Hugging Face's logo

HYHPING2023
/
checkpoint-modelopt-nvfp4

Safetensors
qwen3_5_moe
8-bit precision
modelopt_fp4
Model card Files
xet
 Community
HYHPING2023 commited on
Commit
edec99e
·
verified ·
1 Parent(s): 727aa29

Upload folder using huggingface_hub

Browse files
Files changed (13) hide show
  1. .gitattributes +2 -0
  2. .quant_summary.txt +0 -0
  3. chat_template.jinja +154 -0
  4. config.json +280 -0
  5. generation_config.json +6 -0
  6. hf_quant_config.json +136 -0
  7. model-00001-of-00003.safetensors +3 -0
  8. model-00002-of-00003.safetensors +3 -0
  9. model-00003-of-00003.safetensors +3 -0
  10. model.safetensors.index.json +3 -0
  11. processor_config.json +63 -0
  12. tokenizer.json +3 -0
  13. tokenizer_config.json +33 -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
.quant_summary.txt ADDED
The diff for this file is too large to render. See raw diff
 
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 +1,280 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3_5MoeForConditionalGeneration"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "hidden_size": 2048,
7
+ "image_token_id": 248056,
8
+ "model_type": "qwen3_5_moe",
9
+ "text_config": {
10
+ "attention_bias": false,
11
+ "attention_dropout": 0.0,
12
+ "attn_output_gate": true,
13
+ "bos_token_id": null,
14
+ "dtype": "bfloat16",
15
+ "eos_token_id": 248044,
16
+ "full_attention_interval": 4,
17
+ "head_dim": 256,
18
+ "hidden_act": "silu",
19
+ "hidden_size": 2048,
20
+ "initializer_range": 0.02,
21
+ "layer_types": [
22
+ "linear_attention",
23
+ "linear_attention",
24
+ "linear_attention",
25
+ "full_attention",
26
+ "linear_attention",
27
+ "linear_attention",
28
+ "linear_attention",
29
+ "full_attention",
30
+ "linear_attention",
31
+ "linear_attention",
32
+ "linear_attention",
33
+ "full_attention",
34
+ "linear_attention",
35
+ "linear_attention",
36
+ "linear_attention",
37
+ "full_attention",
38
+ "linear_attention",
39
+ "linear_attention",
40
+ "linear_attention",
41
+ "full_attention",
42
+ "linear_attention",
43
+ "linear_attention",
44
+ "linear_attention",
45
+ "full_attention",
46
+ "linear_attention",
47
+ "linear_attention",
48
+ "linear_attention",
49
+ "full_attention",
50
+ "linear_attention",
51
+ "linear_attention",
52
+ "linear_attention",
53
+ "full_attention",
54
+ "linear_attention",
55
+ "linear_attention",
56
+ "linear_attention",
57
+ "full_attention",
58
+ "linear_attention",
59
+ "linear_attention",
60
+ "linear_attention",
61
+ "full_attention"
62
+ ],
63
+ "linear_conv_kernel_dim": 4,
64
+ "linear_key_head_dim": 128,
65
+ "linear_num_key_heads": 16,
66
+ "linear_num_value_heads": 32,
67
+ "linear_value_head_dim": 128,
68
+ "mamba_ssm_dtype": "float32",
69
+ "max_position_embeddings": 262144,
70
+ "mlp_only_layers": [],
71
+ "model_type": "qwen3_5_moe_text",
72
+ "moe_intermediate_size": 512,
73
+ "mtp_num_hidden_layers": 1,
74
+ "mtp_use_dedicated_embeddings": false,
75
+ "num_attention_heads": 16,
76
+ "num_experts": 256,
77
+ "num_experts_per_tok": 8,
78
+ "num_hidden_layers": 40,
79
+ "num_key_value_heads": 2,
80
+ "output_router_logits": false,
81
+ "pad_token_id": null,
82
+ "partial_rotary_factor": 0.25,
83
+ "rms_norm_eps": 1e-06,
84
+ "rope_parameters": {
85
+ "mrope_interleaved": true,
86
+ "mrope_section": [
87
+ 11,
88
+ 11,
89
+ 10
90
+ ],
91
+ "partial_rotary_factor": 0.25,
92
+ "rope_theta": 10000000,
93
+ "rope_type": "default"
94
+ },
95
+ "router_aux_loss_coef": 0.001,
96
+ "shared_expert_intermediate_size": 512,
97
+ "tie_word_embeddings": false,
98
+ "use_cache": true,
99
+ "vocab_size": 248320
100
+ },
101
+ "tie_word_embeddings": false,
102
+ "transformers_version": "5.5.4",
103
+ "video_token_id": 248057,
104
+ "vision_config": {
105
+ "deepstack_visual_indexes": [],
106
+ "depth": 27,
107
+ "dtype": "bfloat16",
108
+ "hidden_act": "gelu_pytorch_tanh",
109
+ "hidden_size": 1152,
110
+ "in_channels": 3,
111
+ "initializer_range": 0.02,
112
+ "intermediate_size": 4304,
113
+ "model_type": "qwen3_5_moe",
114
+ "num_heads": 16,
115
+ "num_position_embeddings": 2304,
116
+ "out_hidden_size": 2048,
117
+ "patch_size": 16,
118
+ "spatial_merge_size": 2,
119
+ "temporal_patch_size": 2
120
+ },
121
+ "vision_end_token_id": 248054,
122
+ "vision_start_token_id": 248053,
123
+ "quantization_config": {
124
+ "config_groups": {
125
+ "group_0": {
126
+ "input_activations": {
127
+ "dynamic": false,
128
+ "num_bits": 4,
129
+ "type": "float",
130
+ "group_size": 16
131
+ },
132
+ "weights": {
133
+ "dynamic": false,
134
+ "num_bits": 4,
135
+ "type": "float",
136
+ "group_size": 16
137
+ },
138
+ "targets": [
139
+ "Linear"
140
+ ]
141
+ }
142
+ },
143
+ "ignore": [
144
+ "lm_head",
145
+ "model.language_model.embed_tokens",
146
+ "model.language_model.layers.0.linear_attn*",
147
+ "model.language_model.layers.0.mlp.shared_expert*",
148
+ "model.language_model.layers.0.mlp.shared_expert_gate",
149
+ "model.language_model.layers.1.linear_attn*",
150
+ "model.language_model.layers.1.mlp.shared_expert*",
151
+ "model.language_model.layers.1.mlp.shared_expert_gate",
152
+ "model.language_model.layers.10.linear_attn*",
153
+ "model.language_model.layers.10.mlp.shared_expert*",
154
+ "model.language_model.layers.10.mlp.shared_expert_gate",
155
+ "model.language_model.layers.11.mlp.shared_expert*",
156
+ "model.language_model.layers.11.mlp.shared_expert_gate",
157
+ "model.language_model.layers.11.self_attn*",
158
+ "model.language_model.layers.12.linear_attn*",
159
+ "model.language_model.layers.12.mlp.shared_expert*",
160
+ "model.language_model.layers.12.mlp.shared_expert_gate",
161
+ "model.language_model.layers.13.linear_attn*",
162
+ "model.language_model.layers.13.mlp.shared_expert*",
163
+ "model.language_model.layers.13.mlp.shared_expert_gate",
164
+ "model.language_model.layers.14.linear_attn*",
165
+ "model.language_model.layers.14.mlp.shared_expert*",
166
+ "model.language_model.layers.14.mlp.shared_expert_gate",
167
+ "model.language_model.layers.15.mlp.shared_expert*",
168
+ "model.language_model.layers.15.mlp.shared_expert_gate",
169
+ "model.language_model.layers.15.self_attn*",
170
+ "model.language_model.layers.16.linear_attn*",
171
+ "model.language_model.layers.16.mlp.shared_expert*",
172
+ "model.language_model.layers.16.mlp.shared_expert_gate",
173
+ "model.language_model.layers.17.linear_attn*",
174
+ "model.language_model.layers.17.mlp.shared_expert*",
175
+ "model.language_model.layers.17.mlp.shared_expert_gate",
176
+ "model.language_model.layers.18.linear_attn*",
177
+ "model.language_model.layers.18.mlp.shared_expert*",
178
+ "model.language_model.layers.18.mlp.shared_expert_gate",
179
+ "model.language_model.layers.19.mlp.shared_expert*",
180
+ "model.language_model.layers.19.mlp.shared_expert_gate",
181
+ "model.language_model.layers.19.self_attn*",
182
+ "model.language_model.layers.2.linear_attn*",
183
+ "model.language_model.layers.2.mlp.shared_expert*",
184
+ "model.language_model.layers.2.mlp.shared_expert_gate",
185
+ "model.language_model.layers.20.linear_attn*",
186
+ "model.language_model.layers.20.mlp.shared_expert*",
187
+ "model.language_model.layers.20.mlp.shared_expert_gate",
188
+ "model.language_model.layers.21.linear_attn*",
189
+ "model.language_model.layers.21.mlp.shared_expert*",
190
+ "model.language_model.layers.21.mlp.shared_expert_gate",
191
+ "model.language_model.layers.22.linear_attn*",
192
+ "model.language_model.layers.22.mlp.shared_expert*",
193
+ "model.language_model.layers.22.mlp.shared_expert_gate",
194
+ "model.language_model.layers.23.mlp.shared_expert*",
195
+ "model.language_model.layers.23.mlp.shared_expert_gate",
196
+ "model.language_model.layers.23.self_attn*",
197
+ "model.language_model.layers.24.linear_attn*",
198
+ "model.language_model.layers.24.mlp.shared_expert*",
199
+ "model.language_model.layers.24.mlp.shared_expert_gate",
200
+ "model.language_model.layers.25.linear_attn*",
201
+ "model.language_model.layers.25.mlp.shared_expert*",
202
+ "model.language_model.layers.25.mlp.shared_expert_gate",
203
+ "model.language_model.layers.26.linear_attn*",
204
+ "model.language_model.layers.26.mlp.shared_expert*",
205
+ "model.language_model.layers.26.mlp.shared_expert_gate",
206
+ "model.language_model.layers.27.mlp.shared_expert*",
207
+ "model.language_model.layers.27.mlp.shared_expert_gate",
208
+ "model.language_model.layers.27.self_attn*",
209
+ "model.language_model.layers.28.linear_attn*",
210
+ "model.language_model.layers.28.mlp.shared_expert*",
211
+ "model.language_model.layers.28.mlp.shared_expert_gate",
212
+ "model.language_model.layers.29.linear_attn*",
213
+ "model.language_model.layers.29.mlp.shared_expert*",
214
+ "model.language_model.layers.29.mlp.shared_expert_gate",
215
+ "model.language_model.layers.3.mlp.shared_expert*",
216
+ "model.language_model.layers.3.mlp.shared_expert_gate",
217
+ "model.language_model.layers.3.self_attn*",
218
+ "model.language_model.layers.30.linear_attn*",
219
+ "model.language_model.layers.30.mlp.shared_expert*",
220
+ "model.language_model.layers.30.mlp.shared_expert_gate",
221
+ "model.language_model.layers.31.mlp.shared_expert*",
222
+ "model.language_model.layers.31.mlp.shared_expert_gate",
223
+ "model.language_model.layers.31.self_attn*",
224
+ "model.language_model.layers.32.linear_attn*",
225
+ "model.language_model.layers.32.mlp.shared_expert*",
226
+ "model.language_model.layers.32.mlp.shared_expert_gate",
227
+ "model.language_model.layers.33.linear_attn*",
228
+ "model.language_model.layers.33.mlp.shared_expert*",
229
+ "model.language_model.layers.33.mlp.shared_expert_gate",
230
+ "model.language_model.layers.34.linear_attn*",
231
+ "model.language_model.layers.34.mlp.shared_expert*",
232
+ "model.language_model.layers.34.mlp.shared_expert_gate",
233
+ "model.language_model.layers.35.mlp.shared_expert*",
234
+ "model.language_model.layers.35.mlp.shared_expert_gate",
235
+ "model.language_model.layers.35.self_attn*",
236
+ "model.language_model.layers.36.linear_attn*",
237
+ "model.language_model.layers.36.mlp.shared_expert*",
238
+ "model.language_model.layers.36.mlp.shared_expert_gate",
239
+ "model.language_model.layers.37.linear_attn*",
240
+ "model.language_model.layers.37.mlp.shared_expert*",
241
+ "model.language_model.layers.37.mlp.shared_expert_gate",
242
+ "model.language_model.layers.38.linear_attn*",
243
+ "model.language_model.layers.38.mlp.shared_expert*",
244
+ "model.language_model.layers.38.mlp.shared_expert_gate",
245
+ "model.language_model.layers.39.mlp.shared_expert*",
246
+ "model.language_model.layers.39.mlp.shared_expert_gate",
247
+ "model.language_model.layers.39.self_attn*",
248
+ "model.language_model.layers.4.linear_attn*",
249
+ "model.language_model.layers.4.mlp.shared_expert*",
250
+ "model.language_model.layers.4.mlp.shared_expert_gate",
251
+ "model.language_model.layers.5.linear_attn*",
252
+ "model.language_model.layers.5.mlp.shared_expert*",
253
+ "model.language_model.layers.5.mlp.shared_expert_gate",
254
+ "model.language_model.layers.6.linear_attn*",
255
+ "model.language_model.layers.6.mlp.shared_expert*",
256
+ "model.language_model.layers.6.mlp.shared_expert_gate",
257
+ "model.language_model.layers.7.mlp.shared_expert*",
258
+ "model.language_model.layers.7.mlp.shared_expert_gate",
259
+ "model.language_model.layers.7.self_attn*",
260
+ "model.language_model.layers.8.linear_attn*",
261
+ "model.language_model.layers.8.mlp.shared_expert*",
262
+ "model.language_model.layers.8.mlp.shared_expert_gate",
263
+ "model.language_model.layers.9.linear_attn*",
264
+ "model.language_model.layers.9.mlp.shared_expert*",
265
+ "model.language_model.layers.9.mlp.shared_expert_gate",
266
+ "model.visual*"
267
+ ],
268
+ "quant_algo": "NVFP4",
269
+ "kv_cache_scheme": {
270
+ "dynamic": false,
271
+ "num_bits": 8,
272
+ "type": "float"
273
+ },
274
+ "producer": {
275
+ "name": "modelopt",
276
+ "version": "0.46.0.dev116+gc5e716701"
277
+ },
278
+ "quant_method": "modelopt"
279
+ }
280
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "eos_token_id": 248044,
4
+ "transformers_version": "5.5.4",
5
+ "use_cache": true
6
+ }
hf_quant_config.json ADDED
@@ -0,0 +1,136 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "producer": {
3
+ "name": "modelopt",
4
+ "version": "0.46.0.dev116+gc5e716701"
5
+ },
6
+ "quantization": {
7
+ "quant_algo": "NVFP4",
8
+ "kv_cache_quant_algo": "FP8",
9
+ "group_size": 16,
10
+ "exclude_modules": [
11
+ "lm_head",
12
+ "model.language_model.embed_tokens",
13
+ "model.language_model.layers.0.linear_attn*",
14
+ "model.language_model.layers.0.mlp.shared_expert*",
15
+ "model.language_model.layers.0.mlp.shared_expert_gate",
16
+ "model.language_model.layers.1.linear_attn*",
17
+ "model.language_model.layers.1.mlp.shared_expert*",
18
+ "model.language_model.layers.1.mlp.shared_expert_gate",
19
+ "model.language_model.layers.10.linear_attn*",
20
+ "model.language_model.layers.10.mlp.shared_expert*",
21
+ "model.language_model.layers.10.mlp.shared_expert_gate",
22
+ "model.language_model.layers.11.mlp.shared_expert*",
23
+ "model.language_model.layers.11.mlp.shared_expert_gate",
24
+ "model.language_model.layers.11.self_attn*",
25
+ "model.language_model.layers.12.linear_attn*",
26
+ "model.language_model.layers.12.mlp.shared_expert*",
27
+ "model.language_model.layers.12.mlp.shared_expert_gate",
28
+ "model.language_model.layers.13.linear_attn*",
29
+ "model.language_model.layers.13.mlp.shared_expert*",
30
+ "model.language_model.layers.13.mlp.shared_expert_gate",
31
+ "model.language_model.layers.14.linear_attn*",
32
+ "model.language_model.layers.14.mlp.shared_expert*",
33
+ "model.language_model.layers.14.mlp.shared_expert_gate",
34
+ "model.language_model.layers.15.mlp.shared_expert*",
35
+ "model.language_model.layers.15.mlp.shared_expert_gate",
36
+ "model.language_model.layers.15.self_attn*",
37
+ "model.language_model.layers.16.linear_attn*",
38
+ "model.language_model.layers.16.mlp.shared_expert*",
39
+ "model.language_model.layers.16.mlp.shared_expert_gate",
40
+ "model.language_model.layers.17.linear_attn*",
41
+ "model.language_model.layers.17.mlp.shared_expert*",
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*",
45
+ "model.language_model.layers.18.mlp.shared_expert_gate",
46
+ "model.language_model.layers.19.mlp.shared_expert*",
47
+ "model.language_model.layers.19.mlp.shared_expert_gate",
48
+ "model.language_model.layers.19.self_attn*",
49
+ "model.language_model.layers.2.linear_attn*",
50
+ "model.language_model.layers.2.mlp.shared_expert*",
51
+ "model.language_model.layers.2.mlp.shared_expert_gate",
52
+ "model.language_model.layers.20.linear_attn*",
53
+ "model.language_model.layers.20.mlp.shared_expert*",
54
+ "model.language_model.layers.20.mlp.shared_expert_gate",
55
+ "model.language_model.layers.21.linear_attn*",
56
+ "model.language_model.layers.21.mlp.shared_expert*",
57
+ "model.language_model.layers.21.mlp.shared_expert_gate",
58
+ "model.language_model.layers.22.linear_attn*",
59
+ "model.language_model.layers.22.mlp.shared_expert*",
60
+ "model.language_model.layers.22.mlp.shared_expert_gate",
61
+ "model.language_model.layers.23.mlp.shared_expert*",
62
+ "model.language_model.layers.23.mlp.shared_expert_gate",
63
+ "model.language_model.layers.23.self_attn*",
64
+ "model.language_model.layers.24.linear_attn*",
65
+ "model.language_model.layers.24.mlp.shared_expert*",
66
+ "model.language_model.layers.24.mlp.shared_expert_gate",
67
+ "model.language_model.layers.25.linear_attn*",
68
+ "model.language_model.layers.25.mlp.shared_expert*",
69
+ "model.language_model.layers.25.mlp.shared_expert_gate",
70
+ "model.language_model.layers.26.linear_attn*",
71
+ "model.language_model.layers.26.mlp.shared_expert*",
72
+ "model.language_model.layers.26.mlp.shared_expert_gate",
73
+ "model.language_model.layers.27.mlp.shared_expert*",
74
+ "model.language_model.layers.27.mlp.shared_expert_gate",
75
+ "model.language_model.layers.27.self_attn*",
76
+ "model.language_model.layers.28.linear_attn*",
77
+ "model.language_model.layers.28.mlp.shared_expert*",
78
+ "model.language_model.layers.28.mlp.shared_expert_gate",
79
+ "model.language_model.layers.29.linear_attn*",
80
+ "model.language_model.layers.29.mlp.shared_expert*",
81
+ "model.language_model.layers.29.mlp.shared_expert_gate",
82
+ "model.language_model.layers.3.mlp.shared_expert*",
83
+ "model.language_model.layers.3.mlp.shared_expert_gate",
84
+ "model.language_model.layers.3.self_attn*",
85
+ "model.language_model.layers.30.linear_attn*",
86
+ "model.language_model.layers.30.mlp.shared_expert*",
87
+ "model.language_model.layers.30.mlp.shared_expert_gate",
88
+ "model.language_model.layers.31.mlp.shared_expert*",
89
+ "model.language_model.layers.31.mlp.shared_expert_gate",
90
+ "model.language_model.layers.31.self_attn*",
91
+ "model.language_model.layers.32.linear_attn*",
92
+ "model.language_model.layers.32.mlp.shared_expert*",
93
+ "model.language_model.layers.32.mlp.shared_expert_gate",
94
+ "model.language_model.layers.33.linear_attn*",
95
+ "model.language_model.layers.33.mlp.shared_expert*",
96
+ "model.language_model.layers.33.mlp.shared_expert_gate",
97
+ "model.language_model.layers.34.linear_attn*",
98
+ "model.language_model.layers.34.mlp.shared_expert*",
99
+ "model.language_model.layers.34.mlp.shared_expert_gate",
100
+ "model.language_model.layers.35.mlp.shared_expert*",
101
+ "model.language_model.layers.35.mlp.shared_expert_gate",
102
+ "model.language_model.layers.35.self_attn*",
103
+ "model.language_model.layers.36.linear_attn*",
104
+ "model.language_model.layers.36.mlp.shared_expert*",
105
+ "model.language_model.layers.36.mlp.shared_expert_gate",
106
+ "model.language_model.layers.37.linear_attn*",
107
+ "model.language_model.layers.37.mlp.shared_expert*",
108
+ "model.language_model.layers.37.mlp.shared_expert_gate",
109
+ "model.language_model.layers.38.linear_attn*",
110
+ "model.language_model.layers.38.mlp.shared_expert*",
111
+ "model.language_model.layers.38.mlp.shared_expert_gate",
112
+ "model.language_model.layers.39.mlp.shared_expert*",
113
+ "model.language_model.layers.39.mlp.shared_expert_gate",
114
+ "model.language_model.layers.39.self_attn*",
115
+ "model.language_model.layers.4.linear_attn*",
116
+ "model.language_model.layers.4.mlp.shared_expert*",
117
+ "model.language_model.layers.4.mlp.shared_expert_gate",
118
+ "model.language_model.layers.5.linear_attn*",
119
+ "model.language_model.layers.5.mlp.shared_expert*",
120
+ "model.language_model.layers.5.mlp.shared_expert_gate",
121
+ "model.language_model.layers.6.linear_attn*",
122
+ "model.language_model.layers.6.mlp.shared_expert*",
123
+ "model.language_model.layers.6.mlp.shared_expert_gate",
124
+ "model.language_model.layers.7.mlp.shared_expert*",
125
+ "model.language_model.layers.7.mlp.shared_expert_gate",
126
+ "model.language_model.layers.7.self_attn*",
127
+ "model.language_model.layers.8.linear_attn*",
128
+ "model.language_model.layers.8.mlp.shared_expert*",
129
+ "model.language_model.layers.8.mlp.shared_expert_gate",
130
+ "model.language_model.layers.9.linear_attn*",
131
+ "model.language_model.layers.9.mlp.shared_expert*",
132
+ "model.language_model.layers.9.mlp.shared_expert_gate",
133
+ "model.visual*"
134
+ ]
135
+ }
136
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:057e71eae8cd588b7ff5f13595362579e73fac4f764b9f1a81ef317274c5a849
3
+ size 10005929080
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d244f1acbb60d01cf6766437bd92400ef6ca6e80e35a89dd4c81a19f46ab6c73
3
+ size 10007729472
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5b5deb73e3b4f6713288287afc7cedec4968ed755bfb65419e532dddfb903c2
3
+ size 3912522824
model.safetensors.index.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d39d7a24a0515568440b4246223c4713bdb86b5a83b6c031c8efef458e0d457b
3
+ size 13655538
processor_config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "image_processor": {
3
+ "data_format": "channels_first",
4
+ "do_convert_rgb": true,
5
+ "do_normalize": true,
6
+ "do_rescale": true,
7
+ "do_resize": true,
8
+ "image_mean": [
9
+ 0.5,
10
+ 0.5,
11
+ 0.5
12
+ ],
13
+ "image_processor_type": "Qwen2VLImageProcessor",
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "merge_size": 2,
20
+ "patch_size": 16,
21
+ "resample": 3,
22
+ "rescale_factor": 0.00392156862745098,
23
+ "size": {
24
+ "longest_edge": 16777216,
25
+ "shortest_edge": 65536
26
+ },
27
+ "temporal_patch_size": 2
28
+ },
29
+ "processor_class": "Qwen3VLProcessor",
30
+ "video_processor": {
31
+ "data_format": "channels_first",
32
+ "default_to_square": true,
33
+ "do_convert_rgb": true,
34
+ "do_normalize": true,
35
+ "do_rescale": true,
36
+ "do_resize": true,
37
+ "do_sample_frames": true,
38
+ "fps": 2,
39
+ "image_mean": [
40
+ 0.5,
41
+ 0.5,
42
+ 0.5
43
+ ],
44
+ "image_std": [
45
+ 0.5,
46
+ 0.5,
47
+ 0.5
48
+ ],
49
+ "max_frames": 768,
50
+ "merge_size": 2,
51
+ "min_frames": 4,
52
+ "patch_size": 16,
53
+ "resample": 3,
54
+ "rescale_factor": 0.00392156862745098,
55
+ "return_metadata": false,
56
+ "size": {
57
+ "longest_edge": 25165824,
58
+ "shortest_edge": 4096
59
+ },
60
+ "temporal_patch_size": 2,
61
+ "video_processor_type": "Qwen3VLVideoProcessor"
62
+ }
63
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:639e352c0f904c1875d448ebed6f6faac005fd3eb58393b7f1fb3ff044e5ca03
3
+ size 19989510
tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "audio_bos_token": "<|audio_start|>",
4
+ "audio_eos_token": "<|audio_end|>",
5
+ "audio_token": "<|audio_pad|>",
6
+ "backend": "tokenizers",
7
+ "bos_token": null,
8
+ "clean_up_tokenization_spaces": false,
9
+ "eos_token": "<|im_end|>",
10
+ "errors": "replace",
11
+ "image_token": "<|image_pad|>",
12
+ "is_local": true,
13
+ "model_max_length": 262144,
14
+ "model_specific_special_tokens": {
15
+ "audio_bos_token": "<|audio_start|>",
16
+ "audio_eos_token": "<|audio_end|>",
17
+ "audio_token": "<|audio_pad|>",
18
+ "image_token": "<|image_pad|>",
19
+ "video_token": "<|video_pad|>",
20
+ "vision_bos_token": "<|vision_start|>",
21
+ "vision_eos_token": "<|vision_end|>"
22
+ },
23
+ "pad_token": "<|endoftext|>",
24
+ "padding_side": "left",
25
+ "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+",
26
+ "processor_class": "Qwen3VLProcessor",
27
+ "split_special_tokens": false,
28
+ "tokenizer_class": "TokenizersBackend",
29
+ "unk_token": null,
30
+ "video_token": "<|video_pad|>",
31
+ "vision_bos_token": "<|vision_start|>",
32
+ "vision_eos_token": "<|vision_end|>"
33
+ }