Hugging Face's logo

lukealonso
/
Qwen3.5-397B-A17B-NVFP4

Text Generation
Safetensors
qwen3_5_moe
qwen3.5
Mixture of Experts
quantized
nvfp4
fp4
multimodal
vision
conversational
modelopt
Model card Files
xet
 Community
1
lukealonso commited on
Commit
9923aaa
·
verified ·
1 Parent(s): afbaf60

Add files using upload-large-folder tool

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 +2 -0
  2. chat_template.jinja +154 -0
  3. config.json +344 -0
  4. generation_config.json +70 -0
  5. hf_quant_config.json +156 -0
  6. merges.txt +0 -0
  7. model-00001-of-00044.safetensors +3 -0
  8. model-00002-of-00044.safetensors +3 -0
  9. model-00003-of-00044.safetensors +3 -0
  10. model-00004-of-00044.safetensors +3 -0
  11. model-00005-of-00044.safetensors +3 -0
  12. model-00006-of-00044.safetensors +3 -0
  13. model-00007-of-00044.safetensors +3 -0
  14. model-00008-of-00044.safetensors +3 -0
  15. model-00009-of-00044.safetensors +3 -0
  16. model-00010-of-00044.safetensors +3 -0
  17. model-00011-of-00044.safetensors +3 -0
  18. model-00012-of-00044.safetensors +3 -0
  19. model-00014-of-00044.safetensors +3 -0
  20. model-00015-of-00044.safetensors +3 -0
  21. model-00016-of-00044.safetensors +3 -0
  22. model-00022-of-00044.safetensors +3 -0
  23. model-00023-of-00044.safetensors +3 -0
  24. model-00024-of-00044.safetensors +3 -0
  25. model-00025-of-00044.safetensors +3 -0
  26. model-00026-of-00044.safetensors +3 -0
  27. model-00027-of-00044.safetensors +3 -0
  28. model-00028-of-00044.safetensors +3 -0
  29. model-00029-of-00044.safetensors +3 -0
  30. model-00030-of-00044.safetensors +3 -0
  31. model-00031-of-00044.safetensors +3 -0
  32. model-00032-of-00044.safetensors +3 -0
  33. model-00034-of-00044.safetensors +3 -0
  34. model-00035-of-00044.safetensors +3 -0
  35. model-00036-of-00044.safetensors +3 -0
  36. model-00037-of-00044.safetensors +3 -0
  37. model-00038-of-00044.safetensors +3 -0
  38. model-00039-of-00044.safetensors +3 -0
  39. model-00040-of-00044.safetensors +3 -0
  40. model-00041-of-00044.safetensors +3 -0
  41. model-00042-of-00044.safetensors +3 -0
  42. model-00043-of-00044.safetensors +3 -0
  43. model-00044-of-00044.safetensors +3 -0
  44. model-inputscales.safetensors +3 -0
  45. model-mtp.safetensors +3 -0
  46. model.safetensors.index.json +3 -0
  47. preprocessor_config.json +21 -0
  48. tokenizer.json +3 -0
  49. tokenizer_config.json +305 -0
  50. video_preprocessor_config.json +21 -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
+ model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text
37
+ 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 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 | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
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 +1,344 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "vision_config": {
3
+ "return_dict": true,
4
+ "output_hidden_states": false,
5
+ "dtype": null,
6
+ "chunk_size_feed_forward": 0,
7
+ "is_encoder_decoder": false,
8
+ "architectures": null,
9
+ "id2label": {
10
+ "0": "LABEL_0",
11
+ "1": "LABEL_1"
12
+ },
13
+ "label2id": {
14
+ "LABEL_0": 0,
15
+ "LABEL_1": 1
16
+ },
17
+ "problem_type": null,
18
+ "_name_or_path": "",
19
+ "deepstack_visual_indexes": [],
20
+ "model_type": "qwen3_5_moe",
21
+ "depth": 27,
22
+ "hidden_size": 1152,
23
+ "hidden_act": "gelu_pytorch_tanh",
24
+ "intermediate_size": 4304,
25
+ "num_heads": 16,
26
+ "in_channels": 3,
27
+ "patch_size": 16,
28
+ "spatial_merge_size": 2,
29
+ "temporal_patch_size": 2,
30
+ "out_hidden_size": 4096,
31
+ "num_position_embeddings": 2304,
32
+ "initializer_range": 0.02,
33
+ "output_attentions": false
34
+ },
35
+ "text_config": {
36
+ "pad_token_id": null,
37
+ "bos_token_id": null,
38
+ "eos_token_id": 248044,
39
+ "tie_word_embeddings": false,
40
+ "vocab_size": 248320,
41
+ "max_position_embeddings": 262144,
42
+ "hidden_size": 4096,
43
+ "num_hidden_layers": 60,
44
+ "num_attention_heads": 32,
45
+ "num_key_value_heads": 2,
46
+ "hidden_act": "silu",
47
+ "initializer_range": 0.02,
48
+ "rms_norm_eps": 1e-06,
49
+ "use_cache": true,
50
+ "attention_bias": false,
51
+ "attention_dropout": 0.0,
52
+ "head_dim": 256,
53
+ "rope_parameters": {
54
+ "mrope_interleaved": true,
55
+ "mrope_section": [
56
+ 11,
57
+ 11,
58
+ 10
59
+ ],
60
+ "rope_type": "default",
61
+ "rope_theta": 10000000,
62
+ "partial_rotary_factor": 0.25
63
+ },
64
+ "layer_types": [
65
+ "linear_attention",
66
+ "linear_attention",
67
+ "linear_attention",
68
+ "full_attention",
69
+ "linear_attention",
70
+ "linear_attention",
71
+ "linear_attention",
72
+ "full_attention",
73
+ "linear_attention",
74
+ "linear_attention",
75
+ "linear_attention",
76
+ "full_attention",
77
+ "linear_attention",
78
+ "linear_attention",
79
+ "linear_attention",
80
+ "full_attention",
81
+ "linear_attention",
82
+ "linear_attention",
83
+ "linear_attention",
84
+ "full_attention",
85
+ "linear_attention",
86
+ "linear_attention",
87
+ "linear_attention",
88
+ "full_attention",
89
+ "linear_attention",
90
+ "linear_attention",
91
+ "linear_attention",
92
+ "full_attention",
93
+ "linear_attention",
94
+ "linear_attention",
95
+ "linear_attention",
96
+ "full_attention",
97
+ "linear_attention",
98
+ "linear_attention",
99
+ "linear_attention",
100
+ "full_attention",
101
+ "linear_attention",
102
+ "linear_attention",
103
+ "linear_attention",
104
+ "full_attention",
105
+ "linear_attention",
106
+ "linear_attention",
107
+ "linear_attention",
108
+ "full_attention",
109
+ "linear_attention",
110
+ "linear_attention",
111
+ "linear_attention",
112
+ "full_attention",
113
+ "linear_attention",
114
+ "linear_attention",
115
+ "linear_attention",
116
+ "full_attention",
117
+ "linear_attention",
118
+ "linear_attention",
119
+ "linear_attention",
120
+ "full_attention",
121
+ "linear_attention",
122
+ "linear_attention",
123
+ "linear_attention",
124
+ "full_attention"
125
+ ],
126
+ "linear_conv_kernel_dim": 4,
127
+ "linear_key_head_dim": 128,
128
+ "linear_value_head_dim": 128,
129
+ "linear_num_key_heads": 16,
130
+ "linear_num_value_heads": 64,
131
+ "moe_intermediate_size": 1024,
132
+ "shared_expert_intermediate_size": 1024,
133
+ "num_experts_per_tok": 10,
134
+ "num_experts": 512,
135
+ "output_router_logits": false,
136
+ "router_aux_loss_coef": 0.001,
137
+ "return_dict": true,
138
+ "output_hidden_states": false,
139
+ "dtype": "bfloat16",
140
+ "chunk_size_feed_forward": 0,
141
+ "is_encoder_decoder": false,
142
+ "id2label": {
143
+ "0": "LABEL_0",
144
+ "1": "LABEL_1"
145
+ },
146
+ "label2id": {
147
+ "LABEL_0": 0,
148
+ "LABEL_1": 1
149
+ },
150
+ "problem_type": null,
151
+ "_name_or_path": "",
152
+ "attn_output_gate": true,
153
+ "full_attention_interval": 4,
154
+ "mlp_only_layers": [],
155
+ "model_type": "qwen3_5_moe_text",
156
+ "mtp_num_hidden_layers": 1,
157
+ "mtp_use_dedicated_embeddings": false,
158
+ "mamba_ssm_dtype": "float32",
159
+ "partial_rotary_factor": 0.25,
160
+ "output_attentions": false
161
+ },
162
+ "image_token_id": 248056,
163
+ "video_token_id": 248057,
164
+ "vision_start_token_id": 248053,
165
+ "vision_end_token_id": 248054,
166
+ "tie_word_embeddings": false,
167
+ "return_dict": true,
168
+ "output_hidden_states": false,
169
+ "dtype": null,
170
+ "chunk_size_feed_forward": 0,
171
+ "is_encoder_decoder": false,
172
+ "architectures": [
173
+ "Qwen3_5MoeForConditionalGeneration"
174
+ ],
175
+ "id2label": {
176
+ "0": "LABEL_0",
177
+ "1": "LABEL_1"
178
+ },
179
+ "label2id": {
180
+ "LABEL_0": 0,
181
+ "LABEL_1": 1
182
+ },
183
+ "problem_type": null,
184
+ "_name_or_path": "Qwen/Qwen3.5-397B-A17B",
185
+ "transformers_version": "5.3.0.dev0",
186
+ "model_type": "qwen3_5_moe",
187
+ "output_attentions": false,
188
+ "quantization_config": {
189
+ "config_groups": {
190
+ "group_0": {
191
+ "input_activations": {
192
+ "dynamic": false,
193
+ "num_bits": 4,
194
+ "type": "float",
195
+ "group_size": 16
196
+ },
197
+ "weights": {
198
+ "dynamic": false,
199
+ "num_bits": 4,
200
+ "type": "float",
201
+ "group_size": 16
202
+ },
203
+ "targets": [
204
+ "Linear"
205
+ ]
206
+ }
207
+ },
208
+ "ignore": [
209
+ "lm_head",
210
+ "model.language_model.layers.0.linear_attn*",
211
+ "model.language_model.layers.0.mlp.shared_expert_gate",
212
+ "model.language_model.layers.1.linear_attn*",
213
+ "model.language_model.layers.1.mlp.shared_expert_gate",
214
+ "model.language_model.layers.10.linear_attn*",
215
+ "model.language_model.layers.10.mlp.shared_expert_gate",
216
+ "model.language_model.layers.11.mlp.shared_expert_gate",
217
+ "model.language_model.layers.11.self_attn*",
218
+ "model.language_model.layers.12.linear_attn*",
219
+ "model.language_model.layers.12.mlp.shared_expert_gate",
220
+ "model.language_model.layers.13.linear_attn*",
221
+ "model.language_model.layers.13.mlp.shared_expert_gate",
222
+ "model.language_model.layers.14.linear_attn*",
223
+ "model.language_model.layers.14.mlp.shared_expert_gate",
224
+ "model.language_model.layers.15.mlp.shared_expert_gate",
225
+ "model.language_model.layers.15.self_attn*",
226
+ "model.language_model.layers.16.linear_attn*",
227
+ "model.language_model.layers.16.mlp.shared_expert_gate",
228
+ "model.language_model.layers.17.linear_attn*",
229
+ "model.language_model.layers.17.mlp.shared_expert_gate",
230
+ "model.language_model.layers.18.linear_attn*",
231
+ "model.language_model.layers.18.mlp.shared_expert_gate",
232
+ "model.language_model.layers.19.mlp.shared_expert_gate",
233
+ "model.language_model.layers.19.self_attn*",
234
+ "model.language_model.layers.2.linear_attn*",
235
+ "model.language_model.layers.2.mlp.shared_expert_gate",
236
+ "model.language_model.layers.20.linear_attn*",
237
+ "model.language_model.layers.20.mlp.shared_expert_gate",
238
+ "model.language_model.layers.21.linear_attn*",
239
+ "model.language_model.layers.21.mlp.shared_expert_gate",
240
+ "model.language_model.layers.22.linear_attn*",
241
+ "model.language_model.layers.22.mlp.shared_expert_gate",
242
+ "model.language_model.layers.23.mlp.shared_expert_gate",
243
+ "model.language_model.layers.23.self_attn*",
244
+ "model.language_model.layers.24.linear_attn*",
245
+ "model.language_model.layers.24.mlp.shared_expert_gate",
246
+ "model.language_model.layers.25.linear_attn*",
247
+ "model.language_model.layers.25.mlp.shared_expert_gate",
248
+ "model.language_model.layers.26.linear_attn*",
249
+ "model.language_model.layers.26.mlp.shared_expert_gate",
250
+ "model.language_model.layers.27.mlp.shared_expert_gate",
251
+ "model.language_model.layers.27.self_attn*",
252
+ "model.language_model.layers.28.linear_attn*",
253
+ "model.language_model.layers.28.mlp.shared_expert_gate",
254
+ "model.language_model.layers.29.linear_attn*",
255
+ "model.language_model.layers.29.mlp.shared_expert_gate",
256
+ "model.language_model.layers.3.mlp.shared_expert_gate",
257
+ "model.language_model.layers.3.self_attn*",
258
+ "model.language_model.layers.30.linear_attn*",
259
+ "model.language_model.layers.30.mlp.shared_expert_gate",
260
+ "model.language_model.layers.31.mlp.shared_expert_gate",
261
+ "model.language_model.layers.31.self_attn*",
262
+ "model.language_model.layers.32.linear_attn*",
263
+ "model.language_model.layers.32.mlp.shared_expert_gate",
264
+ "model.language_model.layers.33.linear_attn*",
265
+ "model.language_model.layers.33.mlp.shared_expert_gate",
266
+ "model.language_model.layers.34.linear_attn*",
267
+ "model.language_model.layers.34.mlp.shared_expert_gate",
268
+ "model.language_model.layers.35.mlp.shared_expert_gate",
269
+ "model.language_model.layers.35.self_attn*",
270
+ "model.language_model.layers.36.linear_attn*",
271
+ "model.language_model.layers.36.mlp.shared_expert_gate",
272
+ "model.language_model.layers.37.linear_attn*",
273
+ "model.language_model.layers.37.mlp.shared_expert_gate",
274
+ "model.language_model.layers.38.linear_attn*",
275
+ "model.language_model.layers.38.mlp.shared_expert_gate",
276
+ "model.language_model.layers.39.mlp.shared_expert_gate",
277
+ "model.language_model.layers.39.self_attn*",
278
+ "model.language_model.layers.4.linear_attn*",
279
+ "model.language_model.layers.4.mlp.shared_expert_gate",
280
+ "model.language_model.layers.40.linear_attn*",
281
+ "model.language_model.layers.40.mlp.shared_expert_gate",
282
+ "model.language_model.layers.41.linear_attn*",
283
+ "model.language_model.layers.41.mlp.shared_expert_gate",
284
+ "model.language_model.layers.42.linear_attn*",
285
+ "model.language_model.layers.42.mlp.shared_expert_gate",
286
+ "model.language_model.layers.43.mlp.shared_expert_gate",
287
+ "model.language_model.layers.43.self_attn*",
288
+ "model.language_model.layers.44.linear_attn*",
289
+ "model.language_model.layers.44.mlp.shared_expert_gate",
290
+ "model.language_model.layers.45.linear_attn*",
291
+ "model.language_model.layers.45.mlp.shared_expert_gate",
292
+ "model.language_model.layers.46.linear_attn*",
293
+ "model.language_model.layers.46.mlp.shared_expert_gate",
294
+ "model.language_model.layers.47.mlp.shared_expert_gate",
295
+ "model.language_model.layers.47.self_attn*",
296
+ "model.language_model.layers.48.linear_attn*",
297
+ "model.language_model.layers.48.mlp.shared_expert_gate",
298
+ "model.language_model.layers.49.linear_attn*",
299
+ "model.language_model.layers.49.mlp.shared_expert_gate",
300
+ "model.language_model.layers.5.linear_attn*",
301
+ "model.language_model.layers.5.mlp.shared_expert_gate",
302
+ "model.language_model.layers.50.linear_attn*",
303
+ "model.language_model.layers.50.mlp.shared_expert_gate",
304
+ "model.language_model.layers.51.mlp.shared_expert_gate",
305
+ "model.language_model.layers.51.self_attn*",
306
+ "model.language_model.layers.52.linear_attn*",
307
+ "model.language_model.layers.52.mlp.shared_expert_gate",
308
+ "model.language_model.layers.53.linear_attn*",
309
+ "model.language_model.layers.53.mlp.shared_expert_gate",
310
+ "model.language_model.layers.54.linear_attn*",
311
+ "model.language_model.layers.54.mlp.shared_expert_gate",
312
+ "model.language_model.layers.55.mlp.shared_expert_gate",
313
+ "model.language_model.layers.55.self_attn*",
314
+ "model.language_model.layers.56.linear_attn*",
315
+ "model.language_model.layers.56.mlp.shared_expert_gate",
316
+ "model.language_model.layers.57.linear_attn*",
317
+ "model.language_model.layers.57.mlp.shared_expert_gate",
318
+ "model.language_model.layers.58.linear_attn*",
319
+ "model.language_model.layers.58.mlp.shared_expert_gate",
320
+ "model.language_model.layers.59.mlp.shared_expert_gate",
321
+ "model.language_model.layers.59.self_attn*",
322
+ "model.language_model.layers.6.linear_attn*",
323
+ "model.language_model.layers.6.mlp.shared_expert_gate",
324
+ "model.language_model.layers.7.mlp.shared_expert_gate",
325
+ "model.language_model.layers.7.self_attn*",
326
+ "model.language_model.layers.8.linear_attn*",
327
+ "model.language_model.layers.8.mlp.shared_expert_gate",
328
+ "model.language_model.layers.9.linear_attn*",
329
+ "model.language_model.layers.9.mlp.shared_expert_gate",
330
+ "model.visual*"
331
+ ],
332
+ "quant_algo": "NVFP4",
333
+ "kv_cache_scheme": {
334
+ "dynamic": false,
335
+ "num_bits": 8,
336
+ "type": "float"
337
+ },
338
+ "producer": {
339
+ "name": "modelopt",
340
+ "version": "0.43.0.dev82+gd3748c2c6"
341
+ },
342
+ "quant_method": "modelopt"
343
+ }
344
+ }
generation_config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "max_length": null,
3
+ "max_new_tokens": null,
4
+ "min_length": null,
5
+ "min_new_tokens": null,
6
+ "early_stopping": null,
7
+ "max_time": null,
8
+ "stop_strings": null,
9
+ "do_sample": null,
10
+ "num_beams": null,
11
+ "use_cache": true,
12
+ "cache_implementation": null,
13
+ "cache_config": null,
14
+ "temperature": null,
15
+ "top_k": null,
16
+ "top_p": null,
17
+ "min_p": null,
18
+ "top_h": null,
19
+ "typical_p": null,
20
+ "epsilon_cutoff": null,
21
+ "eta_cutoff": null,
22
+ "repetition_penalty": null,
23
+ "encoder_repetition_penalty": null,
24
+ "length_penalty": null,
25
+ "no_repeat_ngram_size": null,
26
+ "bad_words_ids": null,
27
+ "renormalize_logits": null,
28
+ "forced_bos_token_id": null,
29
+ "forced_eos_token_id": null,
30
+ "remove_invalid_values": null,
31
+ "exponential_decay_length_penalty": null,
32
+ "suppress_tokens": null,
33
+ "begin_suppress_tokens": null,
34
+ "sequence_bias": null,
35
+ "token_healing": null,
36
+ "guidance_scale": null,
37
+ "watermarking_config": null,
38
+ "num_return_sequences": null,
39
+ "output_attentions": false,
40
+ "output_hidden_states": false,
41
+ "output_scores": null,
42
+ "output_logits": null,
43
+ "return_dict_in_generate": null,
44
+ "pad_token_id": null,
45
+ "bos_token_id": null,
46
+ "eos_token_id": 248044,
47
+ "encoder_no_repeat_ngram_size": null,
48
+ "decoder_start_token_id": null,
49
+ "is_assistant": null,
50
+ "num_assistant_tokens": null,
51
+ "num_assistant_tokens_schedule": null,
52
+ "assistant_confidence_threshold": null,
53
+ "prompt_lookup_num_tokens": null,
54
+ "max_matching_ngram_size": null,
55
+ "assistant_early_exit": null,
56
+ "assistant_lookbehind": null,
57
+ "target_lookbehind": null,
58
+ "compile_config": null,
59
+ "disable_compile": null,
60
+ "low_memory": null,
61
+ "penalty_alpha": null,
62
+ "dola_layers": null,
63
+ "diversity_penalty": null,
64
+ "num_beam_groups": null,
65
+ "constraints": null,
66
+ "force_words_ids": null,
67
+ "prefill_chunk_size": null,
68
+ "_from_model_config": true,
69
+ "transformers_version": "5.3.0.dev0"
70
+ }
hf_quant_config.json ADDED
@@ -0,0 +1,156 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "config_groups": {
3
+ "group_0": {
4
+ "input_activations": {
5
+ "dynamic": false,
6
+ "num_bits": 4,
7
+ "type": "float",
8
+ "group_size": 16
9
+ },
10
+ "weights": {
11
+ "dynamic": false,
12
+ "num_bits": 4,
13
+ "type": "float",
14
+ "group_size": 16
15
+ },
16
+ "targets": [
17
+ "Linear"
18
+ ]
19
+ }
20
+ },
21
+ "ignore": [
22
+ "lm_head",
23
+ "model.language_model.layers.0.linear_attn*",
24
+ "model.language_model.layers.0.mlp.shared_expert_gate",
25
+ "model.language_model.layers.1.linear_attn*",
26
+ "model.language_model.layers.1.mlp.shared_expert_gate",
27
+ "model.language_model.layers.10.linear_attn*",
28
+ "model.language_model.layers.10.mlp.shared_expert_gate",
29
+ "model.language_model.layers.11.mlp.shared_expert_gate",
30
+ "model.language_model.layers.11.self_attn*",
31
+ "model.language_model.layers.12.linear_attn*",
32
+ "model.language_model.layers.12.mlp.shared_expert_gate",
33
+ "model.language_model.layers.13.linear_attn*",
34
+ "model.language_model.layers.13.mlp.shared_expert_gate",
35
+ "model.language_model.layers.14.linear_attn*",
36
+ "model.language_model.layers.14.mlp.shared_expert_gate",
37
+ "model.language_model.layers.15.mlp.shared_expert_gate",
38
+ "model.language_model.layers.15.self_attn*",
39
+ "model.language_model.layers.16.linear_attn*",
40
+ "model.language_model.layers.16.mlp.shared_expert_gate",
41
+ "model.language_model.layers.17.linear_attn*",
42
+ "model.language_model.layers.17.mlp.shared_expert_gate",
43
+ "model.language_model.layers.18.linear_attn*",
44
+ "model.language_model.layers.18.mlp.shared_expert_gate",
45
+ "model.language_model.layers.19.mlp.shared_expert_gate",
46
+ "model.language_model.layers.19.self_attn*",
47
+ "model.language_model.layers.2.linear_attn*",
48
+ "model.language_model.layers.2.mlp.shared_expert_gate",
49
+ "model.language_model.layers.20.linear_attn*",
50
+ "model.language_model.layers.20.mlp.shared_expert_gate",
51
+ "model.language_model.layers.21.linear_attn*",
52
+ "model.language_model.layers.21.mlp.shared_expert_gate",
53
+ "model.language_model.layers.22.linear_attn*",
54
+ "model.language_model.layers.22.mlp.shared_expert_gate",
55
+ "model.language_model.layers.23.mlp.shared_expert_gate",
56
+ "model.language_model.layers.23.self_attn*",
57
+ "model.language_model.layers.24.linear_attn*",
58
+ "model.language_model.layers.24.mlp.shared_expert_gate",
59
+ "model.language_model.layers.25.linear_attn*",
60
+ "model.language_model.layers.25.mlp.shared_expert_gate",
61
+ "model.language_model.layers.26.linear_attn*",
62
+ "model.language_model.layers.26.mlp.shared_expert_gate",
63
+ "model.language_model.layers.27.mlp.shared_expert_gate",
64
+ "model.language_model.layers.27.self_attn*",
65
+ "model.language_model.layers.28.linear_attn*",
66
+ "model.language_model.layers.28.mlp.shared_expert_gate",
67
+ "model.language_model.layers.29.linear_attn*",
68
+ "model.language_model.layers.29.mlp.shared_expert_gate",
69
+ "model.language_model.layers.3.mlp.shared_expert_gate",
70
+ "model.language_model.layers.3.self_attn*",
71
+ "model.language_model.layers.30.linear_attn*",
72
+ "model.language_model.layers.30.mlp.shared_expert_gate",
73
+ "model.language_model.layers.31.mlp.shared_expert_gate",
74
+ "model.language_model.layers.31.self_attn*",
75
+ "model.language_model.layers.32.linear_attn*",
76
+ "model.language_model.layers.32.mlp.shared_expert_gate",
77
+ "model.language_model.layers.33.linear_attn*",
78
+ "model.language_model.layers.33.mlp.shared_expert_gate",
79
+ "model.language_model.layers.34.linear_attn*",
80
+ "model.language_model.layers.34.mlp.shared_expert_gate",
81
+ "model.language_model.layers.35.mlp.shared_expert_gate",
82
+ "model.language_model.layers.35.self_attn*",
83
+ "model.language_model.layers.36.linear_attn*",
84
+ "model.language_model.layers.36.mlp.shared_expert_gate",
85
+ "model.language_model.layers.37.linear_attn*",
86
+ "model.language_model.layers.37.mlp.shared_expert_gate",
87
+ "model.language_model.layers.38.linear_attn*",
88
+ "model.language_model.layers.38.mlp.shared_expert_gate",
89
+ "model.language_model.layers.39.mlp.shared_expert_gate",
90
+ "model.language_model.layers.39.self_attn*",
91
+ "model.language_model.layers.4.linear_attn*",
92
+ "model.language_model.layers.4.mlp.shared_expert_gate",
93
+ "model.language_model.layers.40.linear_attn*",
94
+ "model.language_model.layers.40.mlp.shared_expert_gate",
95
+ "model.language_model.layers.41.linear_attn*",
96
+ "model.language_model.layers.41.mlp.shared_expert_gate",
97
+ "model.language_model.layers.42.linear_attn*",
98
+ "model.language_model.layers.42.mlp.shared_expert_gate",
99
+ "model.language_model.layers.43.mlp.shared_expert_gate",
100
+ "model.language_model.layers.43.self_attn*",
101
+ "model.language_model.layers.44.linear_attn*",
102
+ "model.language_model.layers.44.mlp.shared_expert_gate",
103
+ "model.language_model.layers.45.linear_attn*",
104
+ "model.language_model.layers.45.mlp.shared_expert_gate",
105
+ "model.language_model.layers.46.linear_attn*",
106
+ "model.language_model.layers.46.mlp.shared_expert_gate",
107
+ "model.language_model.layers.47.mlp.shared_expert_gate",
108
+ "model.language_model.layers.47.self_attn*",
109
+ "model.language_model.layers.48.linear_attn*",
110
+ "model.language_model.layers.48.mlp.shared_expert_gate",
111
+ "model.language_model.layers.49.linear_attn*",
112
+ "model.language_model.layers.49.mlp.shared_expert_gate",
113
+ "model.language_model.layers.5.linear_attn*",
114
+ "model.language_model.layers.5.mlp.shared_expert_gate",
115
+ "model.language_model.layers.50.linear_attn*",
116
+ "model.language_model.layers.50.mlp.shared_expert_gate",
117
+ "model.language_model.layers.51.mlp.shared_expert_gate",
118
+ "model.language_model.layers.51.self_attn*",
119
+ "model.language_model.layers.52.linear_attn*",
120
+ "model.language_model.layers.52.mlp.shared_expert_gate",
121
+ "model.language_model.layers.53.linear_attn*",
122
+ "model.language_model.layers.53.mlp.shared_expert_gate",
123
+ "model.language_model.layers.54.linear_attn*",
124
+ "model.language_model.layers.54.mlp.shared_expert_gate",
125
+ "model.language_model.layers.55.mlp.shared_expert_gate",
126
+ "model.language_model.layers.55.self_attn*",
127
+ "model.language_model.layers.56.linear_attn*",
128
+ "model.language_model.layers.56.mlp.shared_expert_gate",
129
+ "model.language_model.layers.57.linear_attn*",
130
+ "model.language_model.layers.57.mlp.shared_expert_gate",
131
+ "model.language_model.layers.58.linear_attn*",
132
+ "model.language_model.layers.58.mlp.shared_expert_gate",
133
+ "model.language_model.layers.59.mlp.shared_expert_gate",
134
+ "model.language_model.layers.59.self_attn*",
135
+ "model.language_model.layers.6.linear_attn*",
136
+ "model.language_model.layers.6.mlp.shared_expert_gate",
137
+ "model.language_model.layers.7.mlp.shared_expert_gate",
138
+ "model.language_model.layers.7.self_attn*",
139
+ "model.language_model.layers.8.linear_attn*",
140
+ "model.language_model.layers.8.mlp.shared_expert_gate",
141
+ "model.language_model.layers.9.linear_attn*",
142
+ "model.language_model.layers.9.mlp.shared_expert_gate",
143
+ "model.visual*"
144
+ ],
145
+ "quant_algo": "NVFP4",
146
+ "kv_cache_scheme": {
147
+ "dynamic": false,
148
+ "num_bits": 8,
149
+ "type": "float"
150
+ },
151
+ "producer": {
152
+ "name": "modelopt",
153
+ "version": "0.43.0.dev82+gd3748c2c6"
154
+ },
155
+ "quant_method": "modelopt"
156
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4484e1077b32eba64c73a5a1f49e08e0861469fbca96ec285eb9b14a35e2e60d
3
+ size 5370741772
model-00002-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8fcf044dfc76fdb198e777e970dc3ce362412be16ae9daf3a314bd6f8d8bab8
3
+ size 5370257024
model-00003-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e52b468defcf6d75bfbc115877178979f9899c395152df98c1cda0a4a709345
3
+ size 5369901700
model-00004-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3f3de0b7a62f208d1d01e9cfb3a32bd3bb66eaf86ffb6c64aa1200c2da477e1
3
+ size 5369815384
model-00005-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc3fb906adc576d9ced22c156513b52d248551cd4d208278859a14cc8b0f4a27
3
+ size 5370257480
model-00006-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5d2164bd06b7a8306d85b4491e97b4473f3d5923569bd1398ddd3d3d4401a98
3
+ size 5369722444
model-00007-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d547548964abbd3d117ce430e19c447936296cd83d8aa0385a7891ecbd48827a
3
+ size 5369994480
model-00008-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4a5c9aac049e207b6a51522a3f904012dadfdb19f5720273ba1696be0e82ff5
3
+ size 5370261512
model-00009-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c471ab728e77a38662b4a51c716253928010c5d3030ad7a0b3e766115ce50c67
3
+ size 5369728004
model-00010-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f28d01880111e2c07755dec4b7b926acc08ba95969924c915f844482f0174f8a
3
+ size 5370001728
model-00011-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73850f57defd497fcda4dc0be638a49ebcea901d4532cb3727957d661f836d91
3
+ size 5419806836
model-00012-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:476e1ef0e144f25ca61f1ee9fb25b79c2f957e7411b30201e41b0376bd58c549
3
+ size 5369739180
model-00014-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4e0b014e6445b330e2ceb82253f1b184c92c462c53c870f91d5f3818c649009
3
+ size 5369728076
model-00015-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82a1fbbdc2785e595fa70a0c104924766e8fc26c45bf78a4f3357898f033b0ab
3
+ size 5370001648
model-00016-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0ff40db3ec54144c09d296c7b86b1bed23930825806d14741bf121eeca8d182
3
+ size 5428320940
model-00022-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24ccee13a1841087019c5317974560bc9e7c97c991d40374da93056d201c6e35
3
+ size 5369821624
model-00023-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4be6556a8893508f78e80600446088c1f984b2c2be1ec1691a34907edc2cb3c7
3
+ size 5369908268
model-00024-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8dd33eef8d53642c3ebf3158bc97c0e4041a7e16bf89ebf2bf3b74068e48a25
3
+ size 5369822176
model-00025-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d5aa1a900cbf2133a794596745de9fa39800e92a2f050590833cbbb4adc155d
3
+ size 5370263472
model-00026-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:acab32aa0ff96a9dc1ab2737059125264683e8143041c42db7a5d33bbd64fbc0
3
+ size 5369908260
model-00027-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:581b4964037fe4aef9be64b957e53ef279990528c44bf3fe1629facfd25300b0
3
+ size 5369821632
model-00028-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfc32628340d8c4539ba6cae15bfaf2b39a72979e43fd2aea2622440105dbb98
3
+ size 5370264016
model-00029-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90f374ee7988791f31b50fb69f6086e1b8a4e7114a1e5b1fc5626aacb6232951
3
+ size 5369728804
model-00030-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f07b919ea488fd0ef269274ec9da46bc15cb923cdca219db0ec8f2aa326f9e08
3
+ size 5370000920
model-00031-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c643c1c7cdbc9686556b7723d61fba9084ad0e3f2758f53e08f68d297aa1d743
3
+ size 5370264016
model-00032-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f00e92d5d619263008e91dcd928b9ef0795e1cad71d3bab035ebbeea231fb58
3
+ size 5369728004
model-00034-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b164ace235146e514edcd30d29d5400f0c19d46d98cd9aaead74174f0fc2ba4d
3
+ size 5415100292
model-00035-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92c538b1fc75de677272b588ec72d8b0e89f7a4418629f3e59ca0ad52acfdcec
3
+ size 5369726284
model-00036-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fcf30d777423f50c3ff9ec6f9d4fc7a31bd3dd00204dc2398844e76a85cbc41
3
+ size 5370001728
model-00037-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6669da89f9ff2d50e949354c4b5bb9ee2fa9cc768d9e1a152287023452bbdfd8
3
+ size 5369728172
model-00038-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:965c10f1e8cec81478442db38f240ea861a5ea17fba62daed9b98e9da82ea32c
3
+ size 5370001544
model-00039-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d7564f3eedf395ba3c157082e871f70219186c08b4bb453412897fbc3689607
3
+ size 5370264024
model-00040-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e13ee60e854f331cccec8e7dc4d36ee7bd29fbb280bda1d00bc6fda5f6ae83c
3
+ size 5369727988
model-00041-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f94adb095b05ef2889f71cb4844845e9940293a834555e9987cf911a9531364
3
+ size 5370001728
model-00042-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f92dc1c11951350c4a2d73e8dfa010daab0c9e297abf8e43a4a72cdb05bebae9
3
+ size 5369822096
model-00043-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3b3a8f30ff8a95409c11ac1427c7d3426a8f2e3b51170c88ff23391635de4b2
3
+ size 5369907796
model-00044-of-00044.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44b3b276f689a5ceafa9cca096a042fc742c1f5e93c14b8ee30fa97123d5d3a2
3
+ size 5833837332
model-inputscales.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:311fcc19cd167c688eb04efb64a17c9e86b4aa60e81842d31fcb6b55adbf4f5e
3
+ size 12129288
model-mtp.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a62def835563aedc03bacfad3087f64ad128c8eac9cb8ac9f526ac42dd0cde6
3
+ size 13191327760
model.safetensors.index.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d2e8d01b04c323649ab245911ed6453083bc80fbb7601af459f974b71e80c85
3
+ size 40833519
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 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 | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}\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
+ }