Hugging Face's logo

RESMP-DEV
/
Qwen3-Next-80B-A3B-Thinking-NVFP4

Text Generation
Transformers
Safetensors
English
Chinese
qwen3_next
conversational
compressed-tensors
Model card Files
xet
Community
Kearm commited on
Commit
5719fbf
·
verified ·
1 Parent(s): 2e32ad3

Add files using upload-large-folder tool

Browse files
Files changed (22) hide show
  1. .gitattributes +2 -0
  2. added_tokens.json +28 -0
  3. chat_template.jinja +86 -0
  4. config.json +344 -0
  5. generation_config.json +13 -0
  6. merges.txt +0 -0
  7. model-00001-of-00010.safetensors +3 -0
  8. model-00002-of-00010.safetensors +3 -0
  9. model-00003-of-00010.safetensors +3 -0
  10. model-00004-of-00010.safetensors +3 -0
  11. model-00005-of-00010.safetensors +3 -0
  12. model-00006-of-00010.safetensors +3 -0
  13. model-00007-of-00010.safetensors +3 -0
  14. model-00008-of-00010.safetensors +3 -0
  15. model-00009-of-00010.safetensors +3 -0
  16. model-00010-of-00010.safetensors +3 -0
  17. model.safetensors.index.json +3 -0
  18. recipe.yaml +6 -0
  19. special_tokens_map.json +31 -0
  20. tokenizer.json +3 -0
  21. tokenizer_config.json +239 -0
  22. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
chat_template.jinja ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {{- messages[0].content + '\n\n' }}
5
+ {%- endif %}
6
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
7
+ {%- for tool in tools %}
8
+ {{- "\n" }}
9
+ {{- tool | tojson }}
10
+ {%- endfor %}
11
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
12
+ {%- else %}
13
+ {%- if messages[0].role == 'system' %}
14
+ {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
15
+ {%- endif %}
16
+ {%- endif %}
17
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
18
+ {%- for message in messages[::-1] %}
19
+ {%- set index = (messages|length - 1) - loop.index0 %}
20
+ {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
21
+ {%- set ns.multi_step_tool = false %}
22
+ {%- set ns.last_query_index = index %}
23
+ {%- endif %}
24
+ {%- endfor %}
25
+ {%- for message in messages %}
26
+ {%- if message.content is string %}
27
+ {%- set content = message.content %}
28
+ {%- else %}
29
+ {%- set content = '' %}
30
+ {%- endif %}
31
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
32
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
33
+ {%- elif message.role == "assistant" %}
34
+ {%- set reasoning_content = '' %}
35
+ {%- if message.reasoning_content is string %}
36
+ {%- set reasoning_content = message.reasoning_content %}
37
+ {%- else %}
38
+ {%- if '</think>' in content %}
39
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
40
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
41
+ {%- endif %}
42
+ {%- endif %}
43
+ {%- if loop.index0 > ns.last_query_index %}
44
+ {%- if loop.last or (not loop.last and reasoning_content) %}
45
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
46
+ {%- else %}
47
+ {{- '<|im_start|>' + message.role + '\n' + content }}
48
+ {%- endif %}
49
+ {%- else %}
50
+ {{- '<|im_start|>' + message.role + '\n' + content }}
51
+ {%- endif %}
52
+ {%- if message.tool_calls %}
53
+ {%- for tool_call in message.tool_calls %}
54
+ {%- if (loop.first and content) or (not loop.first) %}
55
+ {{- '\n' }}
56
+ {%- endif %}
57
+ {%- if tool_call.function %}
58
+ {%- set tool_call = tool_call.function %}
59
+ {%- endif %}
60
+ {{- '<tool_call>\n{"name": "' }}
61
+ {{- tool_call.name }}
62
+ {{- '", "arguments": ' }}
63
+ {%- if tool_call.arguments is string %}
64
+ {{- tool_call.arguments }}
65
+ {%- else %}
66
+ {{- tool_call.arguments | tojson }}
67
+ {%- endif %}
68
+ {{- '}\n</tool_call>' }}
69
+ {%- endfor %}
70
+ {%- endif %}
71
+ {{- '<|im_end|>\n' }}
72
+ {%- elif message.role == "tool" %}
73
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
74
+ {{- '<|im_start|>user' }}
75
+ {%- endif %}
76
+ {{- '\n<tool_response>\n' }}
77
+ {{- content }}
78
+ {{- '\n</tool_response>' }}
79
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
80
+ {{- '<|im_end|>\n' }}
81
+ {%- endif %}
82
+ {%- endif %}
83
+ {%- endfor %}
84
+ {%- if add_generation_prompt %}
85
+ {{- '<|im_start|>assistant\n<think>\n' }}
86
+ {%- endif %}
config.json ADDED
@@ -0,0 +1,344 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3NextForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "decoder_sparse_step": 1,
9
+ "dtype": "bfloat16",
10
+ "eos_token_id": 151645,
11
+ "full_attention_interval": 4,
12
+ "head_dim": 256,
13
+ "hidden_act": "silu",
14
+ "hidden_size": 2048,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 5120,
17
+ "layer_types": [
18
+ "linear_attention",
19
+ "linear_attention",
20
+ "linear_attention",
21
+ "full_attention",
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
+ "linear_attention",
63
+ "linear_attention",
64
+ "linear_attention",
65
+ "full_attention"
66
+ ],
67
+ "linear_conv_kernel_dim": 4,
68
+ "linear_key_head_dim": 128,
69
+ "linear_num_key_heads": 16,
70
+ "linear_num_value_heads": 32,
71
+ "linear_value_head_dim": 128,
72
+ "max_position_embeddings": 262144,
73
+ "mlp_only_layers": [],
74
+ "model_type": "qwen3_next",
75
+ "moe_intermediate_size": 512,
76
+ "norm_topk_prob": true,
77
+ "num_attention_heads": 16,
78
+ "num_experts": 512,
79
+ "num_experts_per_tok": 10,
80
+ "num_hidden_layers": 48,
81
+ "num_key_value_heads": 2,
82
+ "output_router_logits": false,
83
+ "partial_rotary_factor": 0.25,
84
+ "quantization_config": {
85
+ "config_groups": {
86
+ "group_0": {
87
+ "format": "nvfp4-pack-quantized",
88
+ "input_activations": {
89
+ "actorder": null,
90
+ "block_structure": null,
91
+ "dynamic": "local",
92
+ "group_size": 16,
93
+ "num_bits": 4,
94
+ "observer": "minmax",
95
+ "observer_kwargs": {},
96
+ "strategy": "tensor_group",
97
+ "symmetric": true,
98
+ "type": "float"
99
+ },
100
+ "output_activations": null,
101
+ "targets": [
102
+ "Linear"
103
+ ],
104
+ "weights": {
105
+ "actorder": null,
106
+ "block_structure": null,
107
+ "dynamic": false,
108
+ "group_size": 16,
109
+ "num_bits": 4,
110
+ "observer": "minmax",
111
+ "observer_kwargs": {},
112
+ "strategy": "tensor_group",
113
+ "symmetric": true,
114
+ "type": "float"
115
+ }
116
+ }
117
+ },
118
+ "format": "nvfp4-pack-quantized",
119
+ "global_compression_ratio": null,
120
+ "ignore": [
121
+ "model.layers.0.linear_attn.in_proj_qkvz",
122
+ "model.layers.0.linear_attn.in_proj_ba",
123
+ "model.layers.0.linear_attn.out_proj",
124
+ "model.layers.0.mlp.gate",
125
+ "model.layers.0.mlp.shared_expert_gate",
126
+ "model.layers.1.linear_attn.in_proj_qkvz",
127
+ "model.layers.1.linear_attn.in_proj_ba",
128
+ "model.layers.1.linear_attn.out_proj",
129
+ "model.layers.1.mlp.gate",
130
+ "model.layers.1.mlp.shared_expert_gate",
131
+ "model.layers.2.linear_attn.in_proj_qkvz",
132
+ "model.layers.2.linear_attn.in_proj_ba",
133
+ "model.layers.2.linear_attn.out_proj",
134
+ "model.layers.2.mlp.gate",
135
+ "model.layers.2.mlp.shared_expert_gate",
136
+ "model.layers.3.mlp.gate",
137
+ "model.layers.3.mlp.shared_expert_gate",
138
+ "model.layers.4.linear_attn.in_proj_qkvz",
139
+ "model.layers.4.linear_attn.in_proj_ba",
140
+ "model.layers.4.linear_attn.out_proj",
141
+ "model.layers.4.mlp.gate",
142
+ "model.layers.4.mlp.shared_expert_gate",
143
+ "model.layers.5.linear_attn.in_proj_qkvz",
144
+ "model.layers.5.linear_attn.in_proj_ba",
145
+ "model.layers.5.linear_attn.out_proj",
146
+ "model.layers.5.mlp.gate",
147
+ "model.layers.5.mlp.shared_expert_gate",
148
+ "model.layers.6.linear_attn.in_proj_qkvz",
149
+ "model.layers.6.linear_attn.in_proj_ba",
150
+ "model.layers.6.linear_attn.out_proj",
151
+ "model.layers.6.mlp.gate",
152
+ "model.layers.6.mlp.shared_expert_gate",
153
+ "model.layers.7.mlp.gate",
154
+ "model.layers.7.mlp.shared_expert_gate",
155
+ "model.layers.8.linear_attn.in_proj_qkvz",
156
+ "model.layers.8.linear_attn.in_proj_ba",
157
+ "model.layers.8.linear_attn.out_proj",
158
+ "model.layers.8.mlp.gate",
159
+ "model.layers.8.mlp.shared_expert_gate",
160
+ "model.layers.9.linear_attn.in_proj_qkvz",
161
+ "model.layers.9.linear_attn.in_proj_ba",
162
+ "model.layers.9.linear_attn.out_proj",
163
+ "model.layers.9.mlp.gate",
164
+ "model.layers.9.mlp.shared_expert_gate",
165
+ "model.layers.10.linear_attn.in_proj_qkvz",
166
+ "model.layers.10.linear_attn.in_proj_ba",
167
+ "model.layers.10.linear_attn.out_proj",
168
+ "model.layers.10.mlp.gate",
169
+ "model.layers.10.mlp.shared_expert_gate",
170
+ "model.layers.11.mlp.gate",
171
+ "model.layers.11.mlp.shared_expert_gate",
172
+ "model.layers.12.linear_attn.in_proj_qkvz",
173
+ "model.layers.12.linear_attn.in_proj_ba",
174
+ "model.layers.12.linear_attn.out_proj",
175
+ "model.layers.12.mlp.gate",
176
+ "model.layers.12.mlp.shared_expert_gate",
177
+ "model.layers.13.linear_attn.in_proj_qkvz",
178
+ "model.layers.13.linear_attn.in_proj_ba",
179
+ "model.layers.13.linear_attn.out_proj",
180
+ "model.layers.13.mlp.gate",
181
+ "model.layers.13.mlp.shared_expert_gate",
182
+ "model.layers.14.linear_attn.in_proj_qkvz",
183
+ "model.layers.14.linear_attn.in_proj_ba",
184
+ "model.layers.14.linear_attn.out_proj",
185
+ "model.layers.14.mlp.gate",
186
+ "model.layers.14.mlp.shared_expert_gate",
187
+ "model.layers.15.mlp.gate",
188
+ "model.layers.15.mlp.shared_expert_gate",
189
+ "model.layers.16.linear_attn.in_proj_qkvz",
190
+ "model.layers.16.linear_attn.in_proj_ba",
191
+ "model.layers.16.linear_attn.out_proj",
192
+ "model.layers.16.mlp.gate",
193
+ "model.layers.16.mlp.shared_expert_gate",
194
+ "model.layers.17.linear_attn.in_proj_qkvz",
195
+ "model.layers.17.linear_attn.in_proj_ba",
196
+ "model.layers.17.linear_attn.out_proj",
197
+ "model.layers.17.mlp.gate",
198
+ "model.layers.17.mlp.shared_expert_gate",
199
+ "model.layers.18.linear_attn.in_proj_qkvz",
200
+ "model.layers.18.linear_attn.in_proj_ba",
201
+ "model.layers.18.linear_attn.out_proj",
202
+ "model.layers.18.mlp.gate",
203
+ "model.layers.18.mlp.shared_expert_gate",
204
+ "model.layers.19.mlp.gate",
205
+ "model.layers.19.mlp.shared_expert_gate",
206
+ "model.layers.20.linear_attn.in_proj_qkvz",
207
+ "model.layers.20.linear_attn.in_proj_ba",
208
+ "model.layers.20.linear_attn.out_proj",
209
+ "model.layers.20.mlp.gate",
210
+ "model.layers.20.mlp.shared_expert_gate",
211
+ "model.layers.21.linear_attn.in_proj_qkvz",
212
+ "model.layers.21.linear_attn.in_proj_ba",
213
+ "model.layers.21.linear_attn.out_proj",
214
+ "model.layers.21.mlp.gate",
215
+ "model.layers.21.mlp.shared_expert_gate",
216
+ "model.layers.22.linear_attn.in_proj_qkvz",
217
+ "model.layers.22.linear_attn.in_proj_ba",
218
+ "model.layers.22.linear_attn.out_proj",
219
+ "model.layers.22.mlp.gate",
220
+ "model.layers.22.mlp.shared_expert_gate",
221
+ "model.layers.23.mlp.gate",
222
+ "model.layers.23.mlp.shared_expert_gate",
223
+ "model.layers.24.linear_attn.in_proj_qkvz",
224
+ "model.layers.24.linear_attn.in_proj_ba",
225
+ "model.layers.24.linear_attn.out_proj",
226
+ "model.layers.24.mlp.gate",
227
+ "model.layers.24.mlp.shared_expert_gate",
228
+ "model.layers.25.linear_attn.in_proj_qkvz",
229
+ "model.layers.25.linear_attn.in_proj_ba",
230
+ "model.layers.25.linear_attn.out_proj",
231
+ "model.layers.25.mlp.gate",
232
+ "model.layers.25.mlp.shared_expert_gate",
233
+ "model.layers.26.linear_attn.in_proj_qkvz",
234
+ "model.layers.26.linear_attn.in_proj_ba",
235
+ "model.layers.26.linear_attn.out_proj",
236
+ "model.layers.26.mlp.gate",
237
+ "model.layers.26.mlp.shared_expert_gate",
238
+ "model.layers.27.mlp.gate",
239
+ "model.layers.27.mlp.shared_expert_gate",
240
+ "model.layers.28.linear_attn.in_proj_qkvz",
241
+ "model.layers.28.linear_attn.in_proj_ba",
242
+ "model.layers.28.linear_attn.out_proj",
243
+ "model.layers.28.mlp.gate",
244
+ "model.layers.28.mlp.shared_expert_gate",
245
+ "model.layers.29.linear_attn.in_proj_qkvz",
246
+ "model.layers.29.linear_attn.in_proj_ba",
247
+ "model.layers.29.linear_attn.out_proj",
248
+ "model.layers.29.mlp.gate",
249
+ "model.layers.29.mlp.shared_expert_gate",
250
+ "model.layers.30.linear_attn.in_proj_qkvz",
251
+ "model.layers.30.linear_attn.in_proj_ba",
252
+ "model.layers.30.linear_attn.out_proj",
253
+ "model.layers.30.mlp.gate",
254
+ "model.layers.30.mlp.shared_expert_gate",
255
+ "model.layers.31.mlp.gate",
256
+ "model.layers.31.mlp.shared_expert_gate",
257
+ "model.layers.32.linear_attn.in_proj_qkvz",
258
+ "model.layers.32.linear_attn.in_proj_ba",
259
+ "model.layers.32.linear_attn.out_proj",
260
+ "model.layers.32.mlp.gate",
261
+ "model.layers.32.mlp.shared_expert_gate",
262
+ "model.layers.33.linear_attn.in_proj_qkvz",
263
+ "model.layers.33.linear_attn.in_proj_ba",
264
+ "model.layers.33.linear_attn.out_proj",
265
+ "model.layers.33.mlp.gate",
266
+ "model.layers.33.mlp.shared_expert_gate",
267
+ "model.layers.34.linear_attn.in_proj_qkvz",
268
+ "model.layers.34.linear_attn.in_proj_ba",
269
+ "model.layers.34.linear_attn.out_proj",
270
+ "model.layers.34.mlp.gate",
271
+ "model.layers.34.mlp.shared_expert_gate",
272
+ "model.layers.35.mlp.gate",
273
+ "model.layers.35.mlp.shared_expert_gate",
274
+ "model.layers.36.linear_attn.in_proj_qkvz",
275
+ "model.layers.36.linear_attn.in_proj_ba",
276
+ "model.layers.36.linear_attn.out_proj",
277
+ "model.layers.36.mlp.gate",
278
+ "model.layers.36.mlp.shared_expert_gate",
279
+ "model.layers.37.linear_attn.in_proj_qkvz",
280
+ "model.layers.37.linear_attn.in_proj_ba",
281
+ "model.layers.37.linear_attn.out_proj",
282
+ "model.layers.37.mlp.gate",
283
+ "model.layers.37.mlp.shared_expert_gate",
284
+ "model.layers.38.linear_attn.in_proj_qkvz",
285
+ "model.layers.38.linear_attn.in_proj_ba",
286
+ "model.layers.38.linear_attn.out_proj",
287
+ "model.layers.38.mlp.gate",
288
+ "model.layers.38.mlp.shared_expert_gate",
289
+ "model.layers.39.mlp.gate",
290
+ "model.layers.39.mlp.shared_expert_gate",
291
+ "model.layers.40.linear_attn.in_proj_qkvz",
292
+ "model.layers.40.linear_attn.in_proj_ba",
293
+ "model.layers.40.linear_attn.out_proj",
294
+ "model.layers.40.mlp.gate",
295
+ "model.layers.40.mlp.shared_expert_gate",
296
+ "model.layers.41.linear_attn.in_proj_qkvz",
297
+ "model.layers.41.linear_attn.in_proj_ba",
298
+ "model.layers.41.linear_attn.out_proj",
299
+ "model.layers.41.mlp.gate",
300
+ "model.layers.41.mlp.shared_expert_gate",
301
+ "model.layers.42.linear_attn.in_proj_qkvz",
302
+ "model.layers.42.linear_attn.in_proj_ba",
303
+ "model.layers.42.linear_attn.out_proj",
304
+ "model.layers.42.mlp.gate",
305
+ "model.layers.42.mlp.shared_expert_gate",
306
+ "model.layers.43.mlp.gate",
307
+ "model.layers.43.mlp.shared_expert_gate",
308
+ "model.layers.44.linear_attn.in_proj_qkvz",
309
+ "model.layers.44.linear_attn.in_proj_ba",
310
+ "model.layers.44.linear_attn.out_proj",
311
+ "model.layers.44.mlp.gate",
312
+ "model.layers.44.mlp.shared_expert_gate",
313
+ "model.layers.45.linear_attn.in_proj_qkvz",
314
+ "model.layers.45.linear_attn.in_proj_ba",
315
+ "model.layers.45.linear_attn.out_proj",
316
+ "model.layers.45.mlp.gate",
317
+ "model.layers.45.mlp.shared_expert_gate",
318
+ "model.layers.46.linear_attn.in_proj_qkvz",
319
+ "model.layers.46.linear_attn.in_proj_ba",
320
+ "model.layers.46.linear_attn.out_proj",
321
+ "model.layers.46.mlp.gate",
322
+ "model.layers.46.mlp.shared_expert_gate",
323
+ "model.layers.47.mlp.gate",
324
+ "model.layers.47.mlp.shared_expert_gate",
325
+ "lm_head"
326
+ ],
327
+ "kv_cache_scheme": null,
328
+ "quant_method": "compressed-tensors",
329
+ "quantization_status": "compressed",
330
+ "sparsity_config": {},
331
+ "transform_config": {},
332
+ "version": "0.12.3.a20251007"
333
+ },
334
+ "rms_norm_eps": 1e-06,
335
+ "rope_scaling": null,
336
+ "rope_theta": 10000000,
337
+ "router_aux_loss_coef": 0.001,
338
+ "shared_expert_intermediate_size": 512,
339
+ "tie_word_embeddings": false,
340
+ "transformers_version": "4.57.0",
341
+ "use_cache": true,
342
+ "use_sliding_window": false,
343
+ "vocab_size": 151936
344
+ }
generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "temperature": 0.6,
10
+ "top_k": 20,
11
+ "top_p": 0.95,
12
+ "transformers_version": "4.57.0"
13
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f7a0d2e271d2449610604cd87d4b53c41ded20b7b857d8aa2681701506773b7
3
+ size 5003034072
model-00002-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5764f2334e88afb1374d6720c48ef8832de45483541206e802278f9d6712a467
3
+ size 5003502512
model-00003-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:808e9af284594705c1fc63279517e2c05410a3805131f13fd8aa0323a4563261
3
+ size 5003532512
model-00004-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d02d42955408c34c7968373b6a271fbfd46f8480e27d68cb1f5419257a6fce3f
3
+ size 5003863032
model-00005-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af002a9cef21e59e16a31149fcd5f4834af5b9daadb27860670b1f70a914e945
3
+ size 5003533424
model-00006-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:548dbd695162885ac48bfa66c0f438c866ab7808971c66ecde664bbef7179882
3
+ size 5003534464
model-00007-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c2952f778e64e4613b72ed9ee3fb9b286c34ad2e4d85a818f3c617f2e8a7343
3
+ size 5003974752
model-00008-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5324e8f26a478fe567ac82606d828a0b2debb99014e60e5335f0d24589a38bdb
3
+ size 5003534480
model-00009-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9881fb8d22829b274e0715f77b4e4d643e3ece91002e9a8fa0b6c5f28e554c03
3
+ size 5003534480
model-00010-of-00010.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:633213ce6a01f7c2ddad3978f09dce472f8025ffdf2269cbfa024bca23d22126
3
+ size 2534645064
model.safetensors.index.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07bc97be27a1c846de10d65f74ae32170e909d7f81269311addcf9bc8faa0961
3
+ size 29728645
recipe.yaml ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ default_stage:
2
+ default_modifiers:
3
+ QuantizationModifier:
4
+ targets: [Linear]
5
+ ignore: [lm_head, 're:.*mlp.gate$', 're:.*mlp.shared_expert_gate$', 're:.*linear_attn.*']
6
+ scheme: NVFP4
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
3
+ size 11422654
tokenizer_config.json ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "model_max_length": 1010000,
235
+ "pad_token": "<|endoftext|>",
236
+ "split_special_tokens": false,
237
+ "tokenizer_class": "Qwen2Tokenizer",
238
+ "unk_token": null
239
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff