Hugging Face's logo

manishkumar2101114
/
Qwen-Qwen3.6-35B-A3B-FP8

Safetensors
qwen3_5_moe
fp8
Model card Files
xet
 Community
manishkumar2101114 commited on
Commit
458aace
·
verified ·
1 Parent(s): d8d287e

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +1 -0
  2. chat_template.jinja +154 -0
  3. config.json +778 -0
  4. generation_config.json +12 -0
  5. layers-0.safetensors +3 -0
  6. layers-1.safetensors +3 -0
  7. layers-10.safetensors +3 -0
  8. layers-11.safetensors +3 -0
  9. layers-12.safetensors +3 -0
  10. layers-13.safetensors +3 -0
  11. layers-14.safetensors +3 -0
  12. layers-15.safetensors +3 -0
  13. layers-16.safetensors +3 -0
  14. layers-17.safetensors +3 -0
  15. layers-18.safetensors +3 -0
  16. layers-19.safetensors +3 -0
  17. layers-2.safetensors +3 -0
  18. layers-20.safetensors +3 -0
  19. layers-21.safetensors +3 -0
  20. layers-22.safetensors +3 -0
  21. layers-23.safetensors +3 -0
  22. layers-24.safetensors +3 -0
  23. layers-25.safetensors +3 -0
  24. layers-26.safetensors +3 -0
  25. layers-27.safetensors +3 -0
  26. layers-28.safetensors +3 -0
  27. layers-29.safetensors +3 -0
  28. layers-3.safetensors +3 -0
  29. layers-30.safetensors +3 -0
  30. layers-31.safetensors +3 -0
  31. layers-32.safetensors +3 -0
  32. layers-33.safetensors +3 -0
  33. layers-34.safetensors +3 -0
  34. layers-35.safetensors +3 -0
  35. layers-36.safetensors +3 -0
  36. layers-37.safetensors +3 -0
  37. layers-38.safetensors +3 -0
  38. layers-39.safetensors +3 -0
  39. layers-4.safetensors +3 -0
  40. layers-5.safetensors +3 -0
  41. layers-6.safetensors +3 -0
  42. layers-7.safetensors +3 -0
  43. layers-8.safetensors +3 -0
  44. layers-9.safetensors +3 -0
  45. model.safetensors.index.json +0 -0
  46. mtp.safetensors +3 -0
  47. outside.safetensors +3 -0
  48. preprocessor_config.json +21 -0
  49. tokenizer.json +3 -0
  50. tokenizer_config.json +305 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
chat_template.jinja ADDED
@@ -0,0 +1,154 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ {%- if tools and tools is iterable and tools is not mapping %}
46
+ {{- '<|im_start|>system\n' }}
47
+ {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
48
+ {%- for tool in tools %}
49
+ {{- "\n" }}
50
+ {{- tool | tojson }}
51
+ {%- endfor %}
52
+ {{- "\n</tools>" }}
53
+ {{- '\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>' }}
54
+ {%- if messages[0].role == 'system' %}
55
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
56
+ {%- if content %}
57
+ {{- '\n\n' + content }}
58
+ {%- endif %}
59
+ {%- endif %}
60
+ {{- '<|im_end|>\n' }}
61
+ {%- else %}
62
+ {%- if messages[0].role == 'system' %}
63
+ {%- set content = render_content(messages[0].content, false, true)|trim %}
64
+ {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
65
+ {%- endif %}
66
+ {%- endif %}
67
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
68
+ {%- for message in messages[::-1] %}
69
+ {%- set index = (messages|length - 1) - loop.index0 %}
70
+ {%- if ns.multi_step_tool and message.role == "user" %}
71
+ {%- set content = render_content(message.content, false)|trim %}
72
+ {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
73
+ {%- set ns.multi_step_tool = false %}
74
+ {%- set ns.last_query_index = index %}
75
+ {%- endif %}
76
+ {%- endif %}
77
+ {%- endfor %}
78
+ {%- if ns.multi_step_tool %}
79
+ {{- raise_exception('No user query found in messages.') }}
80
+ {%- endif %}
81
+ {%- for message in messages %}
82
+ {%- set content = render_content(message.content, true)|trim %}
83
+ {%- if message.role == "system" %}
84
+ {%- if not loop.first %}
85
+ {{- raise_exception('System message must be at the beginning.') }}
86
+ {%- endif %}
87
+ {%- elif message.role == "user" %}
88
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
89
+ {%- elif message.role == "assistant" %}
90
+ {%- set reasoning_content = '' %}
91
+ {%- if message.reasoning_content is string %}
92
+ {%- set reasoning_content = message.reasoning_content %}
93
+ {%- else %}
94
+ {%- if '</think>' in content %}
95
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
96
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
97
+ {%- endif %}
98
+ {%- endif %}
99
+ {%- set reasoning_content = reasoning_content|trim %}
100
+ {%- if (preserve_thinking is defined and preserve_thinking is true) or (loop.index0 > ns.last_query_index) %}
101
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
102
+ {%- else %}
103
+ {{- '<|im_start|>' + message.role + '\n' + content }}
104
+ {%- endif %}
105
+ {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
106
+ {%- for tool_call in message.tool_calls %}
107
+ {%- if tool_call.function is defined %}
108
+ {%- set tool_call = tool_call.function %}
109
+ {%- endif %}
110
+ {%- if loop.first %}
111
+ {%- if content|trim %}
112
+ {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
113
+ {%- else %}
114
+ {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
115
+ {%- endif %}
116
+ {%- else %}
117
+ {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
118
+ {%- endif %}
119
+ {%- if tool_call.arguments is defined %}
120
+ {%- for args_name, args_value in tool_call.arguments|items %}
121
+ {{- '<parameter=' + args_name + '>\n' }}
122
+ {%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
123
+ {{- args_value }}
124
+ {{- '\n</parameter>\n' }}
125
+ {%- endfor %}
126
+ {%- endif %}
127
+ {{- '</function>\n</tool_call>' }}
128
+ {%- endfor %}
129
+ {%- endif %}
130
+ {{- '<|im_end|>\n' }}
131
+ {%- elif message.role == "tool" %}
132
+ {%- if loop.previtem and loop.previtem.role != "tool" %}
133
+ {{- '<|im_start|>user' }}
134
+ {%- endif %}
135
+ {{- '\n<tool_response>\n' }}
136
+ {{- content }}
137
+ {{- '\n</tool_response>' }}
138
+ {%- if not loop.last and loop.nextitem.role != "tool" %}
139
+ {{- '<|im_end|>\n' }}
140
+ {%- elif loop.last %}
141
+ {{- '<|im_end|>\n' }}
142
+ {%- endif %}
143
+ {%- else %}
144
+ {{- raise_exception('Unexpected message role.') }}
145
+ {%- endif %}
146
+ {%- endfor %}
147
+ {%- if add_generation_prompt %}
148
+ {{- '<|im_start|>assistant\n' }}
149
+ {%- if enable_thinking is defined and enable_thinking is false %}
150
+ {{- '<think>\n\n</think>\n\n' }}
151
+ {%- else %}
152
+ {{- '<think>\n' }}
153
+ {%- endif %}
154
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,778 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5MoeForConditionalGeneration"
4
+ ],
5
+ "image_token_id": 248056,
6
+ "model_type": "qwen3_5_moe",
7
+ "text_config": {
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "attn_output_gate": true,
11
+ "bos_token_id": 248044,
12
+ "dtype": "bfloat16",
13
+ "eos_token_id": 248044,
14
+ "full_attention_interval": 4,
15
+ "head_dim": 256,
16
+ "hidden_act": "silu",
17
+ "hidden_size": 2048,
18
+ "initializer_range": 0.02,
19
+ "layer_types": [
20
+ "linear_attention",
21
+ "linear_attention",
22
+ "linear_attention",
23
+ "full_attention",
24
+ "linear_attention",
25
+ "linear_attention",
26
+ "linear_attention",
27
+ "full_attention",
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
+ ],
61
+ "linear_conv_kernel_dim": 4,
62
+ "linear_key_head_dim": 128,
63
+ "linear_num_key_heads": 16,
64
+ "linear_num_value_heads": 32,
65
+ "linear_value_head_dim": 128,
66
+ "mamba_ssm_dtype": "float32",
67
+ "max_position_embeddings": 262144,
68
+ "model_type": "qwen3_5_moe_text",
69
+ "moe_intermediate_size": 512,
70
+ "mtp_num_hidden_layers": 1,
71
+ "mtp_use_dedicated_embeddings": false,
72
+ "num_attention_heads": 16,
73
+ "num_experts": 256,
74
+ "num_experts_per_tok": 8,
75
+ "num_hidden_layers": 40,
76
+ "num_key_value_heads": 2,
77
+ "output_router_logits": false,
78
+ "pad_token_id": null,
79
+ "partial_rotary_factor": 0.25,
80
+ "rms_norm_eps": 1e-06,
81
+ "rope_parameters": {
82
+ "mrope_interleaved": true,
83
+ "mrope_section": [
84
+ 11,
85
+ 11,
86
+ 10
87
+ ],
88
+ "partial_rotary_factor": 0.25,
89
+ "rope_theta": 10000000,
90
+ "rope_type": "default"
91
+ },
92
+ "router_aux_loss_coef": 0.001,
93
+ "shared_expert_intermediate_size": 512,
94
+ "tie_word_embeddings": false,
95
+ "use_cache": true,
96
+ "vocab_size": 248320
97
+ },
98
+ "tie_word_embeddings": false,
99
+ "transformers_version": "4.57.1",
100
+ "video_token_id": 248057,
101
+ "vision_config": {
102
+ "deepstack_visual_indexes": [],
103
+ "depth": 27,
104
+ "hidden_act": "gelu_pytorch_tanh",
105
+ "hidden_size": 1152,
106
+ "in_channels": 3,
107
+ "initializer_range": 0.02,
108
+ "intermediate_size": 4304,
109
+ "model_type": "qwen3_5_moe",
110
+ "num_heads": 16,
111
+ "num_position_embeddings": 2304,
112
+ "out_hidden_size": 2048,
113
+ "patch_size": 16,
114
+ "spatial_merge_size": 2,
115
+ "temporal_patch_size": 2
116
+ },
117
+ "vision_end_token_id": 248054,
118
+ "vision_start_token_id": 248053,
119
+ "quantization_config": {
120
+ "activation_scheme": "dynamic",
121
+ "fmt": "e4m3",
122
+ "quant_method": "fp8",
123
+ "modules_to_not_convert": [
124
+ "model.visual.blocks.0.attn.proj",
125
+ "model.visual.blocks.0.attn.qkv",
126
+ "model.visual.blocks.0.mlp.linear_fc1",
127
+ "model.visual.blocks.0.mlp.linear_fc2",
128
+ "visual.blocks.0.attn.proj",
129
+ "visual.blocks.0.attn.qkv_proj",
130
+ "visual.blocks.0.mlp.linear_fc1",
131
+ "visual.blocks.0.mlp.linear_fc2",
132
+ "model.visual.blocks.1.attn.proj",
133
+ "model.visual.blocks.1.attn.qkv",
134
+ "model.visual.blocks.1.mlp.linear_fc1",
135
+ "model.visual.blocks.1.mlp.linear_fc2",
136
+ "visual.blocks.1.attn.proj",
137
+ "visual.blocks.1.attn.qkv_proj",
138
+ "visual.blocks.1.mlp.linear_fc1",
139
+ "visual.blocks.1.mlp.linear_fc2",
140
+ "model.visual.blocks.2.attn.proj",
141
+ "model.visual.blocks.2.attn.qkv",
142
+ "model.visual.blocks.2.mlp.linear_fc1",
143
+ "model.visual.blocks.2.mlp.linear_fc2",
144
+ "visual.blocks.2.attn.proj",
145
+ "visual.blocks.2.attn.qkv_proj",
146
+ "visual.blocks.2.mlp.linear_fc1",
147
+ "visual.blocks.2.mlp.linear_fc2",
148
+ "model.visual.blocks.3.attn.proj",
149
+ "model.visual.blocks.3.attn.qkv",
150
+ "model.visual.blocks.3.mlp.linear_fc1",
151
+ "model.visual.blocks.3.mlp.linear_fc2",
152
+ "visual.blocks.3.attn.proj",
153
+ "visual.blocks.3.attn.qkv_proj",
154
+ "visual.blocks.3.mlp.linear_fc1",
155
+ "visual.blocks.3.mlp.linear_fc2",
156
+ "model.visual.blocks.4.attn.proj",
157
+ "model.visual.blocks.4.attn.qkv",
158
+ "model.visual.blocks.4.mlp.linear_fc1",
159
+ "model.visual.blocks.4.mlp.linear_fc2",
160
+ "visual.blocks.4.attn.proj",
161
+ "visual.blocks.4.attn.qkv_proj",
162
+ "visual.blocks.4.mlp.linear_fc1",
163
+ "visual.blocks.4.mlp.linear_fc2",
164
+ "model.visual.blocks.5.attn.proj",
165
+ "model.visual.blocks.5.attn.qkv",
166
+ "model.visual.blocks.5.mlp.linear_fc1",
167
+ "model.visual.blocks.5.mlp.linear_fc2",
168
+ "visual.blocks.5.attn.proj",
169
+ "visual.blocks.5.attn.qkv_proj",
170
+ "visual.blocks.5.mlp.linear_fc1",
171
+ "visual.blocks.5.mlp.linear_fc2",
172
+ "model.visual.blocks.6.attn.proj",
173
+ "model.visual.blocks.6.attn.qkv",
174
+ "model.visual.blocks.6.mlp.linear_fc1",
175
+ "model.visual.blocks.6.mlp.linear_fc2",
176
+ "visual.blocks.6.attn.proj",
177
+ "visual.blocks.6.attn.qkv_proj",
178
+ "visual.blocks.6.mlp.linear_fc1",
179
+ "visual.blocks.6.mlp.linear_fc2",
180
+ "model.visual.blocks.7.attn.proj",
181
+ "model.visual.blocks.7.attn.qkv",
182
+ "model.visual.blocks.7.mlp.linear_fc1",
183
+ "model.visual.blocks.7.mlp.linear_fc2",
184
+ "visual.blocks.7.attn.proj",
185
+ "visual.blocks.7.attn.qkv_proj",
186
+ "visual.blocks.7.mlp.linear_fc1",
187
+ "visual.blocks.7.mlp.linear_fc2",
188
+ "model.visual.blocks.8.attn.proj",
189
+ "model.visual.blocks.8.attn.qkv",
190
+ "model.visual.blocks.8.mlp.linear_fc1",
191
+ "model.visual.blocks.8.mlp.linear_fc2",
192
+ "visual.blocks.8.attn.proj",
193
+ "visual.blocks.8.attn.qkv_proj",
194
+ "visual.blocks.8.mlp.linear_fc1",
195
+ "visual.blocks.8.mlp.linear_fc2",
196
+ "model.visual.blocks.9.attn.proj",
197
+ "model.visual.blocks.9.attn.qkv",
198
+ "model.visual.blocks.9.mlp.linear_fc1",
199
+ "model.visual.blocks.9.mlp.linear_fc2",
200
+ "visual.blocks.9.attn.proj",
201
+ "visual.blocks.9.attn.qkv_proj",
202
+ "visual.blocks.9.mlp.linear_fc1",
203
+ "visual.blocks.9.mlp.linear_fc2",
204
+ "model.visual.blocks.10.attn.proj",
205
+ "model.visual.blocks.10.attn.qkv",
206
+ "model.visual.blocks.10.mlp.linear_fc1",
207
+ "model.visual.blocks.10.mlp.linear_fc2",
208
+ "visual.blocks.10.attn.proj",
209
+ "visual.blocks.10.attn.qkv_proj",
210
+ "visual.blocks.10.mlp.linear_fc1",
211
+ "visual.blocks.10.mlp.linear_fc2",
212
+ "model.visual.blocks.11.attn.proj",
213
+ "model.visual.blocks.11.attn.qkv",
214
+ "model.visual.blocks.11.mlp.linear_fc1",
215
+ "model.visual.blocks.11.mlp.linear_fc2",
216
+ "visual.blocks.11.attn.proj",
217
+ "visual.blocks.11.attn.qkv_proj",
218
+ "visual.blocks.11.mlp.linear_fc1",
219
+ "visual.blocks.11.mlp.linear_fc2",
220
+ "model.visual.blocks.12.attn.proj",
221
+ "model.visual.blocks.12.attn.qkv",
222
+ "model.visual.blocks.12.mlp.linear_fc1",
223
+ "model.visual.blocks.12.mlp.linear_fc2",
224
+ "visual.blocks.12.attn.proj",
225
+ "visual.blocks.12.attn.qkv_proj",
226
+ "visual.blocks.12.mlp.linear_fc1",
227
+ "visual.blocks.12.mlp.linear_fc2",
228
+ "model.visual.blocks.13.attn.proj",
229
+ "model.visual.blocks.13.attn.qkv",
230
+ "model.visual.blocks.13.mlp.linear_fc1",
231
+ "model.visual.blocks.13.mlp.linear_fc2",
232
+ "visual.blocks.13.attn.proj",
233
+ "visual.blocks.13.attn.qkv_proj",
234
+ "visual.blocks.13.mlp.linear_fc1",
235
+ "visual.blocks.13.mlp.linear_fc2",
236
+ "model.visual.blocks.14.attn.proj",
237
+ "model.visual.blocks.14.attn.qkv",
238
+ "model.visual.blocks.14.mlp.linear_fc1",
239
+ "model.visual.blocks.14.mlp.linear_fc2",
240
+ "visual.blocks.14.attn.proj",
241
+ "visual.blocks.14.attn.qkv_proj",
242
+ "visual.blocks.14.mlp.linear_fc1",
243
+ "visual.blocks.14.mlp.linear_fc2",
244
+ "model.visual.blocks.15.attn.proj",
245
+ "model.visual.blocks.15.attn.qkv",
246
+ "model.visual.blocks.15.mlp.linear_fc1",
247
+ "model.visual.blocks.15.mlp.linear_fc2",
248
+ "visual.blocks.15.attn.proj",
249
+ "visual.blocks.15.attn.qkv_proj",
250
+ "visual.blocks.15.mlp.linear_fc1",
251
+ "visual.blocks.15.mlp.linear_fc2",
252
+ "model.visual.blocks.16.attn.proj",
253
+ "model.visual.blocks.16.attn.qkv",
254
+ "model.visual.blocks.16.mlp.linear_fc1",
255
+ "model.visual.blocks.16.mlp.linear_fc2",
256
+ "visual.blocks.16.attn.proj",
257
+ "visual.blocks.16.attn.qkv_proj",
258
+ "visual.blocks.16.mlp.linear_fc1",
259
+ "visual.blocks.16.mlp.linear_fc2",
260
+ "model.visual.blocks.17.attn.proj",
261
+ "model.visual.blocks.17.attn.qkv",
262
+ "model.visual.blocks.17.mlp.linear_fc1",
263
+ "model.visual.blocks.17.mlp.linear_fc2",
264
+ "visual.blocks.17.attn.proj",
265
+ "visual.blocks.17.attn.qkv_proj",
266
+ "visual.blocks.17.mlp.linear_fc1",
267
+ "visual.blocks.17.mlp.linear_fc2",
268
+ "model.visual.blocks.18.attn.proj",
269
+ "model.visual.blocks.18.attn.qkv",
270
+ "model.visual.blocks.18.mlp.linear_fc1",
271
+ "model.visual.blocks.18.mlp.linear_fc2",
272
+ "visual.blocks.18.attn.proj",
273
+ "visual.blocks.18.attn.qkv_proj",
274
+ "visual.blocks.18.mlp.linear_fc1",
275
+ "visual.blocks.18.mlp.linear_fc2",
276
+ "model.visual.blocks.19.attn.proj",
277
+ "model.visual.blocks.19.attn.qkv",
278
+ "model.visual.blocks.19.mlp.linear_fc1",
279
+ "model.visual.blocks.19.mlp.linear_fc2",
280
+ "visual.blocks.19.attn.proj",
281
+ "visual.blocks.19.attn.qkv_proj",
282
+ "visual.blocks.19.mlp.linear_fc1",
283
+ "visual.blocks.19.mlp.linear_fc2",
284
+ "model.visual.blocks.20.attn.proj",
285
+ "model.visual.blocks.20.attn.qkv",
286
+ "model.visual.blocks.20.mlp.linear_fc1",
287
+ "model.visual.blocks.20.mlp.linear_fc2",
288
+ "visual.blocks.20.attn.proj",
289
+ "visual.blocks.20.attn.qkv_proj",
290
+ "visual.blocks.20.mlp.linear_fc1",
291
+ "visual.blocks.20.mlp.linear_fc2",
292
+ "model.visual.blocks.21.attn.proj",
293
+ "model.visual.blocks.21.attn.qkv",
294
+ "model.visual.blocks.21.mlp.linear_fc1",
295
+ "model.visual.blocks.21.mlp.linear_fc2",
296
+ "visual.blocks.21.attn.proj",
297
+ "visual.blocks.21.attn.qkv_proj",
298
+ "visual.blocks.21.mlp.linear_fc1",
299
+ "visual.blocks.21.mlp.linear_fc2",
300
+ "model.visual.blocks.22.attn.proj",
301
+ "model.visual.blocks.22.attn.qkv",
302
+ "model.visual.blocks.22.mlp.linear_fc1",
303
+ "model.visual.blocks.22.mlp.linear_fc2",
304
+ "visual.blocks.22.attn.proj",
305
+ "visual.blocks.22.attn.qkv_proj",
306
+ "visual.blocks.22.mlp.linear_fc1",
307
+ "visual.blocks.22.mlp.linear_fc2",
308
+ "model.visual.blocks.23.attn.proj",
309
+ "model.visual.blocks.23.attn.qkv",
310
+ "model.visual.blocks.23.mlp.linear_fc1",
311
+ "model.visual.blocks.23.mlp.linear_fc2",
312
+ "visual.blocks.23.attn.proj",
313
+ "visual.blocks.23.attn.qkv_proj",
314
+ "visual.blocks.23.mlp.linear_fc1",
315
+ "visual.blocks.23.mlp.linear_fc2",
316
+ "model.visual.blocks.24.attn.proj",
317
+ "model.visual.blocks.24.attn.qkv",
318
+ "model.visual.blocks.24.mlp.linear_fc1",
319
+ "model.visual.blocks.24.mlp.linear_fc2",
320
+ "visual.blocks.24.attn.proj",
321
+ "visual.blocks.24.attn.qkv_proj",
322
+ "visual.blocks.24.mlp.linear_fc1",
323
+ "visual.blocks.24.mlp.linear_fc2",
324
+ "model.visual.blocks.25.attn.proj",
325
+ "model.visual.blocks.25.attn.qkv",
326
+ "model.visual.blocks.25.mlp.linear_fc1",
327
+ "model.visual.blocks.25.mlp.linear_fc2",
328
+ "visual.blocks.25.attn.proj",
329
+ "visual.blocks.25.attn.qkv_proj",
330
+ "visual.blocks.25.mlp.linear_fc1",
331
+ "visual.blocks.25.mlp.linear_fc2",
332
+ "model.visual.blocks.26.attn.proj",
333
+ "model.visual.blocks.26.attn.qkv",
334
+ "model.visual.blocks.26.mlp.linear_fc1",
335
+ "model.visual.blocks.26.mlp.linear_fc2",
336
+ "visual.blocks.26.attn.proj",
337
+ "visual.blocks.26.attn.qkv_proj",
338
+ "visual.blocks.26.mlp.linear_fc1",
339
+ "visual.blocks.26.mlp.linear_fc2",
340
+ "model.visual.deepstack_merger_list.0.linear_fc1",
341
+ "model.visual.deepstack_merger_list.0.linear_fc2",
342
+ "model.visual.deepstack_merger_list.0.norm",
343
+ "visual.deepstack_merger_list.0.linear_fc1",
344
+ "visual.deepstack_merger_list.0.linear_fc2",
345
+ "visual.deepstack_merger_list.0.norm",
346
+ "model.visual.deepstack_merger_list.1.linear_fc1",
347
+ "model.visual.deepstack_merger_list.1.linear_fc2",
348
+ "model.visual.deepstack_merger_list.1.norm",
349
+ "visual.deepstack_merger_list.1.linear_fc1",
350
+ "visual.deepstack_merger_list.1.linear_fc2",
351
+ "visual.deepstack_merger_list.1.norm",
352
+ "model.visual.deepstack_merger_list.2.linear_fc1",
353
+ "model.visual.deepstack_merger_list.2.linear_fc2",
354
+ "model.visual.deepstack_merger_list.2.norm",
355
+ "visual.deepstack_merger_list.2.linear_fc1",
356
+ "visual.deepstack_merger_list.2.linear_fc2",
357
+ "visual.deepstack_merger_list.2.norm",
358
+ "model.visual.merger.linear_fc1",
359
+ "model.visual.merger.linear_fc2",
360
+ "model.visual.merger.norm",
361
+ "model.visual.patch_embed.proj",
362
+ "model.visual.pos_embed",
363
+ "visual.merger.linear_fc1",
364
+ "visual.merger.linear_fc2",
365
+ "visual.merger.norm",
366
+ "visual.patch_embed.proj",
367
+ "visual.pos_embed",
368
+ "visual",
369
+ "model.visual",
370
+ "lm_head",
371
+ "model.embed_tokens",
372
+ "model.language_model.layers.0.input_layernorm",
373
+ "model.language_model.layers.0.mlp.shared_expert_gate",
374
+ "model.language_model.layers.0.post_attention_layernorm",
375
+ "model.language_model.layers.0.mlp.gate",
376
+ "model.language_model.layers.0.linear_attn.A_log",
377
+ "model.language_model.layers.0.linear_attn.conv1d",
378
+ "model.language_model.layers.0.linear_attn.dt_bias",
379
+ "model.language_model.layers.0.linear_attn.in_proj_ba",
380
+ "model.language_model.layers.0.linear_attn.in_proj_b",
381
+ "model.language_model.layers.0.linear_attn.in_proj_a",
382
+ "model.language_model.layers.0.linear_attn.norm",
383
+ "model.language_model.layers.1.input_layernorm",
384
+ "model.language_model.layers.1.mlp.shared_expert_gate",
385
+ "model.language_model.layers.1.post_attention_layernorm",
386
+ "model.language_model.layers.1.mlp.gate",
387
+ "model.language_model.layers.1.linear_attn.A_log",
388
+ "model.language_model.layers.1.linear_attn.conv1d",
389
+ "model.language_model.layers.1.linear_attn.dt_bias",
390
+ "model.language_model.layers.1.linear_attn.in_proj_ba",
391
+ "model.language_model.layers.1.linear_attn.in_proj_b",
392
+ "model.language_model.layers.1.linear_attn.in_proj_a",
393
+ "model.language_model.layers.1.linear_attn.norm",
394
+ "model.language_model.layers.2.input_layernorm",
395
+ "model.language_model.layers.2.mlp.shared_expert_gate",
396
+ "model.language_model.layers.2.post_attention_layernorm",
397
+ "model.language_model.layers.2.mlp.gate",
398
+ "model.language_model.layers.2.linear_attn.A_log",
399
+ "model.language_model.layers.2.linear_attn.conv1d",
400
+ "model.language_model.layers.2.linear_attn.dt_bias",
401
+ "model.language_model.layers.2.linear_attn.in_proj_ba",
402
+ "model.language_model.layers.2.linear_attn.in_proj_b",
403
+ "model.language_model.layers.2.linear_attn.in_proj_a",
404
+ "model.language_model.layers.2.linear_attn.norm",
405
+ "model.language_model.layers.3.input_layernorm",
406
+ "model.language_model.layers.3.mlp.shared_expert_gate",
407
+ "model.language_model.layers.3.post_attention_layernorm",
408
+ "model.language_model.layers.3.mlp.gate",
409
+ "model.language_model.layers.3.self_attn.k_norm",
410
+ "model.language_model.layers.3.self_attn.q_norm",
411
+ "model.language_model.layers.4.input_layernorm",
412
+ "model.language_model.layers.4.mlp.shared_expert_gate",
413
+ "model.language_model.layers.4.post_attention_layernorm",
414
+ "model.language_model.layers.4.mlp.gate",
415
+ "model.language_model.layers.4.linear_attn.A_log",
416
+ "model.language_model.layers.4.linear_attn.conv1d",
417
+ "model.language_model.layers.4.linear_attn.dt_bias",
418
+ "model.language_model.layers.4.linear_attn.in_proj_ba",
419
+ "model.language_model.layers.4.linear_attn.in_proj_b",
420
+ "model.language_model.layers.4.linear_attn.in_proj_a",
421
+ "model.language_model.layers.4.linear_attn.norm",
422
+ "model.language_model.layers.5.input_layernorm",
423
+ "model.language_model.layers.5.mlp.shared_expert_gate",
424
+ "model.language_model.layers.5.post_attention_layernorm",
425
+ "model.language_model.layers.5.mlp.gate",
426
+ "model.language_model.layers.5.linear_attn.A_log",
427
+ "model.language_model.layers.5.linear_attn.conv1d",
428
+ "model.language_model.layers.5.linear_attn.dt_bias",
429
+ "model.language_model.layers.5.linear_attn.in_proj_ba",
430
+ "model.language_model.layers.5.linear_attn.in_proj_b",
431
+ "model.language_model.layers.5.linear_attn.in_proj_a",
432
+ "model.language_model.layers.5.linear_attn.norm",
433
+ "model.language_model.layers.6.input_layernorm",
434
+ "model.language_model.layers.6.mlp.shared_expert_gate",
435
+ "model.language_model.layers.6.post_attention_layernorm",
436
+ "model.language_model.layers.6.mlp.gate",
437
+ "model.language_model.layers.6.linear_attn.A_log",
438
+ "model.language_model.layers.6.linear_attn.conv1d",
439
+ "model.language_model.layers.6.linear_attn.dt_bias",
440
+ "model.language_model.layers.6.linear_attn.in_proj_ba",
441
+ "model.language_model.layers.6.linear_attn.in_proj_b",
442
+ "model.language_model.layers.6.linear_attn.in_proj_a",
443
+ "model.language_model.layers.6.linear_attn.norm",
444
+ "model.language_model.layers.7.input_layernorm",
445
+ "model.language_model.layers.7.mlp.shared_expert_gate",
446
+ "model.language_model.layers.7.post_attention_layernorm",
447
+ "model.language_model.layers.7.mlp.gate",
448
+ "model.language_model.layers.7.self_attn.k_norm",
449
+ "model.language_model.layers.7.self_attn.q_norm",
450
+ "model.language_model.layers.8.input_layernorm",
451
+ "model.language_model.layers.8.mlp.shared_expert_gate",
452
+ "model.language_model.layers.8.post_attention_layernorm",
453
+ "model.language_model.layers.8.mlp.gate",
454
+ "model.language_model.layers.8.linear_attn.A_log",
455
+ "model.language_model.layers.8.linear_attn.conv1d",
456
+ "model.language_model.layers.8.linear_attn.dt_bias",
457
+ "model.language_model.layers.8.linear_attn.in_proj_ba",
458
+ "model.language_model.layers.8.linear_attn.in_proj_b",
459
+ "model.language_model.layers.8.linear_attn.in_proj_a",
460
+ "model.language_model.layers.8.linear_attn.norm",
461
+ "model.language_model.layers.9.input_layernorm",
462
+ "model.language_model.layers.9.mlp.shared_expert_gate",
463
+ "model.language_model.layers.9.post_attention_layernorm",
464
+ "model.language_model.layers.9.mlp.gate",
465
+ "model.language_model.layers.9.linear_attn.A_log",
466
+ "model.language_model.layers.9.linear_attn.conv1d",
467
+ "model.language_model.layers.9.linear_attn.dt_bias",
468
+ "model.language_model.layers.9.linear_attn.in_proj_ba",
469
+ "model.language_model.layers.9.linear_attn.in_proj_b",
470
+ "model.language_model.layers.9.linear_attn.in_proj_a",
471
+ "model.language_model.layers.9.linear_attn.norm",
472
+ "model.language_model.layers.10.input_layernorm",
473
+ "model.language_model.layers.10.mlp.shared_expert_gate",
474
+ "model.language_model.layers.10.post_attention_layernorm",
475
+ "model.language_model.layers.10.mlp.gate",
476
+ "model.language_model.layers.10.linear_attn.A_log",
477
+ "model.language_model.layers.10.linear_attn.conv1d",
478
+ "model.language_model.layers.10.linear_attn.dt_bias",
479
+ "model.language_model.layers.10.linear_attn.in_proj_ba",
480
+ "model.language_model.layers.10.linear_attn.in_proj_b",
481
+ "model.language_model.layers.10.linear_attn.in_proj_a",
482
+ "model.language_model.layers.10.linear_attn.norm",
483
+ "model.language_model.layers.11.input_layernorm",
484
+ "model.language_model.layers.11.mlp.shared_expert_gate",
485
+ "model.language_model.layers.11.post_attention_layernorm",
486
+ "model.language_model.layers.11.mlp.gate",
487
+ "model.language_model.layers.11.self_attn.k_norm",
488
+ "model.language_model.layers.11.self_attn.q_norm",
489
+ "model.language_model.layers.12.input_layernorm",
490
+ "model.language_model.layers.12.mlp.shared_expert_gate",
491
+ "model.language_model.layers.12.post_attention_layernorm",
492
+ "model.language_model.layers.12.mlp.gate",
493
+ "model.language_model.layers.12.linear_attn.A_log",
494
+ "model.language_model.layers.12.linear_attn.conv1d",
495
+ "model.language_model.layers.12.linear_attn.dt_bias",
496
+ "model.language_model.layers.12.linear_attn.in_proj_ba",
497
+ "model.language_model.layers.12.linear_attn.in_proj_b",
498
+ "model.language_model.layers.12.linear_attn.in_proj_a",
499
+ "model.language_model.layers.12.linear_attn.norm",
500
+ "model.language_model.layers.13.input_layernorm",
501
+ "model.language_model.layers.13.mlp.shared_expert_gate",
502
+ "model.language_model.layers.13.post_attention_layernorm",
503
+ "model.language_model.layers.13.mlp.gate",
504
+ "model.language_model.layers.13.linear_attn.A_log",
505
+ "model.language_model.layers.13.linear_attn.conv1d",
506
+ "model.language_model.layers.13.linear_attn.dt_bias",
507
+ "model.language_model.layers.13.linear_attn.in_proj_ba",
508
+ "model.language_model.layers.13.linear_attn.in_proj_b",
509
+ "model.language_model.layers.13.linear_attn.in_proj_a",
510
+ "model.language_model.layers.13.linear_attn.norm",
511
+ "model.language_model.layers.14.input_layernorm",
512
+ "model.language_model.layers.14.mlp.shared_expert_gate",
513
+ "model.language_model.layers.14.post_attention_layernorm",
514
+ "model.language_model.layers.14.mlp.gate",
515
+ "model.language_model.layers.14.linear_attn.A_log",
516
+ "model.language_model.layers.14.linear_attn.conv1d",
517
+ "model.language_model.layers.14.linear_attn.dt_bias",
518
+ "model.language_model.layers.14.linear_attn.in_proj_ba",
519
+ "model.language_model.layers.14.linear_attn.in_proj_b",
520
+ "model.language_model.layers.14.linear_attn.in_proj_a",
521
+ "model.language_model.layers.14.linear_attn.norm",
522
+ "model.language_model.layers.15.input_layernorm",
523
+ "model.language_model.layers.15.mlp.shared_expert_gate",
524
+ "model.language_model.layers.15.post_attention_layernorm",
525
+ "model.language_model.layers.15.mlp.gate",
526
+ "model.language_model.layers.15.self_attn.k_norm",
527
+ "model.language_model.layers.15.self_attn.q_norm",
528
+ "model.language_model.layers.16.input_layernorm",
529
+ "model.language_model.layers.16.mlp.shared_expert_gate",
530
+ "model.language_model.layers.16.post_attention_layernorm",
531
+ "model.language_model.layers.16.mlp.gate",
532
+ "model.language_model.layers.16.linear_attn.A_log",
533
+ "model.language_model.layers.16.linear_attn.conv1d",
534
+ "model.language_model.layers.16.linear_attn.dt_bias",
535
+ "model.language_model.layers.16.linear_attn.in_proj_ba",
536
+ "model.language_model.layers.16.linear_attn.in_proj_b",
537
+ "model.language_model.layers.16.linear_attn.in_proj_a",
538
+ "model.language_model.layers.16.linear_attn.norm",
539
+ "model.language_model.layers.17.input_layernorm",
540
+ "model.language_model.layers.17.mlp.shared_expert_gate",
541
+ "model.language_model.layers.17.post_attention_layernorm",
542
+ "model.language_model.layers.17.mlp.gate",
543
+ "model.language_model.layers.17.linear_attn.A_log",
544
+ "model.language_model.layers.17.linear_attn.conv1d",
545
+ "model.language_model.layers.17.linear_attn.dt_bias",
546
+ "model.language_model.layers.17.linear_attn.in_proj_ba",
547
+ "model.language_model.layers.17.linear_attn.in_proj_b",
548
+ "model.language_model.layers.17.linear_attn.in_proj_a",
549
+ "model.language_model.layers.17.linear_attn.norm",
550
+ "model.language_model.layers.18.input_layernorm",
551
+ "model.language_model.layers.18.mlp.shared_expert_gate",
552
+ "model.language_model.layers.18.post_attention_layernorm",
553
+ "model.language_model.layers.18.mlp.gate",
554
+ "model.language_model.layers.18.linear_attn.A_log",
555
+ "model.language_model.layers.18.linear_attn.conv1d",
556
+ "model.language_model.layers.18.linear_attn.dt_bias",
557
+ "model.language_model.layers.18.linear_attn.in_proj_ba",
558
+ "model.language_model.layers.18.linear_attn.in_proj_b",
559
+ "model.language_model.layers.18.linear_attn.in_proj_a",
560
+ "model.language_model.layers.18.linear_attn.norm",
561
+ "model.language_model.layers.19.input_layernorm",
562
+ "model.language_model.layers.19.mlp.shared_expert_gate",
563
+ "model.language_model.layers.19.post_attention_layernorm",
564
+ "model.language_model.layers.19.mlp.gate",
565
+ "model.language_model.layers.19.self_attn.k_norm",
566
+ "model.language_model.layers.19.self_attn.q_norm",
567
+ "model.language_model.layers.20.input_layernorm",
568
+ "model.language_model.layers.20.mlp.shared_expert_gate",
569
+ "model.language_model.layers.20.post_attention_layernorm",
570
+ "model.language_model.layers.20.mlp.gate",
571
+ "model.language_model.layers.20.linear_attn.A_log",
572
+ "model.language_model.layers.20.linear_attn.conv1d",
573
+ "model.language_model.layers.20.linear_attn.dt_bias",
574
+ "model.language_model.layers.20.linear_attn.in_proj_ba",
575
+ "model.language_model.layers.20.linear_attn.in_proj_b",
576
+ "model.language_model.layers.20.linear_attn.in_proj_a",
577
+ "model.language_model.layers.20.linear_attn.norm",
578
+ "model.language_model.layers.21.input_layernorm",
579
+ "model.language_model.layers.21.mlp.shared_expert_gate",
580
+ "model.language_model.layers.21.post_attention_layernorm",
581
+ "model.language_model.layers.21.mlp.gate",
582
+ "model.language_model.layers.21.linear_attn.A_log",
583
+ "model.language_model.layers.21.linear_attn.conv1d",
584
+ "model.language_model.layers.21.linear_attn.dt_bias",
585
+ "model.language_model.layers.21.linear_attn.in_proj_ba",
586
+ "model.language_model.layers.21.linear_attn.in_proj_b",
587
+ "model.language_model.layers.21.linear_attn.in_proj_a",
588
+ "model.language_model.layers.21.linear_attn.norm",
589
+ "model.language_model.layers.22.input_layernorm",
590
+ "model.language_model.layers.22.mlp.shared_expert_gate",
591
+ "model.language_model.layers.22.post_attention_layernorm",
592
+ "model.language_model.layers.22.mlp.gate",
593
+ "model.language_model.layers.22.linear_attn.A_log",
594
+ "model.language_model.layers.22.linear_attn.conv1d",
595
+ "model.language_model.layers.22.linear_attn.dt_bias",
596
+ "model.language_model.layers.22.linear_attn.in_proj_ba",
597
+ "model.language_model.layers.22.linear_attn.in_proj_b",
598
+ "model.language_model.layers.22.linear_attn.in_proj_a",
599
+ "model.language_model.layers.22.linear_attn.norm",
600
+ "model.language_model.layers.23.input_layernorm",
601
+ "model.language_model.layers.23.mlp.shared_expert_gate",
602
+ "model.language_model.layers.23.post_attention_layernorm",
603
+ "model.language_model.layers.23.mlp.gate",
604
+ "model.language_model.layers.23.self_attn.k_norm",
605
+ "model.language_model.layers.23.self_attn.q_norm",
606
+ "model.language_model.layers.24.input_layernorm",
607
+ "model.language_model.layers.24.mlp.shared_expert_gate",
608
+ "model.language_model.layers.24.post_attention_layernorm",
609
+ "model.language_model.layers.24.mlp.gate",
610
+ "model.language_model.layers.24.linear_attn.A_log",
611
+ "model.language_model.layers.24.linear_attn.conv1d",
612
+ "model.language_model.layers.24.linear_attn.dt_bias",
613
+ "model.language_model.layers.24.linear_attn.in_proj_ba",
614
+ "model.language_model.layers.24.linear_attn.in_proj_b",
615
+ "model.language_model.layers.24.linear_attn.in_proj_a",
616
+ "model.language_model.layers.24.linear_attn.norm",
617
+ "model.language_model.layers.25.input_layernorm",
618
+ "model.language_model.layers.25.mlp.shared_expert_gate",
619
+ "model.language_model.layers.25.post_attention_layernorm",
620
+ "model.language_model.layers.25.mlp.gate",
621
+ "model.language_model.layers.25.linear_attn.A_log",
622
+ "model.language_model.layers.25.linear_attn.conv1d",
623
+ "model.language_model.layers.25.linear_attn.dt_bias",
624
+ "model.language_model.layers.25.linear_attn.in_proj_ba",
625
+ "model.language_model.layers.25.linear_attn.in_proj_b",
626
+ "model.language_model.layers.25.linear_attn.in_proj_a",
627
+ "model.language_model.layers.25.linear_attn.norm",
628
+ "model.language_model.layers.26.input_layernorm",
629
+ "model.language_model.layers.26.mlp.shared_expert_gate",
630
+ "model.language_model.layers.26.post_attention_layernorm",
631
+ "model.language_model.layers.26.mlp.gate",
632
+ "model.language_model.layers.26.linear_attn.A_log",
633
+ "model.language_model.layers.26.linear_attn.conv1d",
634
+ "model.language_model.layers.26.linear_attn.dt_bias",
635
+ "model.language_model.layers.26.linear_attn.in_proj_ba",
636
+ "model.language_model.layers.26.linear_attn.in_proj_b",
637
+ "model.language_model.layers.26.linear_attn.in_proj_a",
638
+ "model.language_model.layers.26.linear_attn.norm",
639
+ "model.language_model.layers.27.input_layernorm",
640
+ "model.language_model.layers.27.mlp.shared_expert_gate",
641
+ "model.language_model.layers.27.post_attention_layernorm",
642
+ "model.language_model.layers.27.mlp.gate",
643
+ "model.language_model.layers.27.self_attn.k_norm",
644
+ "model.language_model.layers.27.self_attn.q_norm",
645
+ "model.language_model.layers.28.input_layernorm",
646
+ "model.language_model.layers.28.mlp.shared_expert_gate",
647
+ "model.language_model.layers.28.post_attention_layernorm",
648
+ "model.language_model.layers.28.mlp.gate",
649
+ "model.language_model.layers.28.linear_attn.A_log",
650
+ "model.language_model.layers.28.linear_attn.conv1d",
651
+ "model.language_model.layers.28.linear_attn.dt_bias",
652
+ "model.language_model.layers.28.linear_attn.in_proj_ba",
653
+ "model.language_model.layers.28.linear_attn.in_proj_b",
654
+ "model.language_model.layers.28.linear_attn.in_proj_a",
655
+ "model.language_model.layers.28.linear_attn.norm",
656
+ "model.language_model.layers.29.input_layernorm",
657
+ "model.language_model.layers.29.mlp.shared_expert_gate",
658
+ "model.language_model.layers.29.post_attention_layernorm",
659
+ "model.language_model.layers.29.mlp.gate",
660
+ "model.language_model.layers.29.linear_attn.A_log",
661
+ "model.language_model.layers.29.linear_attn.conv1d",
662
+ "model.language_model.layers.29.linear_attn.dt_bias",
663
+ "model.language_model.layers.29.linear_attn.in_proj_ba",
664
+ "model.language_model.layers.29.linear_attn.in_proj_b",
665
+ "model.language_model.layers.29.linear_attn.in_proj_a",
666
+ "model.language_model.layers.29.linear_attn.norm",
667
+ "model.language_model.layers.30.input_layernorm",
668
+ "model.language_model.layers.30.mlp.shared_expert_gate",
669
+ "model.language_model.layers.30.post_attention_layernorm",
670
+ "model.language_model.layers.30.mlp.gate",
671
+ "model.language_model.layers.30.linear_attn.A_log",
672
+ "model.language_model.layers.30.linear_attn.conv1d",
673
+ "model.language_model.layers.30.linear_attn.dt_bias",
674
+ "model.language_model.layers.30.linear_attn.in_proj_ba",
675
+ "model.language_model.layers.30.linear_attn.in_proj_b",
676
+ "model.language_model.layers.30.linear_attn.in_proj_a",
677
+ "model.language_model.layers.30.linear_attn.norm",
678
+ "model.language_model.layers.31.input_layernorm",
679
+ "model.language_model.layers.31.mlp.shared_expert_gate",
680
+ "model.language_model.layers.31.post_attention_layernorm",
681
+ "model.language_model.layers.31.mlp.gate",
682
+ "model.language_model.layers.31.self_attn.k_norm",
683
+ "model.language_model.layers.31.self_attn.q_norm",
684
+ "model.language_model.layers.32.input_layernorm",
685
+ "model.language_model.layers.32.mlp.shared_expert_gate",
686
+ "model.language_model.layers.32.post_attention_layernorm",
687
+ "model.language_model.layers.32.mlp.gate",
688
+ "model.language_model.layers.32.linear_attn.A_log",
689
+ "model.language_model.layers.32.linear_attn.conv1d",
690
+ "model.language_model.layers.32.linear_attn.dt_bias",
691
+ "model.language_model.layers.32.linear_attn.in_proj_ba",
692
+ "model.language_model.layers.32.linear_attn.in_proj_b",
693
+ "model.language_model.layers.32.linear_attn.in_proj_a",
694
+ "model.language_model.layers.32.linear_attn.norm",
695
+ "model.language_model.layers.33.input_layernorm",
696
+ "model.language_model.layers.33.mlp.shared_expert_gate",
697
+ "model.language_model.layers.33.post_attention_layernorm",
698
+ "model.language_model.layers.33.mlp.gate",
699
+ "model.language_model.layers.33.linear_attn.A_log",
700
+ "model.language_model.layers.33.linear_attn.conv1d",
701
+ "model.language_model.layers.33.linear_attn.dt_bias",
702
+ "model.language_model.layers.33.linear_attn.in_proj_ba",
703
+ "model.language_model.layers.33.linear_attn.in_proj_b",
704
+ "model.language_model.layers.33.linear_attn.in_proj_a",
705
+ "model.language_model.layers.33.linear_attn.norm",
706
+ "model.language_model.layers.34.input_layernorm",
707
+ "model.language_model.layers.34.mlp.shared_expert_gate",
708
+ "model.language_model.layers.34.post_attention_layernorm",
709
+ "model.language_model.layers.34.mlp.gate",
710
+ "model.language_model.layers.34.linear_attn.A_log",
711
+ "model.language_model.layers.34.linear_attn.conv1d",
712
+ "model.language_model.layers.34.linear_attn.dt_bias",
713
+ "model.language_model.layers.34.linear_attn.in_proj_ba",
714
+ "model.language_model.layers.34.linear_attn.in_proj_b",
715
+ "model.language_model.layers.34.linear_attn.in_proj_a",
716
+ "model.language_model.layers.34.linear_attn.norm",
717
+ "model.language_model.layers.35.input_layernorm",
718
+ "model.language_model.layers.35.mlp.shared_expert_gate",
719
+ "model.language_model.layers.35.post_attention_layernorm",
720
+ "model.language_model.layers.35.mlp.gate",
721
+ "model.language_model.layers.35.self_attn.k_norm",
722
+ "model.language_model.layers.35.self_attn.q_norm",
723
+ "model.language_model.layers.36.input_layernorm",
724
+ "model.language_model.layers.36.mlp.shared_expert_gate",
725
+ "model.language_model.layers.36.post_attention_layernorm",
726
+ "model.language_model.layers.36.mlp.gate",
727
+ "model.language_model.layers.36.linear_attn.A_log",
728
+ "model.language_model.layers.36.linear_attn.conv1d",
729
+ "model.language_model.layers.36.linear_attn.dt_bias",
730
+ "model.language_model.layers.36.linear_attn.in_proj_ba",
731
+ "model.language_model.layers.36.linear_attn.in_proj_b",
732
+ "model.language_model.layers.36.linear_attn.in_proj_a",
733
+ "model.language_model.layers.36.linear_attn.norm",
734
+ "model.language_model.layers.37.input_layernorm",
735
+ "model.language_model.layers.37.mlp.shared_expert_gate",
736
+ "model.language_model.layers.37.post_attention_layernorm",
737
+ "model.language_model.layers.37.mlp.gate",
738
+ "model.language_model.layers.37.linear_attn.A_log",
739
+ "model.language_model.layers.37.linear_attn.conv1d",
740
+ "model.language_model.layers.37.linear_attn.dt_bias",
741
+ "model.language_model.layers.37.linear_attn.in_proj_ba",
742
+ "model.language_model.layers.37.linear_attn.in_proj_b",
743
+ "model.language_model.layers.37.linear_attn.in_proj_a",
744
+ "model.language_model.layers.37.linear_attn.norm",
745
+ "model.language_model.layers.38.input_layernorm",
746
+ "model.language_model.layers.38.mlp.shared_expert_gate",
747
+ "model.language_model.layers.38.post_attention_layernorm",
748
+ "model.language_model.layers.38.mlp.gate",
749
+ "model.language_model.layers.38.linear_attn.A_log",
750
+ "model.language_model.layers.38.linear_attn.conv1d",
751
+ "model.language_model.layers.38.linear_attn.dt_bias",
752
+ "model.language_model.layers.38.linear_attn.in_proj_ba",
753
+ "model.language_model.layers.38.linear_attn.in_proj_b",
754
+ "model.language_model.layers.38.linear_attn.in_proj_a",
755
+ "model.language_model.layers.38.linear_attn.norm",
756
+ "model.language_model.layers.39.input_layernorm",
757
+ "model.language_model.layers.39.mlp.shared_expert_gate",
758
+ "model.language_model.layers.39.post_attention_layernorm",
759
+ "model.language_model.layers.39.mlp.gate",
760
+ "model.language_model.layers.39.self_attn.k_norm",
761
+ "model.language_model.layers.39.self_attn.q_norm",
762
+ "mtp.layers.0.input_layernorm",
763
+ "mtp.layers.0.mlp.gate",
764
+ "mtp.layers.0.mlp.shared_expert_gate",
765
+ "mtp.layers.0.post_attention_layernorm",
766
+ "mtp.layers.0.self_attn.k_norm",
767
+ "mtp.layers.0.self_attn.q_norm",
768
+ "mtp.fc",
769
+ "mtp.norm",
770
+ "mtp.pre_fc_norm_embedding",
771
+ "mtp.pre_fc_norm_hidden"
772
+ ],
773
+ "weight_block_size": [
774
+ 128,
775
+ 128
776
+ ]
777
+ }
778
+ }
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
+ }
layers-0.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:969ed52b6d4a45e1c919115aed81a48a00004625a0406eebf630e829ff97c5bf
3
+ size 843713608
layers-1.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b6714f0a7b7f9f7ed9eceefc31af655de1863bd83a23d735aa8dbad2cc03dfe
3
+ size 843713608
layers-10.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cc57c2d6e18830429e2c9ea27a0b7d15e6502c74463d3d4ec6b621c699a5ef8
3
+ size 843715168
layers-11.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f85558bc82b754230204607f55a3035fd39a6ad4e7f0f5613aa40a632566cab
3
+ size 837094000
layers-12.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0eb974e0b80092a722d10140647aedc14647831007ea7d898b892064c9fb4d0d
3
+ size 843715168
layers-13.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d4bbdc09e40a3ccfa503c5149c7bb477b07bf8a75ca81613aa68031d995cbf8
3
+ size 843715168
layers-14.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c6c07e10d047dd742b90fdfdbe734d5b4627fcae7728f8319413194c8d6f171
3
+ size 843715168
layers-15.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:786c965fcbc9544aa97524e986ff7e1e2303b6c22812249b283b8c590ada7a77
3
+ size 837094000
layers-16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbbaab6eef74ab4f24d374ce94203c8f439019a26d322d8b02fb1cee6ed70267
3
+ size 843715168
layers-17.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29a35db86d591da297ac0ff46f773bf5e5386035172b6c637e00cf0786b0fdc9
3
+ size 843715168
layers-18.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99db8f52e91928e6a362c4510b15112c0c5d2eb0e9279b3413ec1db2016f1b2b
3
+ size 843715168
layers-19.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1bc3e93c3a22adc01a77b4a2d5e2171e9588e2478ed648526596700ffa566c7
3
+ size 837094000
layers-2.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ca3668d7dde8c47e796186f9a459afe6f86a60e547bc2f72fcc87543e4a718e
3
+ size 843713608
layers-20.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:027f68acf35eb9e9fc41ae12154c18da1b0126bee7eaf16a177cfcbeaafbc7a6
3
+ size 843715168
layers-21.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79205dfb7fe145b26e5941f1b9590a870bc9e1df3127a67bd1ac32f1a12ad75f
3
+ size 843715168
layers-22.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94e7674ffb28f4cd9cf8859c6d0440cbd5d4d3a6dc33193a0442642ae303cd17
3
+ size 843715168
layers-23.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51a7c63c51959faa40c369c80ddac42233cd13d7ad6603e75574bbeeca72e98d
3
+ size 837094000
layers-24.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c64b42cb8abc93ff5e5ac801c556da6eb81545a151c10320618bae250c9efd9
3
+ size 843715168
layers-25.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18ca830020bd0c7af5f99257112e1c5ba457673d4fd926e6eafcb3127edb06b5
3
+ size 843715168
layers-26.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3fcd9cfeeb8ef52b749041df0986865cd2b6822a67bd69d0e0692571e49cfde
3
+ size 843715168
layers-27.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48829a4c312ecaf44e03bd9266245549982c326c0311b37694eb29dde4f30c62
3
+ size 837094000
layers-28.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e40e51e6b2fbd04642cdfe3e66f4936bb74ef880ea8ff5417ec2075c47a938f
3
+ size 843715168
layers-29.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:154e2b6da74a5c7921382d1738a57d4a7a9465594f68aa2f7e269340cef27d76
3
+ size 843715168
layers-3.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ebbd0a7aa2f82f516ec339b66b317f5a7d710d244c42d00f4fea22478bac7da
3
+ size 837092440
layers-30.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:292aa0e63dfbd0c757945021b0995b83d7f561985202df9fbfe591c61911f9fa
3
+ size 843715168
layers-31.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21073b1a747d3736b46dc4f84ed66ae287ee3acb699807757a06d77de98af99e
3
+ size 837094000
layers-32.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52e7905b111b6fbfb2b91b9f5b4fd748e61c93cbd39e988d1fabbcd9e00f4f20
3
+ size 843715168
layers-33.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcc4ad3526f6bb99ae9af57cc319da6bfd69228e5d0bcbd678590323f240cccb
3
+ size 843715168
layers-34.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f52d1343ed110f00a661fcdc17e530a5f3c22a9397469bd2f41e22c8a2ffe9f1
3
+ size 843715168
layers-35.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a079648624f32732831382efa86c72bf03bc58336dcfe6b8ae11f4fcba33e2ea
3
+ size 837094000
layers-36.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f293aff9b2498b7a86303bfb928a03b62b1763bf71f0fe35c14d2d1712292673
3
+ size 843715168
layers-37.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:918c26a832494ea368013e5fce8dba0e98923cc62f69d0b21f752dfeb241d404
3
+ size 843715168
layers-38.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cd43a74c05a8f112c4f137f8139f217601a6035f6474c256b4bac315ccf5c39
3
+ size 843715168
layers-39.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e347a8527fb41e4dde7e92a359feb0709d770d2b7ab4f2081c940205b85dba9
3
+ size 837094000
layers-4.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fda002efe01809173b2a9179d529e04f1a9e28d58038cf47fea02b1251c544e
3
+ size 843713608
layers-5.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85f08db02168b263497757002827eb15c44c9ae46962ec26f19a648a0f5fb826
3
+ size 843713608
layers-6.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0601aa7cd21d29efdd6330614aaff2b9a7e4b599d1de894fdb50525033c8725a
3
+ size 843713608
layers-7.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec6d9082f26b2e3d6010114cac16d71626836a53812782690bce582bf2baac51
3
+ size 837092440
layers-8.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4284bb825ff85f6166208edfb8315897771db03dae82a078bc69014c695502a
3
+ size 843713608
layers-9.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2bc291ccdccde1094f34e5d2f506e2b8a3857327faa9ffbd2d3a5d75de9d23a
3
+ size 843713608
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
mtp.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e9c9fef90a5c02314cf27eeccc72f9f61ce711c12c869244c7127c787b5bd7d
3
+ size 853860608
outside.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb9755bc8ebd638e6a9994ae75064f9a6ac3f56541c00a10a90b7a930d24cc4f
3
+ size 2927422112
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 sha256:5f9e4d4901a92b997e463c1f46055088b6cca5ca61a6522d1b9f64c4bb81cb42
3
+ size 12807982
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{%- if tools and tools is iterable and tools is not mapping %}\n {{- '<|im_start|>system\\n' }}\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 {{- '<|im_start|>system\\n' + content + '<|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 {%- else %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- set reasoning_content = reasoning_content|trim %}\n {%- if (preserve_thinking is defined and 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 %}\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
+ }