
+ "model.language_model.layers.14.linear_attn.norm",
350
+ "model.language_model.layers.14.linear_attn.out_proj",
351
+ "model.language_model.layers.14.mlp.gate",
352
+ "model.language_model.layers.14.mlp.shared_expert.down_proj",
353
+ "model.language_model.layers.14.mlp.shared_expert.gate_proj",
354
+ "model.language_model.layers.14.mlp.shared_expert.up_proj",
355
+ "model.language_model.layers.14.mlp.shared_expert_gate",
356
+ "model.language_model.layers.14.mlp_hyper_connection.block_inject_weight",
357
+ "model.language_model.layers.14.mlp_hyper_connection.hc_norm",
358
+ "model.language_model.layers.14.mlp_hyper_connection.input_mix_weight_down",
359
+ "model.language_model.layers.14.mlp_hyper_connection.input_mix_weight_up",
360
+ "model.language_model.layers.15.attn_hyper_connection.block_inject_weight",
361
+ "model.language_model.layers.15.attn_hyper_connection.hc_norm",
362
+ "model.language_model.layers.15.attn_hyper_connection.input_mix_weight_down",
363
+ "model.language_model.layers.15.attn_hyper_connection.input_mix_weight_up",
364
+ "model.language_model.layers.15.mlp.gate",
365
+ "model.language_model.layers.15.mlp.shared_expert.down_proj",
366
+ "model.language_model.layers.15.mlp.shared_expert.gate_proj",
367
+ "model.language_model.layers.15.mlp.shared_expert.up_proj",
368
+ "model.language_model.layers.15.mlp.shared_expert_gate",
369
+ "model.language_model.layers.15.mlp_hyper_connection.block_inject_weight",
370
+ "model.language_model.layers.15.mlp_hyper_connection.hc_norm",
371
+ "model.language_model.layers.15.mlp_hyper_connection.input_mix_weight_down",
372
+ "model.language_model.layers.15.mlp_hyper_connection.input_mix_weight_up",
373
+ "model.language_model.layers.15.self_attn.indexer.index_qk_proj",
374
+ "model.language_model.layers.15.self_attn.indexer.k_layernorm",
375
+ "model.language_model.layers.15.self_attn.indexer.q_layernorm",
376
+ "model.language_model.layers.15.self_attn.k_norm",
377
+ "model.language_model.layers.15.self_attn.k_proj",
378
+ "model.language_model.layers.15.self_attn.o_proj",
379
+ "model.language_model.layers.15.self_attn.q_norm",
380
+ "model.language_model.layers.15.self_attn.q_proj",
381
+ "model.language_model.layers.15.self_attn.v_proj",
382
+ "model.language_model.layers.16.attn_hyper_connection.block_inject_weight",
383
+ "model.language_model.layers.16.attn_hyper_connection.hc_norm",
384
+ "model.language_model.layers.16.attn_hyper_connection.input_mix_weight_down",
385
+ "model.language_model.layers.16.attn_hyper_connection.input_mix_weight_up",
386
+ "model.language_model.layers.16.linear_attn.A_log",
387
+ "model.language_model.layers.16.linear_attn.conv1d",
388
+ "model.language_model.layers.16.linear_attn.dt_bias",
389
+ "model.language_model.layers.16.linear_attn.in_proj_a",
390
+ "model.language_model.layers.16.linear_attn.in_proj_b",
391
+ "model.language_model.layers.16.linear_attn.in_proj_qkv",
392
+ "model.language_model.layers.16.linear_attn.in_proj_z",
393
+ "model.language_model.layers.16.linear_attn.norm",
394
+ "model.language_model.layers.16.linear_attn.out_proj",
395
+ "model.language_model.layers.16.mlp.gate",
396
+ "model.language_model.layers.16.mlp.shared_expert.down_proj",
397
+ "model.language_model.layers.16.mlp.shared_expert.gate_proj",
398
+ "model.language_model.layers.16.mlp.shared_expert.up_proj",
399
+ "model.language_model.layers.16.mlp.shared_expert_gate",
400
+ "model.language_model.layers.16.mlp_hyper_connection.block_inject_weight",
401
+ "model.language_model.layers.16.mlp_hyper_connection.hc_norm",
402
+ "model.language_model.layers.16.mlp_hyper_connection.input_mix_weight_down",
403
+ "model.language_model.layers.16.mlp_hyper_connection.input_mix_weight_up",
404
+ "model.language_model.layers.17.attn_hyper_connection.block_inject_weight",
405
+ "model.language_model.layers.17.attn_hyper_connection.hc_norm",
406
+ "model.language_model.layers.17.attn_hyper_connection.input_mix_weight_down",
407
+ "model.language_model.layers.17.attn_hyper_connection.input_mix_weight_up",
408
+ "model.language_model.layers.17.linear_attn.A_log",
409
+ "model.language_model.layers.17.linear_attn.conv1d",
410
+ "model.language_model.layers.17.linear_attn.dt_bias",
411
+ "model.language_model.layers.17.linear_attn.in_proj_a",
412
+ "model.language_model.layers.17.linear_attn.in_proj_b",
413
+ "model.language_model.layers.17.linear_attn.in_proj_qkv",
414
+ "model.language_model.layers.17.linear_attn.in_proj_z",
415
+ "model.language_model.layers.17.linear_attn.norm",
416
+ "model.language_model.layers.17.linear_attn.out_proj",
417
+ "model.language_model.layers.17.mlp.gate",
418
+ "model.language_model.layers.17.mlp.shared_expert.down_proj",
419
+ "model.language_model.layers.17.mlp.shared_expert.gate_proj",
420
+ "model.language_model.layers.17.mlp.shared_expert.up_proj",
421
+ "model.language_model.layers.17.mlp.shared_expert_gate",
422
+ "model.language_model.layers.17.mlp_hyper_connection.block_inject_weight",
423
+ "model.language_model.layers.17.mlp_hyper_connection.hc_norm",
424
+ "model.language_model.layers.17.mlp_hyper_connection.input_mix_weight_down",
425
+ "model.language_model.layers.17.mlp_hyper_connection.input_mix_weight_up",
426
+ "model.language_model.layers.18.attn_hyper_connection.block_inject_weight",
427
+ "model.language_model.layers.18.attn_hyper_connection.hc_norm",
428
+ "model.language_model.layers.18.attn_hyper_connection.input_mix_weight_down",
429
+ "model.language_model.layers.18.attn_hyper_connection.input_mix_weight_up",
430
+ "model.language_model.layers.18.linear_attn.A_log",
431
+ "model.language_model.layers.18.linear_attn.conv1d",
432
+ "model.language_model.layers.18.linear_attn.dt_bias",
433
+ "model.language_model.layers.18.linear_attn.in_proj_a",
434
+ "model.language_model.layers.18.linear_attn.in_proj_b",
435
+ "model.language_model.layers.18.linear_attn.in_proj_qkv",
436
+ "model.language_model.layers.18.linear_attn.in_proj_z",
437
+ "model.language_model.layers.18.linear_attn.norm",
438
+ "model.language_model.layers.18.linear_attn.out_proj",
439
+ "model.language_model.layers.18.mlp.gate",
440
+ "model.language_model.layers.18.mlp.shared_expert.down_proj",
441
+ "model.language_model.layers.18.mlp.shared_expert.gate_proj",
442
+ "model.language_model.layers.18.mlp.shared_expert.up_proj",
443
+ "model.language_model.layers.18.mlp.shared_expert_gate",
444
+ "model.language_model.layers.18.mlp_hyper_connection.block_inject_weight",
445
+ "model.language_model.layers.18.mlp_hyper_connection.hc_norm",
446
+ "model.language_model.layers.18.mlp_hyper_connection.input_mix_weight_down",
447
+ "model.language_model.layers.18.mlp_hyper_connection.input_mix_weight_up",
448
+ "model.language_model.layers.19.attn_hyper_connection.block_inject_weight",
449
+ "model.language_model.layers.19.attn_hyper_connection.hc_norm",
450
+ "model.language_model.layers.19.attn_hyper_connection.input_mix_weight_down",
451
+ "model.language_model.layers.19.attn_hyper_connection.input_mix_weight_up",
452
+ "model.language_model.layers.19.mlp.gate",
453
+ "model.language_model.layers.19.mlp.shared_expert.down_proj",
454
+ "model.language_model.layers.19.mlp.shared_expert.gate_proj",
455
+ "model.language_model.layers.19.mlp.shared_expert.up_proj",
456
+ "model.language_model.layers.19.mlp.shared_expert_gate",
457
+ "model.language_model.layers.19.mlp_hyper_connection.block_inject_weight",
458
+ "model.language_model.layers.19.mlp_hyper_connection.hc_norm",
459
+ "model.language_model.layers.19.mlp_hyper_connection.input_mix_weight_down",
460
+ "model.language_model.layers.19.mlp_hyper_connection.input_mix_weight_up",
461
+ "model.language_model.layers.19.self_attn.indexer.index_qk_proj",
462
+ "model.language_model.layers.19.self_attn.indexer.k_layernorm",
463
+ "model.language_model.layers.19.self_attn.indexer.q_layernorm",
464
+ "model.language_model.layers.19.self_attn.k_norm",
465
+ "model.language_model.layers.19.self_attn.k_proj",
466
+ "model.language_model.layers.19.self_attn.o_proj",
467
+ "model.language_model.layers.19.self_attn.q_norm",
468
+ "model.language_model.layers.19.self_attn.q_proj",
469
+ "model.language_model.layers.19.self_attn.v_proj",
470
+ "model.language_model.layers.2.attn_hyper_connection.block_inject_weight",
471
+ "model.language_model.layers.2.attn_hyper_connection.hc_norm",
472
+ "model.language_model.layers.2.attn_hyper_connection.input_mix_weight_down",
473
+ "model.language_model.layers.2.attn_hyper_connection.input_mix_weight_up",
474
+ "model.language_model.layers.2.linear_attn.A_log",
475
+ "model.language_model.layers.2.linear_attn.conv1d",
476
+ "model.language_model.layers.2.linear_attn.dt_bias",
477
+ "model.language_model.layers.2.linear_attn.in_proj_a",
478
+ "model.language_model.layers.2.linear_attn.in_proj_b",
479
+ "model.language_model.layers.2.linear_attn.in_proj_qkv",
480
+ "model.language_model.layers.2.linear_attn.in_proj_z",
481
+ "model.language_model.layers.2.linear_attn.norm",
482
+ "model.language_model.layers.2.linear_attn.out_proj",
483
+ "model.language_model.layers.2.mlp.gate",
484
+ "model.language_model.layers.2.mlp.shared_expert.down_proj",
485
+ "model.language_model.layers.2.mlp.shared_expert.gate_proj",
486
+ "model.language_model.layers.2.mlp.shared_expert.up_proj",
487
+ "model.language_model.layers.2.mlp.shared_expert_gate",
488
+ "model.language_model.layers.2.mlp_hyper_connection.block_inject_weight",
489
+ "model.language_model.layers.2.mlp_hyper_connection.hc_norm",
490
+ "model.language_model.layers.2.mlp_hyper_connection.input_mix_weight_down",
491
+ "model.language_model.layers.2.mlp_hyper_connection.input_mix_weight_up",
492
+ "model.language_model.layers.20.attn_hyper_connection.block_inject_weight",
493
+ "model.language_model.layers.20.attn_hyper_connection.hc_norm",
494
+ "model.language_model.layers.20.attn_hyper_connection.input_mix_weight_down",
495
+ "model.language_model.layers.20.attn_hyper_connection.input_mix_weight_up",
496
+ "model.language_model.layers.20.linear_attn.A_log",
497
+ "model.language_model.layers.20.linear_attn.conv1d",
498
+ "model.language_model.layers.20.linear_attn.dt_bias",
499
+ "model.language_model.layers.20.linear_attn.in_proj_a",
500
+ "model.language_model.layers.20.linear_attn.in_proj_b",
501
+ "model.language_model.layers.20.linear_attn.in_proj_qkv",
502
+ "model.language_model.layers.20.linear_attn.in_proj_z",
503
+ "model.language_model.layers.20.linear_attn.norm",
504
+ "model.language_model.layers.20.linear_attn.out_proj",
505
+ "model.language_model.layers.20.mlp.gate",
506
+ "model.language_model.layers.20.mlp.shared_expert.down_proj",
507
+ "model.language_model.layers.20.mlp.shared_expert.gate_proj",
508
+ "model.language_model.layers.20.mlp.shared_expert.up_proj",
509
+ "model.language_model.layers.20.mlp.shared_expert_gate",
510
+ "model.language_model.layers.20.mlp_hyper_connection.block_inject_weight",
511
+ "model.language_model.layers.20.mlp_hyper_connection.hc_norm",
512
+ "model.language_model.layers.20.mlp_hyper_connection.input_mix_weight_down",
513
+ "model.language_model.layers.20.mlp_hyper_connection.input_mix_weight_up",
514
+ "model.language_model.layers.21.attn_hyper_connection.block_inject_weight",
515
+ "model.language_model.layers.21.attn_hyper_connection.hc_norm",
516
+ "model.language_model.layers.21.attn_hyper_connection.input_mix_weight_down",
517
+ "model.language_model.layers.21.attn_hyper_connection.input_mix_weight_up",
518
+ "model.language_model.layers.21.linear_attn.A_log",
519
+ "model.language_model.layers.21.linear_attn.conv1d",
520
+ "model.language_model.layers.21.linear_attn.dt_bias",
521
+ "model.language_model.layers.21.linear_attn.in_proj_a",
522
+ "model.language_model.layers.21.linear_attn.in_proj_b",
523
+ "model.language_model.layers.21.linear_attn.in_proj_qkv",
524
+ "model.language_model.layers.21.linear_attn.in_proj_z",
525
+ "model.language_model.layers.21.linear_attn.norm",
526
+ "model.language_model.layers.21.linear_attn.out_proj",
527
+ "model.language_model.layers.21.mlp.gate",
528
+ "model.language_model.layers.21.mlp.shared_expert.down_proj",
529
+ "model.language_model.layers.21.mlp.shared_expert.gate_proj",
530
+ "model.language_model.layers.21.mlp.shared_expert.up_proj",
531
+ "model.language_model.layers.21.mlp.shared_expert_gate",
532
+ "model.language_model.layers.21.mlp_hyper_connection.block_inject_weight",
533
+ "model.language_model.layers.21.mlp_hyper_connection.hc_norm",
534
+ "model.language_model.layers.21.mlp_hyper_connection.input_mix_weight_down",
535
+ "model.language_model.layers.21.mlp_hyper_connection.input_mix_weight_up",
536
+ "model.language_model.layers.22.attn_hyper_connection.block_inject_weight",
537
+ "model.language_model.layers.22.attn_hyper_connection.hc_norm",
538
+ "model.language_model.layers.22.attn_hyper_connection.input_mix_weight_down",
539
+ "model.language_model.layers.22.attn_hyper_connection.input_mix_weight_up",
540
+ "model.language_model.layers.22.linear_attn.A_log",
541
+ "model.language_model.layers.22.linear_attn.conv1d",
542
+ "model.language_model.layers.22.linear_attn.dt_bias",
543
+ "model.language_model.layers.22.linear_attn.in_proj_a",
544
+ "model.language_model.layers.22.linear_attn.in_proj_b",
545
+ "model.language_model.layers.22.linear_attn.in_proj_qkv",
546
+ "model.language_model.layers.22.linear_attn.in_proj_z",
547
+ "model.language_model.layers.22.linear_attn.norm",
548
+ "model.language_model.layers.22.linear_attn.out_proj",
549
+ "model.language_model.layers.22.mlp.gate",
550
+ "model.language_model.layers.22.mlp.shared_expert.down_proj",
551
+ "model.language_model.layers.22.mlp.shared_expert.gate_proj",
552
+ "model.language_model.layers.22.mlp.shared_expert.up_proj",
553
+ "model.language_model.layers.22.mlp.shared_expert_gate",
554
+ "model.language_model.layers.22.mlp_hyper_connection.block_inject_weight",
555
+ "model.language_model.layers.22.mlp_hyper_connection.hc_norm",
556
+ "model.language_model.layers.22.mlp_hyper_connection.input_mix_weight_down",
557
+ "model.language_model.layers.22.mlp_hyper_connection.input_mix_weight_up",
558
+ "model.language_model.layers.23.attn_hyper_connection.block_inject_weight",
559
+ "model.language_model.layers.23.attn_hyper_connection.hc_norm",
560
+ "model.language_model.layers.23.attn_hyper_connection.input_mix_weight_down",
561
+ "model.language_model.layers.23.attn_hyper_connection.input_mix_weight_up",
562
+ "model.language_model.layers.23.mlp.gate",
563
+ "model.language_model.layers.23.mlp.shared_expert.down_proj",
564
+ "model.language_model.layers.23.mlp.shared_expert.gate_proj",
565
+ "model.language_model.layers.23.mlp.shared_expert.up_proj",
566
+ "model.language_model.layers.23.mlp.shared_expert_gate",
567
+ "model.language_model.layers.23.mlp_hyper_connection.block_inject_weight",
568
+ "model.language_model.layers.23.mlp_hyper_connection.hc_norm",
569
+ "model.language_model.layers.23.mlp_hyper_connection.input_mix_weight_down",
570
+ "model.language_model.layers.23.mlp_hyper_connection.input_mix_weight_up",
571
+ "model.language_model.layers.23.self_attn.indexer.index_qk_proj",
572
+ "model.language_model.layers.23.self_attn.indexer.k_layernorm",
573
+ "model.language_model.layers.23.self_attn.indexer.q_layernorm",
574
+ "model.language_model.layers.23.self_attn.k_norm",
575
+ "model.language_model.layers.23.self_attn.k_proj",
576
+ "model.language_model.layers.23.self_attn.o_proj",
577
+ "model.language_model.layers.23.self_attn.q_norm",
578
+ "model.language_model.layers.23.self_attn.q_proj",
579
+ "model.language_model.layers.23.self_attn.v_proj",
580
+ "model.language_model.layers.24.attn_hyper_connection.block_inject_weight",
581
+ "model.language_model.layers.24.attn_hyper_connection.hc_norm",
582
+ "model.language_model.layers.24.attn_hyper_connection.input_mix_weight_down",
583
+ "model.language_model.layers.24.attn_hyper_connection.input_mix_weight_up",
584
+ "model.language_model.layers.24.linear_attn.A_log",
585
+ "model.language_model.layers.24.linear_attn.conv1d",
586
+ "model.language_model.layers.24.linear_attn.dt_bias",
587
+ "model.language_model.layers.24.linear_attn.in_proj_a",
588
+ "model.language_model.layers.24.linear_attn.in_proj_b",
589
+ "model.language_model.layers.24.linear_attn.in_proj_qkv",
590
+ "model.language_model.layers.24.linear_attn.in_proj_z",
591
+ "model.language_model.layers.24.linear_attn.norm",
592
+ "model.language_model.layers.24.linear_attn.out_proj",
593
+ "model.language_model.layers.24.mlp.gate",
594
+ "model.language_model.layers.24.mlp.shared_expert.down_proj",
595
+ "model.language_model.layers.24.mlp.shared_expert.gate_proj",
596
+ "model.language_model.layers.24.mlp.shared_expert.up_proj",
597
+ "model.language_model.layers.24.mlp.shared_expert_gate",
598
+ "model.language_model.layers.24.mlp_hyper_connection.block_inject_weight",
599
+ "model.language_model.layers.24.mlp_hyper_connection.hc_norm",
600
+ "model.language_model.layers.24.mlp_hyper_connection.input_mix_weight_down",
601
+ "model.language_model.layers.24.mlp_hyper_connection.input_mix_weight_up",
602
+ "model.language_model.layers.25.attn_hyper_connection.block_inject_weight",
603
+ "model.language_model.layers.25.attn_hyper_connection.hc_norm",
604
+ "model.language_model.layers.25.attn_hyper_connection.input_mix_weight_down",
605
+ "model.language_model.layers.25.attn_hyper_connection.input_mix_weight_up",
606
+ "model.language_model.layers.25.linear_attn.A_log",
607
+ "model.language_model.layers.25.linear_attn.conv1d",
608
+ "model.language_model.layers.25.linear_attn.dt_bias",
609
+ "model.language_model.layers.25.linear_attn.in_proj_a",
610
+ "model.language_model.layers.25.linear_attn.in_proj_b",
611
+ "model.language_model.layers.25.linear_attn.in_proj_qkv",
612
+ "model.language_model.layers.25.linear_attn.in_proj_z",
613
+ "model.language_model.layers.25.linear_attn.norm",
614
+ "model.language_model.layers.25.linear_attn.out_proj",
615
+ "model.language_model.layers.25.mlp.gate",
616
+ "model.language_model.layers.25.mlp.shared_expert.down_proj",
617
+ "model.language_model.layers.25.mlp.shared_expert.gate_proj",
618
+ "model.language_model.layers.25.mlp.shared_expert.up_proj",
619
+ "model.language_model.layers.25.mlp.shared_expert_gate",
620
+ "model.language_model.layers.25.mlp_hyper_connection.block_inject_weight",
621
+ "model.language_model.layers.25.mlp_hyper_connection.hc_norm",
622
+ "model.language_model.layers.25.mlp_hyper_connection.input_mix_weight_down",
623
+ "model.language_model.layers.25.mlp_hyper_connection.input_mix_weight_up",
624
+ "model.language_model.layers.26.attn_hyper_connection.block_inject_weight",
625
+ "model.language_model.layers.26.attn_hyper_connection.hc_norm",
626
+ "model.language_model.layers.26.attn_hyper_connection.input_mix_weight_down",
627
+ "model.language_model.layers.26.attn_hyper_connection.input_mix_weight_up",
628
+ "model.language_model.layers.26.linear_attn.A_log",
629
+ "model.language_model.layers.26.linear_attn.conv1d",
630
+ "model.language_model.layers.26.linear_attn.dt_bias",
631
+ "model.language_model.layers.26.linear_attn.in_proj_a",
632
+ "model.language_model.layers.26.linear_attn.in_proj_b",
633
+ "model.language_model.layers.26.linear_attn.in_proj_qkv",
634
+ "model.language_model.layers.26.linear_attn.in_proj_z",
635
+ "model.language_model.layers.26.linear_attn.norm",
636
+ "model.language_model.layers.26.linear_attn.out_proj",
637
+ "model.language_model.layers.26.mlp.gate",
638
+ "model.language_model.layers.26.mlp.shared_expert.down_proj",
639
+ "model.language_model.layers.26.mlp.shared_expert.gate_proj",
640
+ "model.language_model.layers.26.mlp.shared_expert.up_proj",
641
+ "model.language_model.layers.26.mlp.shared_expert_gate",
642
+ "model.language_model.layers.26.mlp_hyper_connection.block_inject_weight",
643
+ "model.language_model.layers.26.mlp_hyper_connection.hc_norm",
644
+ "model.language_model.layers.26.mlp_hyper_connection.input_mix_weight_down",
645
+ "model.language_model.layers.26.mlp_hyper_connection.input_mix_weight_up",
646
+ "model.language_model.layers.27.attn_hyper_connection.block_inject_weight",
647
+ "model.language_model.layers.27.attn_hyper_connection.hc_norm",
648
+ "model.language_model.layers.27.attn_hyper_connection.input_mix_weight_down",
649
+ "model.language_model.layers.27.attn_hyper_connection.input_mix_weight_up",
650
+ "model.language_model.layers.27.mlp.gate",
651
+ "model.language_model.layers.27.mlp.shared_expert.down_proj",
652
+ "model.language_model.layers.27.mlp.shared_expert.gate_proj",
653
+ "model.language_model.layers.27.mlp.shared_expert.up_proj",
654
+ "model.language_model.layers.27.mlp.shared_expert_gate",
655
+ "model.language_model.layers.27.mlp_hyper_connection.block_inject_weight",
656
+ "model.language_model.layers.27.mlp_hyper_connection.hc_norm",
657
+ "model.language_model.layers.27.mlp_hyper_connection.input_mix_weight_down",
658
+ "model.language_model.layers.27.mlp_hyper_connection.input_mix_weight_up",
659
+ "model.language_model.layers.27.self_attn.indexer.index_qk_proj",
660
+ "model.language_model.layers.27.self_attn.indexer.k_layernorm",
661
+ "model.language_model.layers.27.self_attn.indexer.q_layernorm",
662
+ "model.language_model.layers.27.self_attn.k_norm",
663
+ "model.language_model.layers.27.self_attn.k_proj",
664
+ "model.language_model.layers.27.self_attn.o_proj",
665
+ "model.language_model.layers.27.self_attn.q_norm",
666
+ "model.language_model.layers.27.self_attn.q_proj",
667
+ "model.language_model.layers.27.self_attn.v_proj",
668
+ "model.language_model.layers.28.attn_hyper_connection.block_inject_weight",
669
+ "model.language_model.layers.28.attn_hyper_connection.hc_norm",
670
+ "model.language_model.layers.28.attn_hyper_connection.input_mix_weight_down",
671
+ "model.language_model.layers.28.attn_hyper_connection.input_mix_weight_up",
672
+ "model.language_model.layers.28.linear_attn.A_log",
673
+ "model.language_model.layers.28.linear_attn.conv1d",
674
+ "model.language_model.layers.28.linear_attn.dt_bias",
675
+ "model.language_model.layers.28.linear_attn.in_proj_a",
676
+ "model.language_model.layers.28.linear_attn.in_proj_b",
677
+ "model.language_model.layers.28.linear_attn.in_proj_qkv",
678
+ "model.language_model.layers.28.linear_attn.in_proj_z",
679
+ "model.language_model.layers.28.linear_attn.norm",
680
+ "model.language_model.layers.28.linear_attn.out_proj",
681
+ "model.language_model.layers.28.mlp.gate",
682
+ "model.language_model.layers.28.mlp.shared_expert.down_proj",
683
+ "model.language_model.layers.28.mlp.shared_expert.gate_proj",
684
+ "model.language_model.layers.28.mlp.shared_expert.up_proj",
685
+ "model.language_model.layers.28.mlp.shared_expert_gate",
686
+ "model.language_model.layers.28.mlp_hyper_connection.block_inject_weight",
687
+ "model.language_model.layers.28.mlp_hyper_connection.hc_norm",
688
+ "model.language_model.layers.28.mlp_hyper_connection.input_mix_weight_down",
689
+ "model.language_model.layers.28.mlp_hyper_connection.input_mix_weight_up",
690
+ "model.language_model.layers.29.attn_hyper_connection.block_inject_weight",
691
+ "model.language_model.layers.29.attn_hyper_connection.hc_norm",
692
+ "model.language_model.layers.29.attn_hyper_connection.input_mix_weight_down",
693
+ "model.language_model.layers.29.attn_hyper_connection.input_mix_weight_up",
694
+ "model.language_model.layers.29.linear_attn.A_log",
695
+ "model.language_model.layers.29.linear_attn.conv1d",
696
+ "model.language_model.layers.29.linear_attn.dt_bias",
697
+ "model.language_model.layers.29.linear_attn.in_proj_a",
698
+ "model.language_model.layers.29.linear_attn.in_proj_b",
699
+ "model.language_model.layers.29.linear_attn.in_proj_qkv",
700
+ "model.language_model.layers.29.linear_attn.in_proj_z",
701
+ "model.language_model.layers.29.linear_attn.norm",
702
+ "model.language_model.layers.29.linear_attn.out_proj",
703
+ "model.language_model.layers.29.mlp.gate",
704
+ "model.language_model.layers.29.mlp.shared_expert.down_proj",
705
+ "model.language_model.layers.29.mlp.shared_expert.gate_proj",
706
+ "model.language_model.layers.29.mlp.shared_expert.up_proj",
707
+ "model.language_model.layers.29.mlp.shared_expert_gate",
708
+ "model.language_model.layers.29.mlp_hyper_connection.block_inject_weight",
709
+ "model.language_model.layers.29.mlp_hyper_connection.hc_norm",
710
+ "model.language_model.layers.29.mlp_hyper_connection.input_mix_weight_down",
711
+ "model.language_model.layers.29.mlp_hyper_connection.input_mix_weight_up",
712
+ "model.language_model.layers.3.attn_hyper_connection.block_inject_weight",
713
+ "model.language_model.layers.3.attn_hyper_connection.hc_norm",
714
+ "model.language_model.layers.3.attn_hyper_connection.input_mix_weight_down",
715
+ "model.language_model.layers.3.attn_hyper_connection.input_mix_weight_up",
716
+ "model.language_model.layers.3.mlp.gate",
717
+ "model.language_model.layers.3.mlp.shared_expert.down_proj",
718
+ "model.language_model.layers.3.mlp.shared_expert.gate_proj",
719
+ "model.language_model.layers.3.mlp.shared_expert.up_proj",
720
+ "model.language_model.layers.3.mlp.shared_expert_gate",
721
+ "model.language_model.layers.3.mlp_hyper_connection.block_inject_weight",
722
+ "model.language_model.layers.3.mlp_hyper_connection.hc_norm",
723
+ "model.language_model.layers.3.mlp_hyper_connection.input_mix_weight_down",
724
+ "model.language_model.layers.3.mlp_hyper_connection.input_mix_weight_up",
725
+ "model.language_model.layers.3.self_attn.indexer.index_qk_proj",
726
+ "model.language_model.layers.3.self_attn.indexer.k_layernorm",
727
+ "model.language_model.layers.3.self_attn.indexer.q_layernorm",
728
+ "model.language_model.layers.3.self_attn.k_norm",
729
+ "model.language_model.layers.3.self_attn.k_proj",
730
+ "model.language_model.layers.3.self_attn.o_proj",
731
+ "model.language_model.layers.3.self_attn.q_norm",
732
+ "model.language_model.layers.3.self_attn.q_proj",
733
+ "model.language_model.layers.3.self_attn.v_proj",
734
+ "model.language_model.layers.30.attn_hyper_connection.block_inject_weight",
735
+ "model.language_model.layers.30.attn_hyper_connection.hc_norm",
736
+ "model.language_model.layers.30.attn_hyper_connection.input_mix_weight_down",
737
+ "model.language_model.layers.30.attn_hyper_connection.input_mix_weight_up",
738
+ "model.language_model.layers.30.linear_attn.A_log",
739
+ "model.language_model.layers.30.linear_attn.conv1d",
740
+ "model.language_model.layers.30.linear_attn.dt_bias",
741
+ "model.language_model.layers.30.linear_attn.in_proj_a",
742
+ "model.language_model.layers.30.linear_attn.in_proj_b",
743
+ "model.language_model.layers.30.linear_attn.in_proj_qkv",
744
+ "model.language_model.layers.30.linear_attn.in_proj_z",
745
+ "model.language_model.layers.30.linear_attn.norm",
746
+ "model.language_model.layers.30.linear_attn.out_proj",
747
+ "model.language_model.layers.30.mlp.gate",
748
+ "model.language_model.layers.30.mlp.shared_expert.down_proj",
749
+ "model.language_model.layers.30.mlp.shared_expert.gate_proj",
750
+ "model.language_model.layers.30.mlp.shared_expert.up_proj",
751
+ "model.language_model.layers.30.mlp.shared_expert_gate",
752
+ "model.language_model.layers.30.mlp_hyper_connection.block_inject_weight",
753
+ "model.language_model.layers.30.mlp_hyper_connection.hc_norm",
754
+ "model.language_model.layers.30.mlp_hyper_connection.input_mix_weight_down",
755
+ "model.language_model.layers.30.mlp_hyper_connection.input_mix_weight_up",
756
+ "model.language_model.layers.31.attn_hyper_connection.block_inject_weight",
757
+ "model.language_model.layers.31.attn_hyper_connection.hc_norm",
758
+ "model.language_model.layers.31.attn_hyper_connection.input_mix_weight_down",
759
+ "model.language_model.layers.31.attn_hyper_connection.input_mix_weight_up",
760
+ "model.language_model.layers.31.mlp.gate",
761
+ "model.language_model.layers.31.mlp.shared_expert.down_proj",
762
+ "model.language_model.layers.31.mlp.shared_expert.gate_proj",
763
+ "model.language_model.layers.31.mlp.shared_expert.up_proj",
764
+ "model.language_model.layers.31.mlp.shared_expert_gate",
765
+ "model.language_model.layers.31.mlp_hyper_connection.block_inject_weight",
766
+ "model.language_model.layers.31.mlp_hyper_connection.hc_norm",
767
+ "model.language_model.layers.31.mlp_hyper_connection.input_mix_weight_down",
768
+ "model.language_model.layers.31.mlp_hyper_connection.input_mix_weight_up",
769
+ "model.language_model.layers.31.self_attn.indexer.index_qk_proj",
770
+ "model.language_model.layers.31.self_attn.indexer.k_layernorm",
771
+ "model.language_model.layers.31.self_attn.indexer.q_layernorm",
772
+ "model.language_model.layers.31.self_attn.k_norm",
773
+ "model.language_model.layers.31.self_attn.k_proj",
774
+ "model.language_model.layers.31.self_attn.o_proj",
775
+ "model.language_model.layers.31.self_attn.q_norm",
776
+ "model.language_model.layers.31.self_attn.q_proj",
777
+ "model.language_model.layers.31.self_attn.v_proj",
778
+ "model.language_model.layers.32.attn_hyper_connection.block_inject_weight",
779
+ "model.language_model.layers.32.attn_hyper_connection.hc_norm",
780
+ "model.language_model.layers.32.attn_hyper_connection.input_mix_weight_down",
781
+ "model.language_model.layers.32.attn_hyper_connection.input_mix_weight_up",
782
+ "model.language_model.layers.32.linear_attn.A_log",
783
+ "model.language_model.layers.32.linear_attn.conv1d",
784
+ "model.language_model.layers.32.linear_attn.dt_bias",
785
+ "model.language_model.layers.32.linear_attn.in_proj_a",
786
+ "model.language_model.layers.32.linear_attn.in_proj_b",
787
+ "model.language_model.layers.32.linear_attn.in_proj_qkv",
788
+ "model.language_model.layers.32.linear_attn.in_proj_z",
789
+ "model.language_model.layers.32.linear_attn.norm",
790
+ "model.language_model.layers.32.linear_attn.out_proj",
791
+ "model.language_model.layers.32.mlp.gate",
792
+ "model.language_model.layers.32.mlp.shared_expert.down_proj",
793
+ "model.language_model.layers.32.mlp.shared_expert.gate_proj",
794
+ "model.language_model.layers.32.mlp.shared_expert.up_proj",
795
+ "model.language_model.layers.32.mlp.shared_expert_gate",
796
+ "model.language_model.layers.32.mlp_hyper_connection.block_inject_weight",
797
+ "model.language_model.layers.32.mlp_hyper_connection.hc_norm",
798
+ "model.language_model.layers.32.mlp_hyper_connection.input_mix_weight_down",
799
+ "model.language_model.layers.32.mlp_hyper_connection.input_mix_weight_up",
800
+ "model.language_model.layers.33.attn_hyper_connection.block_inject_weight",
801
+ "model.language_model.layers.33.attn_hyper_connection.hc_norm",
802
+ "model.language_model.layers.33.attn_hyper_connection.input_mix_weight_down",
803
+ "model.language_model.layers.33.attn_hyper_connection.input_mix_weight_up",
804
+ "model.language_model.layers.33.linear_attn.A_log",
805
+ "model.language_model.layers.33.linear_attn.conv1d",
806
+ "model.language_model.layers.33.linear_attn.dt_bias",
807
+ "model.language_model.layers.33.linear_attn.in_proj_a",
808
+ "model.language_model.layers.33.linear_attn.in_proj_b",
809
+ "model.language_model.layers.33.linear_attn.in_proj_qkv",
810
+ "model.language_model.layers.33.linear_attn.in_proj_z",
811
+ "model.language_model.layers.33.linear_attn.norm",
812
+ "model.language_model.layers.33.linear_attn.out_proj",
813
+ "model.language_model.layers.33.mlp.gate",
814
+ "model.language_model.layers.33.mlp.shared_expert.down_proj",
815
+ "model.language_model.layers.33.mlp.shared_expert.gate_proj",
816
+ "model.language_model.layers.33.mlp.shared_expert.up_proj",
817
+ "model.language_model.layers.33.mlp.shared_expert_gate",
818
+ "model.language_model.layers.33.mlp_hyper_connection.block_inject_weight",
819
+ "model.language_model.layers.33.mlp_hyper_connection.hc_norm",
820
+ "model.language_model.layers.33.mlp_hyper_connection.input_mix_weight_down",
821
+ "model.language_model.layers.33.mlp_hyper_connection.input_mix_weight_up",
822
+ "model.language_model.layers.34.attn_hyper_connection.block_inject_weight",
823
+ "model.language_model.layers.34.attn_hyper_connection.hc_norm",
824
+ "model.language_model.layers.34.attn_hyper_connection.input_mix_weight_down",
825
+ "model.language_model.layers.34.attn_hyper_connection.input_mix_weight_up",
826
+ "model.language_model.layers.34.linear_attn.A_log",
827
+ "model.language_model.layers.34.linear_attn.conv1d",
828
+ "model.language_model.layers.34.linear_attn.dt_bias",
829
+ "model.language_model.layers.34.linear_attn.in_proj_a",
830
+ "model.language_model.layers.34.linear_attn.in_proj_b",
831
+ "model.language_model.layers.34.linear_attn.in_proj_qkv",
832
+ "model.language_model.layers.34.linear_attn.in_proj_z",
833
+ "model.language_model.layers.34.linear_attn.norm",
834
+ "model.language_model.layers.34.linear_attn.out_proj",
835
+ "model.language_model.layers.34.mlp.gate",
836
+ "model.language_model.layers.34.mlp.shared_expert.down_proj",
837
+ "model.language_model.layers.34.mlp.shared_expert.gate_proj",
838
+ "model.language_model.layers.34.mlp.shared_expert.up_proj",
839
+ "model.language_model.layers.34.mlp.shared_expert_gate",
840
+ "model.language_model.layers.34.mlp_hyper_connection.block_inject_weight",
841
+ "model.language_model.layers.34.mlp_hyper_connection.hc_norm",
842
+ "model.language_model.layers.34.mlp_hyper_connection.input_mix_weight_down",
843
+ "model.language_model.layers.34.mlp_hyper_connection.input_mix_weight_up",
844
+ "model.language_model.layers.35.attn_hyper_connection.block_inject_weight",
845
+ "model.language_model.layers.35.attn_hyper_connection.hc_norm",
846
+ "model.language_model.layers.35.attn_hyper_connection.input_mix_weight_down",
847
+ "model.language_model.layers.35.attn_hyper_connection.input_mix_weight_up",
848
+ "model.language_model.layers.35.mlp.gate",
849
+ "model.language_model.layers.35.mlp.shared_expert.down_proj",
850
+ "model.language_model.layers.35.mlp.shared_expert.gate_proj",
851
+ "model.language_model.layers.35.mlp.shared_expert.up_proj",
852
+ "model.language_model.layers.35.mlp.shared_expert_gate",
853
+ "model.language_model.layers.35.mlp_hyper_connection.block_inject_weight",
854
+ "model.language_model.layers.35.mlp_hyper_connection.hc_norm",
855
+ "model.language_model.layers.35.mlp_hyper_connection.input_mix_weight_down",
856
+ "model.language_model.layers.35.mlp_hyper_connection.input_mix_weight_up",
857
+ "model.language_model.layers.35.self_attn.indexer.index_qk_proj",
858
+ "model.language_model.layers.35.self_attn.indexer.k_layernorm",
859
+ "model.language_model.layers.35.self_attn.indexer.q_layernorm",
860
+ "model.language_model.layers.35.self_attn.k_norm",
861
+ "model.language_model.layers.35.self_attn.k_proj",
862
+ "model.language_model.layers.35.self_attn.o_proj",
863
+ "model.language_model.layers.35.self_attn.q_norm",
864
+ "model.language_model.layers.35.self_attn.q_proj",
865
+ "model.language_model.layers.35.self_attn.v_proj",
866
+ "model.language_model.layers.36.attn_hyper_connection.block_inject_weight",
867
+ "model.language_model.layers.36.attn_hyper_connection.hc_norm",
868
+ "model.language_model.layers.36.attn_hyper_connection.input_mix_weight_down",
869
+ "model.language_model.layers.36.attn_hyper_connection.input_mix_weight_up",
870
+ "model.language_model.layers.36.linear_attn.A_log",
871
+ "model.language_model.layers.36.linear_attn.conv1d",
872
+ "model.language_model.layers.36.linear_attn.dt_bias",
873
+ "model.language_model.layers.36.linear_attn.in_proj_a",
874
+ "model.language_model.layers.36.linear_attn.in_proj_b",
875
+ "model.language_model.layers.36.linear_attn.in_proj_qkv",
876
+ "model.language_model.layers.36.linear_attn.in_proj_z",
877
+ "model.language_model.layers.36.linear_attn.norm",
878
+ "model.language_model.layers.36.linear_attn.out_proj",
879
+ "model.language_model.layers.36.mlp.gate",
880
+ "model.language_model.layers.36.mlp.shared_expert.down_proj",
881
+ "model.language_model.layers.36.mlp.shared_expert.gate_proj",
882
+ "model.language_model.layers.36.mlp.shared_expert.up_proj",
883
+ "model.language_model.layers.36.mlp.shared_expert_gate",
884
+ "model.language_model.layers.36.mlp_hyper_connection.block_inject_weight",
885
+ "model.language_model.layers.36.mlp_hyper_connection.hc_norm",
886
+ "model.language_model.layers.36.mlp_hyper_connection.input_mix_weight_down",
887
+ "model.language_model.layers.36.mlp_hyper_connection.input_mix_weight_up",
888
+ "model.language_model.layers.37.attn_hyper_connection.block_inject_weight",
889
+ "model.language_model.layers.37.attn_hyper_connection.hc_norm",
890
+ "model.language_model.layers.37.attn_hyper_connection.input_mix_weight_down",
891
+ "model.language_model.layers.37.attn_hyper_connection.input_mix_weight_up",
892
+ "model.language_model.layers.37.linear_attn.A_log",
893
+ "model.language_model.layers.37.linear_attn.conv1d",
894
+ "model.language_model.layers.37.linear_attn.dt_bias",
895
+ "model.language_model.layers.37.linear_attn.in_proj_a",
896
+ "model.language_model.layers.37.linear_attn.in_proj_b",
897
+ "model.language_model.layers.37.linear_attn.in_proj_qkv",
898
+ "model.language_model.layers.37.linear_attn.in_proj_z",
899
+ "model.language_model.layers.37.linear_attn.norm",
900
+ "model.language_model.layers.37.linear_attn.out_proj",
901
+ "model.language_model.layers.37.mlp.gate",
902
+ "model.language_model.layers.37.mlp.shared_expert.down_proj",
903
+ "model.language_model.layers.37.mlp.shared_expert.gate_proj",
904
+ "model.language_model.layers.37.mlp.shared_expert.up_proj",
905
+ "model.language_model.layers.37.mlp.shared_expert_gate",
906
+ "model.language_model.layers.37.mlp_hyper_connection.block_inject_weight",
907
+ "model.language_model.layers.37.mlp_hyper_connection.hc_norm",
908
+ "model.language_model.layers.37.mlp_hyper_connection.input_mix_weight_down",
909
+ "model.language_model.layers.37.mlp_hyper_connection.input_mix_weight_up",
910
+ "model.language_model.layers.38.attn_hyper_connection.block_inject_weight",
911
+ "model.language_model.layers.38.attn_hyper_connection.hc_norm",
912
+ "model.language_model.layers.38.attn_hyper_connection.input_mix_weight_down",
913
+ "model.language_model.layers.38.attn_hyper_connection.input_mix_weight_up",
914
+ "model.language_model.layers.38.linear_attn.A_log",
915
+ "model.language_model.layers.38.linear_attn.conv1d",
916
+ "model.language_model.layers.38.linear_attn.dt_bias",
917
+ "model.language_model.layers.38.linear_attn.in_proj_a",
918
+ "model.language_model.layers.38.linear_attn.in_proj_b",
919
+ "model.language_model.layers.38.linear_attn.in_proj_qkv",
920
+ "model.language_model.layers.38.linear_attn.in_proj_z",
921
+ "model.language_model.layers.38.linear_attn.norm",
922
+ "model.language_model.layers.38.linear_attn.out_proj",
923
+ "model.language_model.layers.38.mlp.gate",
924
+ "model.language_model.layers.38.mlp.shared_expert.down_proj",
925
+ "model.language_model.layers.38.mlp.shared_expert.gate_proj",
926
+ "model.language_model.layers.38.mlp.shared_expert.up_proj",
927
+ "model.language_model.layers.38.mlp.shared_expert_gate",
928
+ "model.language_model.layers.38.mlp_hyper_connection.block_inject_weight",
929
+ "model.language_model.layers.38.mlp_hyper_connection.hc_norm",
930
+ "model.language_model.layers.38.mlp_hyper_connection.input_mix_weight_down",
931
+ "model.language_model.layers.38.mlp_hyper_connection.input_mix_weight_up",
932
+ "model.language_model.layers.39.attn_hyper_connection.block_inject_weight",
933
+ "model.language_model.layers.39.attn_hyper_connection.hc_norm",
934
+ "model.language_model.layers.39.attn_hyper_connection.input_mix_weight_down",
935
+ "model.language_model.layers.39.attn_hyper_connection.input_mix_weight_up",
936
+ "model.language_model.layers.39.mlp.gate",
937
+ "model.language_model.layers.39.mlp.shared_expert.down_proj",
938
+ "model.language_model.layers.39.mlp.shared_expert.gate_proj",
939
+ "model.language_model.layers.39.mlp.shared_expert.up_proj",
940
+ "model.language_model.layers.39.mlp.shared_expert_gate",
941
+ "model.language_model.layers.39.mlp_hyper_connection.block_inject_weight",
942
+ "model.language_model.layers.39.mlp_hyper_connection.hc_norm",
943
+ "model.language_model.layers.39.mlp_hyper_connection.input_mix_weight_down",
944
+ "model.language_model.layers.39.mlp_hyper_connection.input_mix_weight_up",
945
+ "model.language_model.layers.39.self_attn.indexer.index_qk_proj",
946
+ "model.language_model.layers.39.self_attn.indexer.k_layernorm",
947
+ "model.language_model.layers.39.self_attn.indexer.q_layernorm",
948
+ "model.language_model.layers.39.self_attn.k_norm",
949
+ "model.language_model.layers.39.self_attn.k_proj",
950
+ "model.language_model.layers.39.self_attn.o_proj",
951
+ "model.language_model.layers.39.self_attn.q_norm",
952
+ "model.language_model.layers.39.self_attn.q_proj",
953
+ "model.language_model.layers.39.self_attn.v_proj",
954
+ "model.language_model.layers.4.attn_hyper_connection.block_inject_weight",
955
+ "model.language_model.layers.4.attn_hyper_connection.hc_norm",
956
+ "model.language_model.layers.4.attn_hyper_connection.input_mix_weight_down",
957
+ "model.language_model.layers.4.attn_hyper_connection.input_mix_weight_up",
958
+ "model.language_model.layers.4.linear_attn.A_log",
959
+ "model.language_model.layers.4.linear_attn.conv1d",
960
+ "model.language_model.layers.4.linear_attn.dt_bias",
961
+ "model.language_model.layers.4.linear_attn.in_proj_a",
962
+ "model.language_model.layers.4.linear_attn.in_proj_b",
963
+ "model.language_model.layers.4.linear_attn.in_proj_qkv",
964
+ "model.language_model.layers.4.linear_attn.in_proj_z",
965
+ "model.language_model.layers.4.linear_attn.norm",
966
+ "model.language_model.layers.4.linear_attn.out_proj",
967
+ "model.language_model.layers.4.mlp.gate",
968
+ "model.language_model.layers.4.mlp.shared_expert.down_proj",
969
+ "model.language_model.layers.4.mlp.shared_expert.gate_proj",
970
+ "model.language_model.layers.4.mlp.shared_expert.up_proj",
971
+ "model.language_model.layers.4.mlp.shared_expert_gate",
972
+ "model.language_model.layers.4.mlp_hyper_connection.block_inject_weight",
973
+ "model.language_model.layers.4.mlp_hyper_connection.hc_norm",
974
+ "model.language_model.layers.4.mlp_hyper_connection.input_mix_weight_down",
975
+ "model.language_model.layers.4.mlp_hyper_connection.input_mix_weight_up",
976
+ "model.language_model.layers.40.attn_hyper_connection.block_inject_weight",
977
+ "model.language_model.layers.40.attn_hyper_connection.hc_norm",
978
+ "model.language_model.layers.40.attn_hyper_connection.input_mix_weight_down",
979
+ "model.language_model.layers.40.attn_hyper_connection.input_mix_weight_up",
980
+ "model.language_model.layers.40.linear_attn.A_log",
981
+ "model.language_model.layers.40.linear_attn.conv1d",
982
+ "model.language_model.layers.40.linear_attn.dt_bias",
983
+ "model.language_model.layers.40.linear_attn.in_proj_a",
984
+ "model.language_model.layers.40.linear_attn.in_proj_b",
985
+ "model.language_model.layers.40.linear_attn.in_proj_qkv",
986
+ "model.language_model.layers.40.linear_attn.in_proj_z",
987
+ "model.language_model.layers.40.linear_attn.norm",
988
+ "model.language_model.layers.40.linear_attn.out_proj",
989
+ "model.language_model.layers.40.mlp.gate",
990
+ "model.language_model.layers.40.mlp.shared_expert.down_proj",
991
+ "model.language_model.layers.40.mlp.shared_expert.gate_proj",
992
+ "model.language_model.layers.40.mlp.shared_expert.up_proj",
993
+ "model.language_model.layers.40.mlp.shared_expert_gate",
994
+ "model.language_model.layers.40.mlp_hyper_connection.block_inject_weight",
995
+ "model.language_model.layers.40.mlp_hyper_connection.hc_norm",
996
+ "model.language_model.layers.40.mlp_hyper_connection.input_mix_weight_down",
997
+ "model.language_model.layers.40.mlp_hyper_connection.input_mix_weight_up",
998
+ "model.language_model.layers.41.attn_hyper_connection.block_inject_weight",
999
+ "model.language_model.layers.41.attn_hyper_connection.hc_norm",
1000
+ "model.language_model.layers.41.attn_hyper_connection.input_mix_weight_down",
1001
+ "model.language_model.layers.41.attn_hyper_connection.input_mix_weight_up",
1002
+ "model.language_model.layers.41.linear_attn.A_log",
1003
+ "model.language_model.layers.41.linear_attn.conv1d",
1004
+ "model.language_model.layers.41.linear_attn.dt_bias",
1005
+ "model.language_model.layers.41.linear_attn.in_proj_a",
1006
+ "model.language_model.layers.41.linear_attn.in_proj_b",
1007
+ "model.language_model.layers.41.linear_attn.in_proj_qkv",
1008
+ "model.language_model.layers.41.linear_attn.in_proj_z",
1009
+ "model.language_model.layers.41.linear_attn.norm",
1010
+ "model.language_model.layers.41.linear_attn.out_proj",
1011
+ "model.language_model.layers.41.mlp.gate",
1012
+ "model.language_model.layers.41.mlp.shared_expert.down_proj",
1013
+ "model.language_model.layers.41.mlp.shared_expert.gate_proj",
1014
+ "model.language_model.layers.41.mlp.shared_expert.up_proj",
1015
+ "model.language_model.layers.41.mlp.shared_expert_gate",
1016
+ "model.language_model.layers.41.mlp_hyper_connection.block_inject_weight",
1017
+ "model.language_model.layers.41.mlp_hyper_connection.hc_norm",
1018
+ "model.language_model.layers.41.mlp_hyper_connection.input_mix_weight_down",
1019
+ "model.language_model.layers.41.mlp_hyper_connection.input_mix_weight_up",
1020
+ "model.language_model.layers.42.attn_hyper_connection.block_inject_weight",
1021
+ "model.language_model.layers.42.attn_hyper_connection.hc_norm",
1022
+ "model.language_model.layers.42.attn_hyper_connection.input_mix_weight_down",
1023
+ "model.language_model.layers.42.attn_hyper_connection.input_mix_weight_up",
1024
+ "model.language_model.layers.42.linear_attn.A_log",
1025
+ "model.language_model.layers.42.linear_attn.conv1d",
1026
+ "model.language_model.layers.42.linear_attn.dt_bias",
1027
+ "model.language_model.layers.42.linear_attn.in_proj_a",
1028
+ "model.language_model.layers.42.linear_attn.in_proj_b",
1029
+ "model.language_model.layers.42.linear_attn.in_proj_qkv",
1030
+ "model.language_model.layers.42.linear_attn.in_proj_z",
1031
+ "model.language_model.layers.42.linear_attn.norm",
1032
+ "model.language_model.layers.42.linear_attn.out_proj",
1033
+ "model.language_model.layers.42.mlp.gate",
1034
+ "model.language_model.layers.42.mlp.shared_expert.down_proj",
1035
+ "model.language_model.layers.42.mlp.shared_expert.gate_proj",
1036
+ "model.language_model.layers.42.mlp.shared_expert.up_proj",
1037
+ "model.language_model.layers.42.mlp.shared_expert_gate",
1038
+ "model.language_model.layers.42.mlp_hyper_connection.block_inject_weight",
1039
+ "model.language_model.layers.42.mlp_hyper_connection.hc_norm",
1040
+ "model.language_model.layers.42.mlp_hyper_connection.input_mix_weight_down",
1041
+ "model.language_model.layers.42.mlp_hyper_connection.input_mix_weight_up",
1042
+ "model.language_model.layers.43.attn_hyper_connection.block_inject_weight",
1043
+ "model.language_model.layers.43.attn_hyper_connection.hc_norm",
1044
+ "model.language_model.layers.43.attn_hyper_connection.input_mix_weight_down",
1045
+ "model.language_model.layers.43.attn_hyper_connection.input_mix_weight_up",
1046
+ "model.language_model.layers.43.mlp.gate",
1047
+ "model.language_model.layers.43.mlp.shared_expert.down_proj",
1048
+ "model.language_model.layers.43.mlp.shared_expert.gate_proj",
1049
+ "model.language_model.layers.43.mlp.shared_expert.up_proj",
1050
+ "model.language_model.layers.43.mlp.shared_expert_gate",
1051
+ "model.language_model.layers.43.mlp_hyper_connection.block_inject_weight",
1052
+ "model.language_model.layers.43.mlp_hyper_connection.hc_norm",
1053
+ "model.language_model.layers.43.mlp_hyper_connection.input_mix_weight_down",
1054
+ "model.language_model.layers.43.mlp_hyper_connection.input_mix_weight_up",
1055
+ "model.language_model.layers.43.self_attn.indexer.index_qk_proj",
1056
+ "model.language_model.layers.43.self_attn.indexer.k_layernorm",
1057
+ "model.language_model.layers.43.self_attn.indexer.q_layernorm",
1058
+ "model.language_model.layers.43.self_attn.k_norm",
1059
+ "model.language_model.layers.43.self_attn.k_proj",
1060
+ "model.language_model.layers.43.self_attn.o_proj",
1061
+ "model.language_model.layers.43.self_attn.q_norm",
1062
+ "model.language_model.layers.43.self_attn.q_proj",
1063
+ "model.language_model.layers.43.self_attn.v_proj",
1064
+ "model.language_model.layers.44.attn_hyper_connection.block_inject_weight",
1065
+ "model.language_model.layers.44.attn_hyper_connection.hc_norm",
1066
+ "model.language_model.layers.44.attn_hyper_connection.input_mix_weight_down",
1067
+ "model.language_model.layers.44.attn_hyper_connection.input_mix_weight_up",
1068
+ "model.language_model.layers.44.linear_attn.A_log",
1069
+ "model.language_model.layers.44.linear_attn.conv1d",
1070
+ "model.language_model.layers.44.linear_attn.dt_bias",
1071
+ "model.language_model.layers.44.linear_attn.in_proj_a",
1072
+ "model.language_model.layers.44.linear_attn.in_proj_b",
1073
+ "model.language_model.layers.44.linear_attn.in_proj_qkv",
1074
+ "model.language_model.layers.44.linear_attn.in_proj_z",
1075
+ "model.language_model.layers.44.linear_attn.norm",
1076
+ "model.language_model.layers.44.linear_attn.out_proj",
1077
+ "model.language_model.layers.44.mlp.gate",
1078
+ "model.language_model.layers.44.mlp.shared_expert.down_proj",
1079
+ "model.language_model.layers.44.mlp.shared_expert.gate_proj",
1080
+ "model.language_model.layers.44.mlp.shared_expert.up_proj",
1081
+ "model.language_model.layers.44.mlp.shared_expert_gate",
1082
+ "model.language_model.layers.44.mlp_hyper_connection.block_inject_weight",
1083
+ "model.language_model.layers.44.mlp_hyper_connection.hc_norm",
1084
+ "model.language_model.layers.44.mlp_hyper_connection.input_mix_weight_down",
1085
+ "model.language_model.layers.44.mlp_hyper_connection.input_mix_weight_up",
1086
+ "model.language_model.layers.45.attn_hyper_connection.block_inject_weight",
1087
+ "model.language_model.layers.45.attn_hyper_connection.hc_norm",
1088
+ "model.language_model.layers.45.attn_hyper_connection.input_mix_weight_down",
1089
+ "model.language_model.layers.45.attn_hyper_connection.input_mix_weight_up",
1090
+ "model.language_model.layers.45.linear_attn.A_log",
1091
+ "model.language_model.layers.45.linear_attn.conv1d",
1092
+ "model.language_model.layers.45.linear_attn.dt_bias",
1093
+ "model.language_model.layers.45.linear_attn.in_proj_a",
1094
+ "model.language_model.layers.45.linear_attn.in_proj_b",
1095
+ "model.language_model.layers.45.linear_attn.in_proj_qkv",
1096
+ "model.language_model.layers.45.linear_attn.in_proj_z",
1097
+ "model.language_model.layers.45.linear_attn.norm",
1098
+ "model.language_model.layers.45.linear_attn.out_proj",
1099
+ "model.language_model.layers.45.mlp.gate",
1100
+ "model.language_model.layers.45.mlp.shared_expert.down_proj",
1101
+ "model.language_model.layers.45.mlp.shared_expert.gate_proj",
1102
+ "model.language_model.layers.45.mlp.shared_expert.up_proj",
1103
+ "model.language_model.layers.45.mlp.shared_expert_gate",
1104
+ "model.language_model.layers.45.mlp_hyper_connection.block_inject_weight",
1105
+ "model.language_model.layers.45.mlp_hyper_connection.hc_norm",
1106
+ "model.language_model.layers.45.mlp_hyper_connection.input_mix_weight_down",
1107
+ "model.language_model.layers.45.mlp_hyper_connection.input_mix_weight_up",
1108
+ "model.language_model.layers.46.attn_hyper_connection.block_inject_weight",
1109
+ "model.language_model.layers.46.attn_hyper_connection.hc_norm",
1110
+ "model.language_model.layers.46.attn_hyper_connection.input_mix_weight_down",
1111
+ "model.language_model.layers.46.attn_hyper_connection.input_mix_weight_up",
1112
+ "model.language_model.layers.46.linear_attn.A_log",
1113
+ "model.language_model.layers.46.linear_attn.conv1d",
1114
+ "model.language_model.layers.46.linear_attn.dt_bias",
1115
+ "model.language_model.layers.46.linear_attn.in_proj_a",
1116
+ "model.language_model.layers.46.linear_attn.in_proj_b",
1117
+ "model.language_model.layers.46.linear_attn.in_proj_qkv",
1118
+ "model.language_model.layers.46.linear_attn.in_proj_z",
1119
+ "model.language_model.layers.46.linear_attn.norm",
1120
+ "model.language_model.layers.46.linear_attn.out_proj",
1121
+ "model.language_model.layers.46.mlp.gate",
1122
+ "model.language_model.layers.46.mlp.shared_expert.down_proj",
1123
+ "model.language_model.layers.46.mlp.shared_expert.gate_proj",
1124
+ "model.language_model.layers.46.mlp.shared_expert.up_proj",
1125
+ "model.language_model.layers.46.mlp.shared_expert_gate",
1126
+ "model.language_model.layers.46.mlp_hyper_connection.block_inject_weight",
1127
+ "model.language_model.layers.46.mlp_hyper_connection.hc_norm",
1128
+ "model.language_model.layers.46.mlp_hyper_connection.input_mix_weight_down",
1129
+ "model.language_model.layers.46.mlp_hyper_connection.input_mix_weight_up",
1130
+ "model.language_model.layers.47.attn_hyper_connection.block_inject_weight",
1131
+ "model.language_model.layers.47.attn_hyper_connection.hc_norm",
1132
+ "model.language_model.layers.47.attn_hyper_connection.input_mix_weight_down",
1133
+ "model.language_model.layers.47.attn_hyper_connection.input_mix_weight_up",
1134
+ "model.language_model.layers.47.mlp.gate",
1135
+ "model.language_model.layers.47.mlp.shared_expert.down_proj",
1136
+ "model.language_model.layers.47.mlp.shared_expert.gate_proj",
1137
+ "model.language_model.layers.47.mlp.shared_expert.up_proj",
1138
+ "model.language_model.layers.47.mlp.shared_expert_gate",
1139
+ "model.language_model.layers.47.mlp_hyper_connection.block_inject_weight",
1140
+ "model.language_model.layers.47.mlp_hyper_connection.hc_norm",
1141
+ "model.language_model.layers.47.mlp_hyper_connection.input_mix_weight_down",
1142
+ "model.language_model.layers.47.mlp_hyper_connection.input_mix_weight_up",
1143
+ "model.language_model.layers.47.self_attn.indexer.index_qk_proj",
1144
+ "model.language_model.layers.47.self_attn.indexer.k_layernorm",
1145
+ "model.language_model.layers.47.self_attn.indexer.q_layernorm",
1146
+ "model.language_model.layers.47.self_attn.k_norm",
1147
+ "model.language_model.layers.47.self_attn.k_proj",
1148
+ "model.language_model.layers.47.self_attn.o_proj",
1149
+ "model.language_model.layers.47.self_attn.q_norm",
1150
+ "model.language_model.layers.47.self_attn.q_proj",
1151
+ "model.language_model.layers.47.self_attn.v_proj",
1152
+ "model.language_model.layers.5.attn_hyper_connection.block_inject_weight",
1153
+ "model.language_model.layers.5.attn_hyper_connection.hc_norm",
1154
+ "model.language_model.layers.5.attn_hyper_connection.input_mix_weight_down",
1155
+ "model.language_model.layers.5.attn_hyper_connection.input_mix_weight_up",
1156
+ "model.language_model.layers.5.linear_attn.A_log",
1157
+ "model.language_model.layers.5.linear_attn.conv1d",
1158
+ "model.language_model.layers.5.linear_attn.dt_bias",
1159
+ "model.language_model.layers.5.linear_attn.in_proj_a",
1160
+ "model.language_model.layers.5.linear_attn.in_proj_b",
1161
+ "model.language_model.layers.5.linear_attn.in_proj_qkv",
1162
+ "model.language_model.layers.5.linear_attn.in_proj_z",
1163
+ "model.language_model.layers.5.linear_attn.norm",
1164
+ "model.language_model.layers.5.linear_attn.out_proj",
1165
+ "model.language_model.layers.5.mlp.gate",
1166
+ "model.language_model.layers.5.mlp.shared_expert.down_proj",
1167
+ "model.language_model.layers.5.mlp.shared_expert.gate_proj",
1168
+ "model.language_model.layers.5.mlp.shared_expert.up_proj",
1169
+ "model.language_model.layers.5.mlp.shared_expert_gate",
1170
+ "model.language_model.layers.5.mlp_hyper_connection.block_inject_weight",
1171
+ "model.language_model.layers.5.mlp_hyper_connection.hc_norm",
1172
+ "model.language_model.layers.5.mlp_hyper_connection.input_mix_weight_down",
1173
+ "model.language_model.layers.5.mlp_hyper_connection.input_mix_weight_up",
1174
+ "model.language_model.layers.6.attn_hyper_connection.block_inject_weight",
1175
+ "model.language_model.layers.6.attn_hyper_connection.hc_norm",
1176
+ "model.language_model.layers.6.attn_hyper_connection.input_mix_weight_down",
1177
+ "model.language_model.layers.6.attn_hyper_connection.input_mix_weight_up",
1178
+ "model.language_model.layers.6.linear_attn.A_log",
1179
+ "model.language_model.layers.6.linear_attn.conv1d",
1180
+ "model.language_model.layers.6.linear_attn.dt_bias",
1181
+ "model.language_model.layers.6.linear_attn.in_proj_a",
1182
+ "model.language_model.layers.6.linear_attn.in_proj_b",
1183
+ "model.language_model.layers.6.linear_attn.in_proj_qkv",
1184
+ "model.language_model.layers.6.linear_attn.in_proj_z",
1185
+ "model.language_model.layers.6.linear_attn.norm",
1186
+ "model.language_model.layers.6.linear_attn.out_proj",
1187
+ "model.language_model.layers.6.mlp.gate",
1188
+ "model.language_model.layers.6.mlp.shared_expert.down_proj",
1189
+ "model.language_model.layers.6.mlp.shared_expert.gate_proj",
1190
+ "model.language_model.layers.6.mlp.shared_expert.up_proj",
1191
+ "model.language_model.layers.6.mlp.shared_expert_gate",
1192
+ "model.language_model.layers.6.mlp_hyper_connection.block_inject_weight",
1193
+ "model.language_model.layers.6.mlp_hyper_connection.hc_norm",
1194
+ "model.language_model.layers.6.mlp_hyper_connection.input_mix_weight_down",
1195
+ "model.language_model.layers.6.mlp_hyper_connection.input_mix_weight_up",
1196
+ "model.language_model.layers.7.attn_hyper_connection.block_inject_weight",
1197
+ "model.language_model.layers.7.attn_hyper_connection.hc_norm",
1198
+ "model.language_model.layers.7.attn_hyper_connection.input_mix_weight_down",
1199
+ "model.language_model.layers.7.attn_hyper_connection.input_mix_weight_up",
1200
+ "model.language_model.layers.7.mlp.gate",
1201
+ "model.language_model.layers.7.mlp.shared_expert.down_proj",
1202
+ "model.language_model.layers.7.mlp.shared_expert.gate_proj",
1203
+ "model.language_model.layers.7.mlp.shared_expert.up_proj",
1204
+ "model.language_model.layers.7.mlp.shared_expert_gate",
1205
+ "model.language_model.layers.7.mlp_hyper_connection.block_inject_weight",
1206
+ "model.language_model.layers.7.mlp_hyper_connection.hc_norm",
1207
+ "model.language_model.layers.7.mlp_hyper_connection.input_mix_weight_down",
1208
+ "model.language_model.layers.7.mlp_hyper_connection.input_mix_weight_up",
1209
+ "model.language_model.layers.7.self_attn.indexer.index_qk_proj",
1210
+ "model.language_model.layers.7.self_attn.indexer.k_layernorm",
1211
+ "model.language_model.layers.7.self_attn.indexer.q_layernorm",
1212
+ "model.language_model.layers.7.self_attn.k_norm",
1213
+ "model.language_model.layers.7.self_attn.k_proj",
1214
+ "model.language_model.layers.7.self_attn.o_proj",
1215
+ "model.language_model.layers.7.self_attn.q_norm",
1216
+ "model.language_model.layers.7.self_attn.q_proj",
1217
+ "model.language_model.layers.7.self_attn.v_proj",
1218
+ "model.language_model.layers.8.attn_hyper_connection.block_inject_weight",
1219
+ "model.language_model.layers.8.attn_hyper_connection.hc_norm",
1220
+ "model.language_model.layers.8.attn_hyper_connection.input_mix_weight_down",
1221
+ "model.language_model.layers.8.attn_hyper_connection.input_mix_weight_up",
1222
+ "model.language_model.layers.8.linear_attn.A_log",
1223
+ "model.language_model.layers.8.linear_attn.conv1d",
1224
+ "model.language_model.layers.8.linear_attn.dt_bias",
1225
+ "model.language_model.layers.8.linear_attn.in_proj_a",
1226
+ "model.language_model.layers.8.linear_attn.in_proj_b",
1227
+ "model.language_model.layers.8.linear_attn.in_proj_qkv",
1228
+ "model.language_model.layers.8.linear_attn.in_proj_z",
1229
+ "model.language_model.layers.8.linear_attn.norm",
1230
+ "model.language_model.layers.8.linear_attn.out_proj",
1231
+ "model.language_model.layers.8.mlp.gate",
1232
+ "model.language_model.layers.8.mlp.shared_expert.down_proj",
1233
+ "model.language_model.layers.8.mlp.shared_expert.gate_proj",
1234
+ "model.language_model.layers.8.mlp.shared_expert.up_proj",
1235
+ "model.language_model.layers.8.mlp.shared_expert_gate",
1236
+ "model.language_model.layers.8.mlp_hyper_connection.block_inject_weight",
1237
+ "model.language_model.layers.8.mlp_hyper_connection.hc_norm",
1238
+ "model.language_model.layers.8.mlp_hyper_connection.input_mix_weight_down",
1239
+ "model.language_model.layers.8.mlp_hyper_connection.input_mix_weight_up",
1240
+ "model.language_model.layers.9.attn_hyper_connection.block_inject_weight",
1241
+ "model.language_model.layers.9.attn_hyper_connection.hc_norm",
1242
+ "model.language_model.layers.9.attn_hyper_connection.input_mix_weight_down",
1243
+ "model.language_model.layers.9.attn_hyper_connection.input_mix_weight_up",
1244
+ "model.language_model.layers.9.linear_attn.A_log",
1245
+ "model.language_model.layers.9.linear_attn.conv1d",
1246
+ "model.language_model.layers.9.linear_attn.dt_bias",
1247
+ "model.language_model.layers.9.linear_attn.in_proj_a",
1248
+ "model.language_model.layers.9.linear_attn.in_proj_b",
1249
+ "model.language_model.layers.9.linear_attn.in_proj_qkv",
1250
+ "model.language_model.layers.9.linear_attn.in_proj_z",
1251
+ "model.language_model.layers.9.linear_attn.norm",
1252
+ "model.language_model.layers.9.linear_attn.out_proj",
1253
+ "model.language_model.layers.9.mlp.gate",
1254
+ "model.language_model.layers.9.mlp.shared_expert.down_proj",
1255
+ "model.language_model.layers.9.mlp.shared_expert.gate_proj",
1256
+ "model.language_model.layers.9.mlp.shared_expert.up_proj",
1257
+ "model.language_model.layers.9.mlp.shared_expert_gate",
1258
+ "model.language_model.layers.9.mlp_hyper_connection.block_inject_weight",
1259
+ "model.language_model.layers.9.mlp_hyper_connection.hc_norm",
1260
+ "model.language_model.layers.9.mlp_hyper_connection.input_mix_weight_down",
1261
+ "model.language_model.layers.9.mlp_hyper_connection.input_mix_weight_up",
1262
+ "model.visual.blocks.0.attn.proj",
1263
+ "model.visual.blocks.0.attn.qkv",
1264
+ "model.visual.blocks.0.mlp.linear_fc1",
1265
+ "model.visual.blocks.0.mlp.linear_fc2",
1266
+ "model.visual.blocks.0.norm1",
1267
+ "model.visual.blocks.0.norm2",
1268
+ "model.visual.blocks.1.attn.proj",
1269
+ "model.visual.blocks.1.attn.qkv",
1270
+ "model.visual.blocks.1.mlp.linear_fc1",
1271
+ "model.visual.blocks.1.mlp.linear_fc2",
1272
+ "model.visual.blocks.1.norm1",
1273
+ "model.visual.blocks.1.norm2",
1274
+ "model.visual.blocks.10.attn.proj",
1275
+ "model.visual.blocks.10.attn.qkv",
1276
+ "model.visual.blocks.10.mlp.linear_fc1",
1277
+ "model.visual.blocks.10.mlp.linear_fc2",
1278
+ "model.visual.blocks.10.norm1",
1279
+ "model.visual.blocks.10.norm2",
1280
+ "model.visual.blocks.11.attn.proj",
1281
+ "model.visual.blocks.11.attn.qkv",
1282
+ "model.visual.blocks.11.mlp.linear_fc1",
1283
+ "model.visual.blocks.11.mlp.linear_fc2",
1284
+ "model.visual.blocks.11.norm1",
1285
+ "model.visual.blocks.11.norm2",
1286
+ "model.visual.blocks.12.attn.proj",
1287
+ "model.visual.blocks.12.attn.qkv",
1288
+ "model.visual.blocks.12.mlp.linear_fc1",
1289
+ "model.visual.blocks.12.mlp.linear_fc2",
1290
+ "model.visual.blocks.12.norm1",
1291
+ "model.visual.blocks.12.norm2",
1292
+ "model.visual.blocks.13.attn.proj",
1293
+ "model.visual.blocks.13.attn.qkv",
1294
+ "model.visual.blocks.13.mlp.linear_fc1",
1295
+ "model.visual.blocks.13.mlp.linear_fc2",
1296
+ "model.visual.blocks.13.norm1",
1297
+ "model.visual.blocks.13.norm2",
1298
+ "model.visual.blocks.14.attn.proj",
1299
+ "model.visual.blocks.14.attn.qkv",
1300
+ "model.visual.blocks.14.mlp.linear_fc1",
1301
+ "model.visual.blocks.14.mlp.linear_fc2",
1302
+ "model.visual.blocks.14.norm1",
1303
+ "model.visual.blocks.14.norm2",
1304
+ "model.visual.blocks.15.attn.proj",
1305
+ "model.visual.blocks.15.attn.qkv",
1306
+ "model.visual.blocks.15.mlp.linear_fc1",
1307
+ "model.visual.blocks.15.mlp.linear_fc2",
1308
+ "model.visual.blocks.15.norm1",
1309
+ "model.visual.blocks.15.norm2",
1310
+ "model.visual.blocks.16.attn.proj",
1311
+ "model.visual.blocks.16.attn.qkv",
1312
+ "model.visual.blocks.16.mlp.linear_fc1",
1313
+ "model.visual.blocks.16.mlp.linear_fc2",
1314
+ "model.visual.blocks.16.norm1",
1315
+ "model.visual.blocks.16.norm2",
1316
+ "model.visual.blocks.17.attn.proj",
1317
+ "model.visual.blocks.17.attn.qkv",
1318
+ "model.visual.blocks.17.mlp.linear_fc1",
1319
+ "model.visual.blocks.17.mlp.linear_fc2",
1320
+ "model.visual.blocks.17.norm1",
1321
+ "model.visual.blocks.17.norm2",
1322
+ "model.visual.blocks.18.attn.proj",
1323
+ "model.visual.blocks.18.attn.qkv",
1324
+ "model.visual.blocks.18.mlp.linear_fc1",
1325
+ "model.visual.blocks.18.mlp.linear_fc2",
1326
+ "model.visual.blocks.18.norm1",
1327
+ "model.visual.blocks.18.norm2",
1328
+ "model.visual.blocks.19.attn.proj",
1329
+ "model.visual.blocks.19.attn.qkv",
1330
+ "model.visual.blocks.19.mlp.linear_fc1",
1331
+ "model.visual.blocks.19.mlp.linear_fc2",
1332
+ "model.visual.blocks.19.norm1",
1333
+ "model.visual.blocks.19.norm2",
1334
+ "model.visual.blocks.2.attn.proj",
1335
+ "model.visual.blocks.2.attn.qkv",
1336
+ "model.visual.blocks.2.mlp.linear_fc1",
1337
+ "model.visual.blocks.2.mlp.linear_fc2",
1338
+ "model.visual.blocks.2.norm1",
1339
+ "model.visual.blocks.2.norm2",
1340
+ "model.visual.blocks.20.attn.proj",
1341
+ "model.visual.blocks.20.attn.qkv",
1342
+ "model.visual.blocks.20.mlp.linear_fc1",
1343
+ "model.visual.blocks.20.mlp.linear_fc2",
1344
+ "model.visual.blocks.20.norm1",
1345
+ "model.visual.blocks.20.norm2",
1346
+ "model.visual.blocks.21.attn.proj",
1347
+ "model.visual.blocks.21.attn.qkv",
1348
+ "model.visual.blocks.21.mlp.linear_fc1",
1349
+ "model.visual.blocks.21.mlp.linear_fc2",
1350
+ "model.visual.blocks.21.norm1",
1351
+ "model.visual.blocks.21.norm2",
1352
+ "model.visual.blocks.22.attn.proj",
1353
+ "model.visual.blocks.22.attn.qkv",
1354
+ "model.visual.blocks.22.mlp.linear_fc1",
1355
+ "model.visual.blocks.22.mlp.linear_fc2",
1356
+ "model.visual.blocks.22.norm1",
1357
+ "model.visual.blocks.22.norm2",
1358
+ "model.visual.blocks.23.attn.proj",
1359
+ "model.visual.blocks.23.attn.qkv",
1360
+ "model.visual.blocks.23.mlp.linear_fc1",
1361
+ "model.visual.blocks.23.mlp.linear_fc2",
1362
+ "model.visual.blocks.23.norm1",
1363
+ "model.visual.blocks.23.norm2",
1364
+ "model.visual.blocks.24.attn.proj",
1365
+ "model.visual.blocks.24.attn.qkv",
1366
+ "model.visual.blocks.24.mlp.linear_fc1",
1367
+ "model.visual.blocks.24.mlp.linear_fc2",
1368
+ "model.visual.blocks.24.norm1",
1369
+ "model.visual.blocks.24.norm2",
1370
+ "model.visual.blocks.25.attn.proj",
1371
+ "model.visual.blocks.25.attn.qkv",
1372
+ "model.visual.blocks.25.mlp.linear_fc1",
1373
+ "model.visual.blocks.25.mlp.linear_fc2",
1374
+ "model.visual.blocks.25.norm1",
1375
+ "model.visual.blocks.25.norm2",
1376
+ "model.visual.blocks.26.attn.proj",
1377
+ "model.visual.blocks.26.attn.qkv",
1378
+ "model.visual.blocks.26.mlp.linear_fc1",
1379
+ "model.visual.blocks.26.mlp.linear_fc2",
1380
+ "model.visual.blocks.26.norm1",
1381
+ "model.visual.blocks.26.norm2",
1382
+ "model.visual.blocks.3.attn.proj",
1383
+ "model.visual.blocks.3.attn.qkv",
1384
+ "model.visual.blocks.3.mlp.linear_fc1",
1385
+ "model.visual.blocks.3.mlp.linear_fc2",
1386
+ "model.visual.blocks.3.norm1",
1387
+ "model.visual.blocks.3.norm2",
1388
+ "model.visual.blocks.4.attn.proj",
1389
+ "model.visual.blocks.4.attn.qkv",
1390
+ "model.visual.blocks.4.mlp.linear_fc1",
1391
+ "model.visual.blocks.4.mlp.linear_fc2",
1392
+ "model.visual.blocks.4.norm1",
1393
+ "model.visual.blocks.4.norm2",
1394
+ "model.visual.blocks.5.attn.proj",
1395
+ "model.visual.blocks.5.attn.qkv",
1396
+ "model.visual.blocks.5.mlp.linear_fc1",
1397
+ "model.visual.blocks.5.mlp.linear_fc2",
1398
+ "model.visual.blocks.5.norm1",
1399
+ "model.visual.blocks.5.norm2",
1400
+ "model.visual.blocks.6.attn.proj",
1401
+ "model.visual.blocks.6.attn.qkv",
1402
+ "model.visual.blocks.6.mlp.linear_fc1",
1403
+ "model.visual.blocks.6.mlp.linear_fc2",
1404
+ "model.visual.blocks.6.norm1",
1405
+ "model.visual.blocks.6.norm2",
1406
+ "model.visual.blocks.7.attn.proj",
1407
+ "model.visual.blocks.7.attn.qkv",
1408
+ "model.visual.blocks.7.mlp.linear_fc1",
1409
+ "model.visual.blocks.7.mlp.linear_fc2",
1410
+ "model.visual.blocks.7.norm1",
1411
+ "model.visual.blocks.7.norm2",
1412
+ "model.visual.blocks.8.attn.proj",
1413
+ "model.visual.blocks.8.attn.qkv",
1414
+ "model.visual.blocks.8.mlp.linear_fc1",
1415
+ "model.visual.blocks.8.mlp.linear_fc2",
1416
+ "model.visual.blocks.8.norm1",
1417
+ "model.visual.blocks.8.norm2",
1418
+ "model.visual.blocks.9.attn.proj",
1419
+ "model.visual.blocks.9.attn.qkv",
1420
+ "model.visual.blocks.9.mlp.linear_fc1",
1421
+ "model.visual.blocks.9.mlp.linear_fc2",
1422
+ "model.visual.blocks.9.norm1",
1423
+ "model.visual.blocks.9.norm2",
1424
+ "model.visual.merger.linear_fc1",
1425
+ "model.visual.merger.linear_fc2",
1426
+ "model.visual.merger.norm",
1427
+ "model.visual.patch_embed.proj",
1428
+ "model.visual.pos_embed",
1429
+ "mtp.fc_embedding",
1430
+ "mtp.fc_hidden",
1431
+ "mtp.hyper_connection_mixer.hc_norm",
1432
+ "mtp.hyper_connection_mixer.input_mix_weight_down",
1433
+ "mtp.hyper_connection_mixer.input_mix_weight_up",
1434
+ "mtp.layers.0.attn_hyper_connection.block_inject_weight",
1435
+ "mtp.layers.0.attn_hyper_connection.hc_norm",
1436
+ "mtp.layers.0.attn_hyper_connection.input_mix_weight_down",
1437
+ "mtp.layers.0.attn_hyper_connection.input_mix_weight_up",
1438
+ "mtp.layers.0.mlp.gate",
1439
+ "mtp.layers.0.mlp.shared_expert.down_proj",
1440
+ "mtp.layers.0.mlp.shared_expert.gate_proj",
1441
+ "mtp.layers.0.mlp.shared_expert.up_proj",
1442
+ "mtp.layers.0.mlp.shared_expert_gate",
1443
+ "mtp.layers.0.mlp_hyper_connection.block_inject_weight",
1444
+ "mtp.layers.0.mlp_hyper_connection.hc_norm",
1445
+ "mtp.layers.0.mlp_hyper_connection.input_mix_weight_down",
1446
+ "mtp.layers.0.mlp_hyper_connection.input_mix_weight_up",
1447
+ "mtp.layers.0.self_attn.indexer.index_qk_proj",
1448
+ "mtp.layers.0.self_attn.indexer.k_layernorm",
1449
+ "mtp.layers.0.self_attn.indexer.q_layernorm",
1450
+ "mtp.layers.0.self_attn.k_norm",
1451
+ "mtp.layers.0.self_attn.k_proj",
1452
+ "mtp.layers.0.self_attn.o_proj",
1453
+ "mtp.layers.0.self_attn.q_norm",
1454
+ "mtp.layers.0.self_attn.q_proj",
1455
+ "mtp.layers.0.self_attn.v_proj",
1456
+ "mtp.pre_fc_norm_embedding",
1457
+ "mtp.pre_fc_norm_hidden"
1458
+ ]
1459
+ }
1460
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 248044,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 248046,
6
+ 248044
7
+ ],
8
+ "pad_token_id": 248044,
9
+ "temperature": 1.0,
10
+ "top_k": 20,
11
+ "top_p": 0.95
12
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64836044b0d06b54a3a1f3fd3cf4ce06ba005fb6319abb100479b7a151f7f44c
3
+ size 102400512288
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dea5f9ebc78eeac6f1c2751758e7365e3ba7fbeef39d723a9caa8206798767d0
3
+ size 4980717000
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0883c2edbae8e2f0bf6240561536a9cb8059ba368e5209911deb1d704d3f24be
3
+ size 4996346000
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:526f2738015ef06df7cd10f15cd811c7a49f6490b4da292f7820056173c252f9
3
+ size 816384304
model.safetensors.index.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94afd2cacf644bdfcba16d1d1d459866f2c4b208835551e78b76930efa862dce
3
+ size 35707593
nvfp4_experts-00001-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f37b5ed37a7e598c3b125c5cf095f860896b0c3c070b8393487984c129fa0d52
3
+ size 4249228128
nvfp4_experts-00002-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e89dace962c46e042f1bcd78889b1159762ac2c7d0ff7e179f68410826ac3796
3
+ size 4249228128
nvfp4_experts-00003-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5043148ee50f5a04b3a8120f54c24ab67ae0863eeb047f6d2b3f30466bf4b5e9
3
+ size 4249228128
nvfp4_experts-00004-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63523da74874b77aae413beea23741b0b974ad5f6b1b1e9e4d1fb2e8ed4363d5
3
+ size 4249240416
nvfp4_experts-00005-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:963bfea776731902876d7fcb47d65fed7448404020f48c71d531e24138cece72
3
+ size 4249246560
nvfp4_experts-00006-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecf4b4e6b50ed701bda0e2708bb983aa98fa98ee10196b0e4d6c3e79f700689f
3
+ size 4249246560
nvfp4_experts-00007-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a06fc550d212d86e69846c9ed0fb92f0c927565d9ddd7bb669d8bb193d55bee1
3
+ size 4249246560
nvfp4_experts-00008-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9f9de0f1de86159e9f1e5e4573e6375e6f786ec941d42d1533395071b24ff52
3
+ size 4249246560
nvfp4_experts-00009-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:369c707829a36045fa6570b1a1e716d70fad2bfb3b3aac90adeccb980eeb470b
3
+ size 4249246560
nvfp4_experts-00010-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dace02ef08e672d7646e95eee078b7268cd7644b849e28bfcdab3f66e6dec58a
3
+ size 4249246560
nvfp4_experts-00011-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:351e24abcd554e790da4a523d73ca6fb0406e5af76a683de91989df4337a2685
3
+ size 4249246560
nvfp4_experts-00012-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:459cc1a0e56b48f67aecd3d48039dd095e2a8805050b8bbc31cf44a9ca33f33c
3
+ size 4249246560
nvfp4_experts-00013-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5af8d781f5077d6504ea58d3acb7ad1a14e8e8eae1bf77ab815cac3f44503701
3
+ size 4249246560
nvfp4_experts-00014-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ec308f1e1bfc14f1759e6e059bb5a4876bbf4b7e0281ee9fc3f5b8ab135032b
3
+ size 4249246560
nvfp4_experts-00015-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a33be5adf5d5a1ea7306ce47c00ebd60465b9e15afeeaee3f0bdd0b94fc080ab
3
+ size 4249246560
nvfp4_experts-00016-of-00016.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76fb6d93b3788ccd371a0b927c98e92e2fd8225e8ab3f356de1f60d7232c7249
3
+ size 4249246560
nvfp4_experts_mtp.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d44e6d705d2313c713e60114e56874adf358ed5f646dc8704bb5be15f5ddbf7
3
+ size 1597441088
preprocessor_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "size": {
3
+ "longest_edge": 16777216,
4
+ "shortest_edge": 65536
5
+ },
6
+ "patch_size": 16,
7
+ "temporal_patch_size": 2,
8
+ "merge_size": 2,
9
+ "image_mean": [
10
+ 0.5,
11
+ 0.5,
12
+ 0.5
13
+ ],
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "processor_class": "Qwen3VLProcessor",
20
+ "image_processor_type": "Qwen2VLImageProcessorFast"
21
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0997f410c57a1f4e53b09e4be8f4a172d90edd9564368fb0847030937229b9f3
3
+ size 12809320
tokenizer_config.json ADDED
@@ -0,0 +1,305 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "248044": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "248045": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "248046": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "248047": {
29
+ "content": "<|object_ref_start|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "248048": {
37
+ "content": "<|object_ref_end|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "248049": {
45
+ "content": "<|box_start|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "248050": {
53
+ "content": "<|box_end|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "248051": {
61
+ "content": "<|quad_start|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "248052": {
69
+ "content": "<|quad_end|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "248053": {
77
+ "content": "<|vision_start|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "248054": {
85
+ "content": "<|vision_end|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "248055": {
93
+ "content": "<|vision_pad|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "248056": {
101
+ "content": "<|image_pad|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "248057": {
109
+ "content": "<|video_pad|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "248058": {
117
+ "content": "<tool_call>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "248059": {
125
+ "content": "</tool_call>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "248060": {
133
+ "content": "<|fim_prefix|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "248061": {
141
+ "content": "<|fim_middle|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "248062": {
149
+ "content": "<|fim_suffix|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "248063": {
157
+ "content": "<|fim_pad|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "248064": {
165
+ "content": "<|repo_name|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "248065": {
173
+ "content": "<|file_sep|>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "248066": {
181
+ "content": "<tool_response>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "248067": {
189
+ "content": "</tool_response>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "248068": {
197
+ "content": "<think>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ },
204
+ "248069": {
205
+ "content": "</think>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": false
211
+ },
212
+ "248070": {
213
+ "content": "<|audio_start|>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "248071": {
221
+ "content": "<|audio_end|>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "248072": {
229
+ "content": "<tts_pad>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "248073": {
237
+ "content": "<tts_text_bos>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "248074": {
245
+ "content": "<tts_text_eod>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "248075": {
253
+ "content": "<tts_text_bos_single>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "248076": {
261
+ "content": "<|audio_pad|>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ }
268
+ },
269
+ "additional_special_tokens": [
270
+ "<|im_start|>",
271
+ "<|im_end|>",
272
+ "<|object_ref_start|>",
273
+ "<|object_ref_end|>",
274
+ "<|box_start|>",
275
+ "<|box_end|>",
276
+ "<|quad_start|>",
277
+ "<|quad_end|>",
278
+ "<|vision_start|>",
279
+ "<|vision_end|>",
280
+ "<|vision_pad|>",
281
+ "<|image_pad|>",
282
+ "<|video_pad|>"
283
+ ],
284
+ "bos_token": null,
285
+ "chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count, is_system_content=false) %}\n {%- if content is string %}\n {{- content }}\n {%- elif content is iterable and content is not mapping %}\n {%- for item in content %}\n {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain images.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set image_count.value = image_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Picture ' ~ image_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|image_pad|><|vision_end|>' }}\n {%- elif 'video' in item or item.type == 'video' %}\n {%- if is_system_content %}\n {{- raise_exception('System message cannot contain videos.') }}\n {%- endif %}\n {%- if do_vision_count %}\n {%- set video_count.value = video_count.value + 1 %}\n {%- endif %}\n {%- if add_vision_id %}\n {{- 'Video ' ~ video_count.value ~ ': ' }}\n {%- endif %}\n {{- '<|vision_start|><|video_pad|><|vision_end|>' }}\n {%- elif 'text' in item %}\n {{- item.text }}\n {%- else %}\n {{- raise_exception('Unexpected item type in content.') }}\n {%- endif %}\n {%- endfor %}\n {%- elif content is none or content is undefined %}\n {{- '' }}\n {%- else %}\n {{- raise_exception('Unexpected content type.') }}\n {%- endif %}\n{%- endmacro %}\n{%- if not messages %}\n {{- raise_exception('No messages provided.') }}\n{%- endif %}\n{%- set reasoning_instructions = '' %}\n{%- if enable_thinking is undefined or enable_thinking is true %}\n {%- set resolved_reasoning_effort = reasoning_effort|default('xhigh') %}\n {%- if resolved_reasoning_effort not in ('xhigh', 'medium', 'low') %}\n {{- raise_exception('Unexpected reasoning effort ' ~ reasoning_effort ~ '. Supported types are xhigh (default), medium, and low.') }}\n {%- endif %}\n {%- if resolved_reasoning_effort == 'xhigh' %}\n {%- set reasoning_instructions = 'Reasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.' %}\n {%- elif resolved_reasoning_effort == 'low' %}\n {%- set reasoning_instructions = 'Reasoning effort is set to low. Keep your thinking brief and focused, moving directly to the conclusion without unnecessary elaboration.' %}\n {%- endif %}\n{%- endif %}\n{%- if tools and tools is iterable and tools is not mapping %}\n {{- '<|im_start|>system\\n' }}\n {%- if reasoning_instructions %}\n {{- reasoning_instructions + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\" }}\n {{- '\\n\\nIf you choose to call a function ONLY reply in the following format with NO suffix:\\n\\n<tool_call>\\n<function=example_function_name>\\n<parameter=example_parameter_1>\\nvalue_1\\n</parameter>\\n<parameter=example_parameter_2>\\nThis is the value for the second parameter\\nthat can span\\nmultiple lines\\n</parameter>\\n</function>\\n</tool_call>\\n\\n<IMPORTANT>\\nReminder:\\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\\n- Required parameters MUST be specified\\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\\n</IMPORTANT>' }}\n {%- if messages[0].role == 'system' %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {%- if content %}\n {{- '\\n\\n' + content }}\n {%- endif %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {%- set content = render_content(messages[0].content, false, true)|trim %}\n {%- if content %}\n {{- '<|im_start|>system\\n' + (reasoning_instructions + '\\n\\n' if reasoning_instructions else '') + content + '<|im_end|>\\n' }}\n {%- elif reasoning_instructions %}\n {{- '<|im_start|>system\\n' + reasoning_instructions + '<|im_end|>\\n' }}\n {%- endif %}\n {%- elif reasoning_instructions %}\n {{- '<|im_start|>system\\n' + reasoning_instructions + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" %}\n {%- set content = render_content(message.content, false)|trim %}\n {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if ns.multi_step_tool %}\n {{- raise_exception('No user query found in messages.') }}\n{%- endif %}\n{%- for message in messages %}\n {%- set content = render_content(message.content, true)|trim %}\n {%- if message.role == \"system\" %}\n {%- if not loop.first %}\n {{- raise_exception('System message must be at the beginning.') }}\n {%- endif %}\n {%- elif message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- endif %}\n {%- set reasoning_content = reasoning_content|trim %}\n {%- if preserve_thinking is undefined or preserve_thinking is true or loop.index0 > ns.last_query_index %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content + '\\n</think>\\n\\n' + content }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {%- if loop.first %}\n {%- if content|trim %}\n {{- '\\n\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- else %}\n {{- '<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- endif %}\n {%- else %}\n {{- '\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- endif %}\n {%- if tool_call.arguments is defined and tool_call.arguments != '' %}\n {%- for args_name, args_value in tool_call.arguments|items %}\n {{- '<parameter=' + args_name + '>\\n' }}\n {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}\n {{- args_value }}\n {{- '\\n</parameter>\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '</function>\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- content }}\n {{- '\\n</tool_response>' }}\n {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n {{- '<|im_end|>\\n' }}\n {%- elif loop.last %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- else %}\n {{- raise_exception('Unexpected message role.') }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- else %}\n {{- '<think>\\n' }}\n {%- endif %}\n{%- endif %}",
286
+ "clean_up_tokenization_spaces": false,
287
+ "eos_token": "<|im_end|>",
288
+ "errors": "replace",
289
+ "model_max_length": 262144,
290
+ "pad_token": "<|endoftext|>",
291
+ "split_special_tokens": false,
292
+ "tokenizer_class": "Qwen2Tokenizer",
293
+ "unk_token": null,
294
+ "add_bos_token": false,
295
+ "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+",
296
+ "extra_special_tokens": {
297
+ "audio_bos_token": "<|audio_start|>",
298
+ "audio_eos_token": "<|audio_end|>",
299
+ "audio_token": "<|audio_pad|>",
300
+ "image_token": "<|image_pad|>",
301
+ "video_token": "<|video_pad|>",
302
+ "vision_bos_token": "<|vision_start|>",
303
+ "vision_eos_token": "<|vision_end|>"
304
+ }
305
+ }
video_preprocessor_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "size": {
3
+ "longest_edge": 25165824,
4
+ "shortest_edge": 4096
5
+ },
6
+ "patch_size": 16,
7
+ "temporal_patch_size": 2,
8
+ "merge_size": 2,
9
+ "image_mean": [
10
+ 0.5,
11
+ 0.5,
12
+ 0.5
13
+ ],
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "processor_class": "Qwen3VLProcessor",
20
+ "video_processor_type": "Qwen3VLVideoProcessor"
21
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff