Hugging Face's logo

lukealonso
/
MiMo-V2.5-NVFP4

Safetensors
mimo_v2
8-bit precision
modelopt
Model card Files
xet
 Community
5
lukealonso commited on
Commit
93ebc84
·
verified ·
1 Parent(s): b85a7bd

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 +1 -0
  2. amax_checkpoint.safetensors +3 -0
  3. audio_tokenizer/chat_template.jinja +120 -0
  4. audio_tokenizer/config.json +68 -0
  5. audio_tokenizer/generation_config.json +9 -0
  6. audio_tokenizer/model.safetensors +3 -0
  7. audio_tokenizer/tokenizer_config.json +267 -0
  8. config.json +598 -0
  9. generation_config.json +9 -0
  10. hf_quant_config.json +227 -0
  11. merges.txt +0 -0
  12. model-00001-of-00035.safetensors +3 -0
  13. model-00002-of-00035.safetensors +3 -0
  14. model-00003-of-00035.safetensors +3 -0
  15. model-00004-of-00035.safetensors +3 -0
  16. model-00005-of-00035.safetensors +3 -0
  17. model-00006-of-00035.safetensors +3 -0
  18. model-00007-of-00035.safetensors +3 -0
  19. model-00008-of-00035.safetensors +3 -0
  20. model-00009-of-00035.safetensors +3 -0
  21. model-00010-of-00035.safetensors +3 -0
  22. model-00011-of-00035.safetensors +3 -0
  23. model-00012-of-00035.safetensors +3 -0
  24. model-00013-of-00035.safetensors +3 -0
  25. model-00015-of-00035.safetensors +3 -0
  26. model-00016-of-00035.safetensors +3 -0
  27. model-00017-of-00035.safetensors +3 -0
  28. model-00018-of-00035.safetensors +3 -0
  29. model-00019-of-00035.safetensors +3 -0
  30. model-00021-of-00035.safetensors +3 -0
  31. model-00022-of-00035.safetensors +3 -0
  32. model-00023-of-00035.safetensors +3 -0
  33. model-00024-of-00035.safetensors +3 -0
  34. model-00025-of-00035.safetensors +3 -0
  35. model-00026-of-00035.safetensors +3 -0
  36. model-00027-of-00035.safetensors +3 -0
  37. model-00028-of-00035.safetensors +3 -0
  38. model-00029-of-00035.safetensors +3 -0
  39. model-00030-of-00035.safetensors +3 -0
  40. model-00031-of-00035.safetensors +3 -0
  41. model-00032-of-00035.safetensors +3 -0
  42. model-00033-of-00035.safetensors +3 -0
  43. model-00034-of-00035.safetensors +3 -0
  44. model-00035-of-00035.safetensors +3 -0
  45. model-inputscales.safetensors +3 -0
  46. model-mtp.safetensors +3 -0
  47. model.safetensors.index.json +3 -0
  48. preprocessor_config.json +19 -0
  49. tokenizer.json +0 -0
  50. tokenizer_config.json +293 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text
amax_checkpoint.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8242c5179df4c3ece758b0f86d26078693bb10baeec88ca79c5ea2a0e375148c
3
+ size 8619248
audio_tokenizer/chat_template.jinja ADDED
@@ -0,0 +1,120 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- if tools %}
2
+ {{- '<|im_start|>system\n' }}
3
+ {%- if messages[0].role == 'system' %}
4
+ {%- if messages[0].content is string %}
5
+ {{- messages[0].content }}
6
+ {%- else %}
7
+ {%- for content in messages[0].content %}
8
+ {%- if content.type == 'audio' %}
9
+ {{- ("<|sosp|>" + (content.meta | tojson) + "<|eosp|>") }}
10
+ {%- elif content.type == 'text' %}
11
+ {{- content.text }}
12
+ {%- endif %}
13
+ {%- endfor %}
14
+ {%- endif %}
15
+ {%- endif %}
16
+ {{- '\n\n' }}
17
+ {{- "# 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>" }}
18
+ {%- for tool in tools %}
19
+ {{- "\n" }}
20
+ {{- tool | tojson }}
21
+ {%- endfor %}
22
+ {{- "\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" }}
23
+ {%- else %}
24
+ {%- if messages[0].role == 'system' %}
25
+ {{- '<|im_start|>system\n' }}
26
+ {%- if messages[0].content is string %}
27
+ {{- messages[0].content }}
28
+ {%- else %}
29
+ {%- for content in messages[0].content %}
30
+ {%- if content.type == 'audio' %}
31
+ {{- ("<|sosp|>" + (content.meta | tojson) + "<|eosp|>") }}
32
+ {%- elif content.type == 'text' %}
33
+ {{- content.text }}
34
+ {%- endif %}
35
+ {%- endfor %}
36
+ {%- endif %}
37
+ {{- '\n<|im_end|>\n' }}
38
+ {%- endif %}
39
+ {%- endif %}
40
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1, assistant_is_last=false) %}
41
+ {%- for message in messages[::-1] %}
42
+ {%- set index = (messages|length - 1) - loop.index0 %}
43
+ {%- 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>')) %}
44
+ {%- set ns.multi_step_tool = false %}
45
+ {%- set ns.last_query_index = index %}
46
+ {%- endif %}
47
+ {%- endfor %}
48
+ {%- for message in messages %}
49
+ {%- if message.content is string %}
50
+ {%- set content = message.content %}
51
+ {%- else %}
52
+ {%- set content = namespace(text="") %}
53
+ {%- for mcontent in message.content %}
54
+ {%- if mcontent.type == 'audio' %}
55
+ {%- set content.text = content.text~("<|sosp|>" + (mcontent.meta | tojson) + "<|eosp|>") %}
56
+ {%- elif mcontent.type == 'text' %}
57
+ {%- set content.text = content.text~mcontent.text %}
58
+ {%- endif %}
59
+ {%- endfor %}
60
+ {%- set content = content.text %}
61
+ {%- endif %}
62
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
63
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
64
+ {%- elif message.role == "assistant" %}
65
+ {%- set reasoning_content = "" %}
66
+ {%- if message.reasoning_content is string %}
67
+ {%- set reasoning_content = message.reasoning_content %}
68
+ {%- else %}
69
+ {%- if '</think>' in content %}
70
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
71
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
72
+ {%- endif %}
73
+ {%- endif %}
74
+ {%- if loop.index0 > ns.last_query_index %}
75
+ {%- if loop.last or (not loop.last and reasoning_content) %}
76
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip("\n") + '\n</think>\n\n' + content.lstrip('\n') }}
77
+ {%- else %}
78
+ {{- '<|im_start|>' + message.role + '\n' + content }}
79
+ {%- endif %}
80
+ {%- else %}
81
+ {{- '<|im_start|>' + message.role + '\n' + content }}
82
+ {%- endif %}
83
+ {%- if message.tool_calls %}
84
+ {%- for tool_call in message.tool_calls %}
85
+ {%- if (loop.first and content) or (not loop.first) %}{{- '\n' }}{%- endif %}
86
+ {%- if tool_call.function %}
87
+ {%- set tool_call = tool_call.function %}
88
+ {%- endif %}
89
+ {{- '<tool_call>\n{"name": "' }}
90
+ {{- tool_call.name }}
91
+ {{- '", "arguments": ' }}
92
+ {%- if tool_call.arguments is string %}
93
+ {{- tool_call.arguments }}
94
+ {%- else %}
95
+ {{- tool_call.arguments | tojson }}
96
+ {%- endif %}
97
+ {{- '}\n</tool_call>' }}
98
+ {%- endfor %}
99
+ {%- endif %}
100
+ {%- if loop.last %}
101
+ {%- set ns.assistant_is_last = true %}
102
+ {%- else %}
103
+ {{- '<|im_end|>\n' }}
104
+ {%- endif %}
105
+ {%- elif message.role == "tool" %}
106
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}{{- '<|im_start|>user' }}{%- endif %}
107
+ {{- '\n<tool_response>\n' }}
108
+ {{- content }}
109
+ {{- '\n</tool_response>' }}
110
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}{{- '<|im_end|>\n' }}{%- endif %}
111
+ {%- endif %}
112
+ {%- endfor %}
113
+ {%- if add_generation_prompt and not ns.assistant_is_last %}
114
+ {{- '<|im_start|>assistant\n' }}
115
+ {%- if audio_output %}
116
+ {{- '<|sostm|>'}}
117
+ {%- elif not enable_thinking %}
118
+ {{- '<think>\n\n</think>\n' }}
119
+ {%- endif %}
120
+ {%- endif %}
audio_tokenizer/config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "max_audio_seconds": 300,
3
+ "stride_size": 2,
4
+ "avg_pooler": 2,
5
+ "d_model": 1024,
6
+ "scale_embedding": false,
7
+ "kernel_size": 3,
8
+ "activation_function": "gelu",
9
+ "encoder_layers": 24,
10
+ "encoder_skip_layer_id": 3,
11
+ "encoder_attention_heads": 16,
12
+ "encoder_ffn_dim": 4096,
13
+ "encoder_causal": true,
14
+ "encoder_attn_window_size": [
15
+ 128,
16
+ 0
17
+ ],
18
+ "decoder_layers": 24,
19
+ "decoder_attention_heads": 16,
20
+ "decoder_ffn_dim": 4096,
21
+ "decoder_kernel_size": 3,
22
+ "decoder_stride_size": 2,
23
+ "decoder_causal": true,
24
+ "decoder_attn_window_size": [
25
+ 128,
26
+ 0
27
+ ],
28
+ "nfft": 960,
29
+ "n_mels": 128,
30
+ "sampling_rate": 24000,
31
+ "hop_length": 240,
32
+ "window_size": 960,
33
+ "vocoder_padding": "same",
34
+ "fmin": 0,
35
+ "fmax": null,
36
+ "num_quantizers": 20,
37
+ "codebook_size": [
38
+ 1024,
39
+ 1024,
40
+ 256,
41
+ 128,
42
+ 128,
43
+ 128,
44
+ 128,
45
+ 128,
46
+ 128,
47
+ 128,
48
+ 128,
49
+ 128,
50
+ 128,
51
+ 128,
52
+ 128,
53
+ 128,
54
+ 128,
55
+ 128,
56
+ 128,
57
+ 128
58
+ ],
59
+ "threshold_ema_dead_code": 2,
60
+ "position_embedding_type": "rope",
61
+ "rope_theta": 10000,
62
+ "rope_type": "default",
63
+ "ln_type": "LayerNorm",
64
+ "use_istft_only": true,
65
+ "hybrid_attention": true,
66
+ "hybrid_block_size": 8,
67
+ "swa_per_block": 2
68
+ }
audio_tokenizer/generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_sample": true,
3
+ "temperature": 0.6,
4
+ "top_k": -1,
5
+ "top_p": 0.95,
6
+ "audio_temperature": 0.9,
7
+ "audio_top_k": -1,
8
+ "audio_top_p": 0.95
9
+ }
audio_tokenizer/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95cca046bda0a67ea52cc77af734ed175282820efbc508099dd8a012eb968cea
3
+ size 652622472
audio_tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,267 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|mimo_audio_start|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "151666": {
190
+ "content": "<|mimo_audio_end|>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": true
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
+ "151669": {
214
+ "content": "<|audio_pad|>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "151670": {
222
+ "content": "<|mimo_video_start|>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "151671": {
230
+ "content": "<|mimo_video_end|>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": true
236
+ }
237
+ },
238
+ "additional_special_tokens": [
239
+ "<|im_start|>",
240
+ "<|im_end|>",
241
+ "<|object_ref_start|>",
242
+ "<|object_ref_end|>",
243
+ "<|box_start|>",
244
+ "<|box_end|>",
245
+ "<|quad_start|>",
246
+ "<|quad_end|>",
247
+ "<|vision_start|>",
248
+ "<|vision_end|>",
249
+ "<|vision_pad|>",
250
+ "<|image_pad|>",
251
+ "<|video_pad|>",
252
+ "<|audio_pad|>",
253
+ "<|mimo_audio_start|>",
254
+ "<|mimo_audio_end|>",
255
+ "<|mimo_video_start|>",
256
+ "<|mimo_video_end|>"
257
+ ],
258
+ "bos_token": null,
259
+ "clean_up_tokenization_spaces": false,
260
+ "eos_token": "<|im_end|>",
261
+ "errors": "replace",
262
+ "model_max_length": 131072,
263
+ "pad_token": "<|endoftext|>",
264
+ "split_special_tokens": false,
265
+ "tokenizer_class": "Qwen2Tokenizer",
266
+ "unk_token": null
267
+ }
config.json ADDED
@@ -0,0 +1,598 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "attention_projection_layout": "fused_qkv",
3
+ "vocab_size": 152576,
4
+ "max_position_embeddings": 1048576,
5
+ "hidden_size": 4096,
6
+ "intermediate_size": 16384,
7
+ "num_hidden_layers": 48,
8
+ "num_attention_heads": 64,
9
+ "num_key_value_heads": 4,
10
+ "hidden_act": "silu",
11
+ "initializer_range": 0.02,
12
+ "layernorm_epsilon": 1e-05,
13
+ "use_cache": true,
14
+ "rope_theta": 10000000,
15
+ "rope_parameters": {
16
+ "rope_type": "default",
17
+ "type": "default",
18
+ "rope_theta": 10000000,
19
+ "partial_rotary_factor": 0.334
20
+ },
21
+ "attention_dropout": 0.0,
22
+ "attention_bias": false,
23
+ "attention_value_scale": 0.707,
24
+ "head_dim": 192,
25
+ "v_head_dim": 128,
26
+ "swa_num_attention_heads": 64,
27
+ "swa_num_key_value_heads": 8,
28
+ "swa_head_dim": 192,
29
+ "swa_v_head_dim": 128,
30
+ "swa_rope_theta": 10000,
31
+ "sliding_window": 128,
32
+ "sliding_window_size": 128,
33
+ "add_full_attention_sink_bias": false,
34
+ "add_swa_attention_sink_bias": true,
35
+ "hybrid_block_size": null,
36
+ "hybrid_layer_pattern": [
37
+ 0,
38
+ 1,
39
+ 1,
40
+ 1,
41
+ 1,
42
+ 0,
43
+ 1,
44
+ 1,
45
+ 1,
46
+ 1,
47
+ 1,
48
+ 0,
49
+ 1,
50
+ 1,
51
+ 1,
52
+ 1,
53
+ 1,
54
+ 0,
55
+ 1,
56
+ 1,
57
+ 1,
58
+ 1,
59
+ 1,
60
+ 0,
61
+ 1,
62
+ 1,
63
+ 1,
64
+ 1,
65
+ 1,
66
+ 0,
67
+ 1,
68
+ 1,
69
+ 1,
70
+ 1,
71
+ 1,
72
+ 0,
73
+ 1,
74
+ 1,
75
+ 1,
76
+ 1,
77
+ 1,
78
+ 0,
79
+ 1,
80
+ 1,
81
+ 1,
82
+ 1,
83
+ 1,
84
+ 0
85
+ ],
86
+ "partial_rotary_factor": 0.334,
87
+ "n_routed_experts": 256,
88
+ "moe_intermediate_size": 2048,
89
+ "num_experts_per_tok": 8,
90
+ "routed_scaling_factor": null,
91
+ "scoring_func": "sigmoid",
92
+ "topk_method": "noaux_tc",
93
+ "n_group": 1,
94
+ "topk_group": 1,
95
+ "norm_topk_prob": true,
96
+ "moe_layer_freq": [
97
+ 0,
98
+ 1,
99
+ 1,
100
+ 1,
101
+ 1,
102
+ 1,
103
+ 1,
104
+ 1,
105
+ 1,
106
+ 1,
107
+ 1,
108
+ 1,
109
+ 1,
110
+ 1,
111
+ 1,
112
+ 1,
113
+ 1,
114
+ 1,
115
+ 1,
116
+ 1,
117
+ 1,
118
+ 1,
119
+ 1,
120
+ 1,
121
+ 1,
122
+ 1,
123
+ 1,
124
+ 1,
125
+ 1,
126
+ 1,
127
+ 1,
128
+ 1,
129
+ 1,
130
+ 1,
131
+ 1,
132
+ 1,
133
+ 1,
134
+ 1,
135
+ 1,
136
+ 1,
137
+ 1,
138
+ 1,
139
+ 1,
140
+ 1,
141
+ 1,
142
+ 1,
143
+ 1,
144
+ 1
145
+ ],
146
+ "vision_config": {
147
+ "depth": 28,
148
+ "fullatt_block_indexes": [
149
+ 0,
150
+ 9,
151
+ 18,
152
+ 27
153
+ ],
154
+ "hidden_act": "silu",
155
+ "hidden_size": 1280,
156
+ "in_chans": 3,
157
+ "intermediate_size": 4608,
158
+ "num_heads": 32,
159
+ "num_key_value_heads": 8,
160
+ "num_query_groups": 4,
161
+ "out_hidden_size": 4096,
162
+ "patch_size": 16,
163
+ "spatial_merge_size": 2,
164
+ "spatial_patch_size": 16,
165
+ "temporal_patch_size": 2,
166
+ "tokens_per_second": 2,
167
+ "use_sink": true,
168
+ "visual_token_window_size": 64,
169
+ "vit_window_attn_types": [
170
+ -1,
171
+ 0,
172
+ 0,
173
+ 0,
174
+ 0,
175
+ 1,
176
+ 1,
177
+ 1,
178
+ 1,
179
+ -1,
180
+ 0,
181
+ 0,
182
+ 0,
183
+ 0,
184
+ 1,
185
+ 1,
186
+ 1,
187
+ 1,
188
+ -1,
189
+ 0,
190
+ 0,
191
+ 0,
192
+ 0,
193
+ 1,
194
+ 1,
195
+ 1,
196
+ 1,
197
+ -1
198
+ ],
199
+ "window_size": 128
200
+ },
201
+ "audio_config": {
202
+ "add_post_norm": true,
203
+ "audio_channels": 20,
204
+ "audio_segment_size": 6000,
205
+ "group_size": 4,
206
+ "input_full_attention": true,
207
+ "input_local_attn_heads": 16,
208
+ "input_local_dim": 1024,
209
+ "input_local_head_dim": 64,
210
+ "input_local_hidden_dropout": 0.0,
211
+ "input_local_intermediate_size": 4096,
212
+ "input_local_layers": 6,
213
+ "out_hidden_size": 4096,
214
+ "partial_rotary_factor": 1.0,
215
+ "projection_layers": 2,
216
+ "rope_theta": 640000,
217
+ "speech_vocab_size": "1280",
218
+ "speech_zeroemb_idx": "1024"
219
+ },
220
+ "processor_config": {
221
+ "audio_avg_pooler": 2,
222
+ "audio_channels": 20,
223
+ "audio_end_token_id": 151674,
224
+ "audio_fmax": null,
225
+ "audio_fmin": 0,
226
+ "audio_group_size": 4,
227
+ "audio_hop_length": 240,
228
+ "audio_input_id_per_second": 25.0,
229
+ "audio_kernel_size": 3,
230
+ "audio_n_mels": 128,
231
+ "audio_nfft": 960,
232
+ "audio_sampling_rate": 24000,
233
+ "audio_segment_size": 6000,
234
+ "audio_start_token_id": 151673,
235
+ "audio_stride_size": 2,
236
+ "audio_token_id": 151669,
237
+ "audio_window_size": 960,
238
+ "audio_zeroemb_idx": [
239
+ 1024,
240
+ 1024,
241
+ 1024,
242
+ 1024,
243
+ 1024,
244
+ 1024,
245
+ 1024,
246
+ 1024,
247
+ 1024,
248
+ 1024,
249
+ 1024,
250
+ 1024,
251
+ 1024,
252
+ 1024,
253
+ 1024,
254
+ 1024,
255
+ 1024,
256
+ 1024,
257
+ 1024,
258
+ 1024
259
+ ],
260
+ "fps": 1.0,
261
+ "image_max_pixels": 8388608,
262
+ "image_min_pixels": 8192,
263
+ "image_token_id": 151655,
264
+ "max_frames": 3600,
265
+ "merge_size": 2,
266
+ "min_frames": null,
267
+ "num_frames": null,
268
+ "pad_token_id": 151643,
269
+ "patch_size": 16,
270
+ "rope_type": "rope",
271
+ "temporal_compression_ratio": 1,
272
+ "temporal_patch_size": 2,
273
+ "use_per_grid_t_timestamps": false,
274
+ "use_video_timestamps": true,
275
+ "video_audio_interleave_length": 0.0,
276
+ "video_end_token_id": 151671,
277
+ "video_max_pixels": 8388608,
278
+ "video_min_pixels": 8192,
279
+ "video_process_num_threads": 16,
280
+ "video_start_token_id": 151670,
281
+ "video_token_id": 151656,
282
+ "video_tokens_per_second": 2,
283
+ "video_total_max_pixels": 268435456,
284
+ "vision_end_token_id": 151653,
285
+ "vision_start_token_id": 151652
286
+ },
287
+ "image_token_id": 151655,
288
+ "video_token_id": 151656,
289
+ "vision_start_token_id": 151652,
290
+ "vision_end_token_id": 151653,
291
+ "vision_model_type": "mimovl",
292
+ "audio_token_id": 151669,
293
+ "audio_start_token_id": 151673,
294
+ "audio_end_token_id": 151674,
295
+ "transformers_version": "5.6.2",
296
+ "architectures": [
297
+ "MiMoV2ForCausalLM"
298
+ ],
299
+ "output_hidden_states": false,
300
+ "return_dict": true,
301
+ "dtype": "bfloat16",
302
+ "chunk_size_feed_forward": 0,
303
+ "is_encoder_decoder": false,
304
+ "id2label": {
305
+ "0": "LABEL_0",
306
+ "1": "LABEL_1"
307
+ },
308
+ "label2id": {
309
+ "LABEL_0": 0,
310
+ "LABEL_1": 1
311
+ },
312
+ "problem_type": null,
313
+ "_name_or_path": "",
314
+ "tie_word_embeddings": false,
315
+ "attention_chunk_size": 128,
316
+ "eos_token_id": 151645,
317
+ "model_type": "mimo_v2",
318
+ "n_shared_experts": null,
319
+ "pad_token_id": 151643,
320
+ "layer_types": [
321
+ "full_attention",
322
+ "sliding_attention",
323
+ "sliding_attention",
324
+ "sliding_attention",
325
+ "sliding_attention",
326
+ "full_attention",
327
+ "sliding_attention",
328
+ "sliding_attention",
329
+ "sliding_attention",
330
+ "sliding_attention",
331
+ "sliding_attention",
332
+ "full_attention",
333
+ "sliding_attention",
334
+ "sliding_attention",
335
+ "sliding_attention",
336
+ "sliding_attention",
337
+ "sliding_attention",
338
+ "full_attention",
339
+ "sliding_attention",
340
+ "sliding_attention",
341
+ "sliding_attention",
342
+ "sliding_attention",
343
+ "sliding_attention",
344
+ "full_attention",
345
+ "sliding_attention",
346
+ "sliding_attention",
347
+ "sliding_attention",
348
+ "sliding_attention",
349
+ "sliding_attention",
350
+ "full_attention",
351
+ "sliding_attention",
352
+ "sliding_attention",
353
+ "sliding_attention",
354
+ "sliding_attention",
355
+ "sliding_attention",
356
+ "full_attention",
357
+ "sliding_attention",
358
+ "sliding_attention",
359
+ "sliding_attention",
360
+ "sliding_attention",
361
+ "sliding_attention",
362
+ "full_attention",
363
+ "sliding_attention",
364
+ "sliding_attention",
365
+ "sliding_attention",
366
+ "sliding_attention",
367
+ "sliding_attention",
368
+ "full_attention"
369
+ ],
370
+ "output_attentions": false,
371
+ "quantization_config": {
372
+ "config_groups": {
373
+ "group_0": {
374
+ "input_activations": {
375
+ "dynamic": false,
376
+ "num_bits": 4,
377
+ "type": "float",
378
+ "group_size": 16
379
+ },
380
+ "weights": {
381
+ "dynamic": false,
382
+ "num_bits": 4,
383
+ "type": "float",
384
+ "group_size": 16
385
+ },
386
+ "targets": [
387
+ "Linear"
388
+ ]
389
+ }
390
+ },
391
+ "ignore": [
392
+ "audio_encoder*",
393
+ "speech_embeddings*",
394
+ "visual*",
395
+ "lm_head",
396
+ "model.embed_tokens",
397
+ "model.norm",
398
+ "model.rotary_emb*",
399
+ "model.swa_rotary_emb*",
400
+ "model.mtp*",
401
+ "model.layers.0*",
402
+ "model.layers.1.self_attn*",
403
+ "model.layers.1.mlp.gate*",
404
+ "model.layers.1.mlp.shared_expert*",
405
+ "model.layers.1.mlp.shared_expert_gate*",
406
+ "model.layers.2.self_attn*",
407
+ "model.layers.2.mlp.gate*",
408
+ "model.layers.2.mlp.shared_expert*",
409
+ "model.layers.2.mlp.shared_expert_gate*",
410
+ "model.layers.3.self_attn*",
411
+ "model.layers.3.mlp.gate*",
412
+ "model.layers.3.mlp.shared_expert*",
413
+ "model.layers.3.mlp.shared_expert_gate*",
414
+ "model.layers.4.self_attn*",
415
+ "model.layers.4.mlp.gate*",
416
+ "model.layers.4.mlp.shared_expert*",
417
+ "model.layers.4.mlp.shared_expert_gate*",
418
+ "model.layers.5.self_attn*",
419
+ "model.layers.5.mlp.gate*",
420
+ "model.layers.5.mlp.shared_expert*",
421
+ "model.layers.5.mlp.shared_expert_gate*",
422
+ "model.layers.6.self_attn*",
423
+ "model.layers.6.mlp.gate*",
424
+ "model.layers.6.mlp.shared_expert*",
425
+ "model.layers.6.mlp.shared_expert_gate*",
426
+ "model.layers.7.self_attn*",
427
+ "model.layers.7.mlp.gate*",
428
+ "model.layers.7.mlp.shared_expert*",
429
+ "model.layers.7.mlp.shared_expert_gate*",
430
+ "model.layers.8.self_attn*",
431
+ "model.layers.8.mlp.gate*",
432
+ "model.layers.8.mlp.shared_expert*",
433
+ "model.layers.8.mlp.shared_expert_gate*",
434
+ "model.layers.9.self_attn*",
435
+ "model.layers.9.mlp.gate*",
436
+ "model.layers.9.mlp.shared_expert*",
437
+ "model.layers.9.mlp.shared_expert_gate*",
438
+ "model.layers.10.self_attn*",
439
+ "model.layers.10.mlp.gate*",
440
+ "model.layers.10.mlp.shared_expert*",
441
+ "model.layers.10.mlp.shared_expert_gate*",
442
+ "model.layers.11.self_attn*",
443
+ "model.layers.11.mlp.gate*",
444
+ "model.layers.11.mlp.shared_expert*",
445
+ "model.layers.11.mlp.shared_expert_gate*",
446
+ "model.layers.12.self_attn*",
447
+ "model.layers.12.mlp.gate*",
448
+ "model.layers.12.mlp.shared_expert*",
449
+ "model.layers.12.mlp.shared_expert_gate*",
450
+ "model.layers.13.self_attn*",
451
+ "model.layers.13.mlp.gate*",
452
+ "model.layers.13.mlp.shared_expert*",
453
+ "model.layers.13.mlp.shared_expert_gate*",
454
+ "model.layers.14.self_attn*",
455
+ "model.layers.14.mlp.gate*",
456
+ "model.layers.14.mlp.shared_expert*",
457
+ "model.layers.14.mlp.shared_expert_gate*",
458
+ "model.layers.15.self_attn*",
459
+ "model.layers.15.mlp.gate*",
460
+ "model.layers.15.mlp.shared_expert*",
461
+ "model.layers.15.mlp.shared_expert_gate*",
462
+ "model.layers.16.self_attn*",
463
+ "model.layers.16.mlp.gate*",
464
+ "model.layers.16.mlp.shared_expert*",
465
+ "model.layers.16.mlp.shared_expert_gate*",
466
+ "model.layers.17.self_attn*",
467
+ "model.layers.17.mlp.gate*",
468
+ "model.layers.17.mlp.shared_expert*",
469
+ "model.layers.17.mlp.shared_expert_gate*",
470
+ "model.layers.18.self_attn*",
471
+ "model.layers.18.mlp.gate*",
472
+ "model.layers.18.mlp.shared_expert*",
473
+ "model.layers.18.mlp.shared_expert_gate*",
474
+ "model.layers.19.self_attn*",
475
+ "model.layers.19.mlp.gate*",
476
+ "model.layers.19.mlp.shared_expert*",
477
+ "model.layers.19.mlp.shared_expert_gate*",
478
+ "model.layers.20.self_attn*",
479
+ "model.layers.20.mlp.gate*",
480
+ "model.layers.20.mlp.shared_expert*",
481
+ "model.layers.20.mlp.shared_expert_gate*",
482
+ "model.layers.21.self_attn*",
483
+ "model.layers.21.mlp.gate*",
484
+ "model.layers.21.mlp.shared_expert*",
485
+ "model.layers.21.mlp.shared_expert_gate*",
486
+ "model.layers.22.self_attn*",
487
+ "model.layers.22.mlp.gate*",
488
+ "model.layers.22.mlp.shared_expert*",
489
+ "model.layers.22.mlp.shared_expert_gate*",
490
+ "model.layers.23.self_attn*",
491
+ "model.layers.23.mlp.gate*",
492
+ "model.layers.23.mlp.shared_expert*",
493
+ "model.layers.23.mlp.shared_expert_gate*",
494
+ "model.layers.24.self_attn*",
495
+ "model.layers.24.mlp.gate*",
496
+ "model.layers.24.mlp.shared_expert*",
497
+ "model.layers.24.mlp.shared_expert_gate*",
498
+ "model.layers.25.self_attn*",
499
+ "model.layers.25.mlp.gate*",
500
+ "model.layers.25.mlp.shared_expert*",
501
+ "model.layers.25.mlp.shared_expert_gate*",
502
+ "model.layers.26.self_attn*",
503
+ "model.layers.26.mlp.gate*",
504
+ "model.layers.26.mlp.shared_expert*",
505
+ "model.layers.26.mlp.shared_expert_gate*",
506
+ "model.layers.27.self_attn*",
507
+ "model.layers.27.mlp.gate*",
508
+ "model.layers.27.mlp.shared_expert*",
509
+ "model.layers.27.mlp.shared_expert_gate*",
510
+ "model.layers.28.self_attn*",
511
+ "model.layers.28.mlp.gate*",
512
+ "model.layers.28.mlp.shared_expert*",
513
+ "model.layers.28.mlp.shared_expert_gate*",
514
+ "model.layers.29.self_attn*",
515
+ "model.layers.29.mlp.gate*",
516
+ "model.layers.29.mlp.shared_expert*",
517
+ "model.layers.29.mlp.shared_expert_gate*",
518
+ "model.layers.30.self_attn*",
519
+ "model.layers.30.mlp.gate*",
520
+ "model.layers.30.mlp.shared_expert*",
521
+ "model.layers.30.mlp.shared_expert_gate*",
522
+ "model.layers.31.self_attn*",
523
+ "model.layers.31.mlp.gate*",
524
+ "model.layers.31.mlp.shared_expert*",
525
+ "model.layers.31.mlp.shared_expert_gate*",
526
+ "model.layers.32.self_attn*",
527
+ "model.layers.32.mlp.gate*",
528
+ "model.layers.32.mlp.shared_expert*",
529
+ "model.layers.32.mlp.shared_expert_gate*",
530
+ "model.layers.33.self_attn*",
531
+ "model.layers.33.mlp.gate*",
532
+ "model.layers.33.mlp.shared_expert*",
533
+ "model.layers.33.mlp.shared_expert_gate*",
534
+ "model.layers.34.self_attn*",
535
+ "model.layers.34.mlp.gate*",
536
+ "model.layers.34.mlp.shared_expert*",
537
+ "model.layers.34.mlp.shared_expert_gate*",
538
+ "model.layers.35.self_attn*",
539
+ "model.layers.35.mlp.gate*",
540
+ "model.layers.35.mlp.shared_expert*",
541
+ "model.layers.35.mlp.shared_expert_gate*",
542
+ "model.layers.36.self_attn*",
543
+ "model.layers.36.mlp.gate*",
544
+ "model.layers.36.mlp.shared_expert*",
545
+ "model.layers.36.mlp.shared_expert_gate*",
546
+ "model.layers.37.self_attn*",
547
+ "model.layers.37.mlp.gate*",
548
+ "model.layers.37.mlp.shared_expert*",
549
+ "model.layers.37.mlp.shared_expert_gate*",
550
+ "model.layers.38.self_attn*",
551
+ "model.layers.38.mlp.gate*",
552
+ "model.layers.38.mlp.shared_expert*",
553
+ "model.layers.38.mlp.shared_expert_gate*",
554
+ "model.layers.39.self_attn*",
555
+ "model.layers.39.mlp.gate*",
556
+ "model.layers.39.mlp.shared_expert*",
557
+ "model.layers.39.mlp.shared_expert_gate*",
558
+ "model.layers.40.self_attn*",
559
+ "model.layers.40.mlp.gate*",
560
+ "model.layers.40.mlp.shared_expert*",
561
+ "model.layers.40.mlp.shared_expert_gate*",
562
+ "model.layers.41.self_attn*",
563
+ "model.layers.41.mlp.gate*",
564
+ "model.layers.41.mlp.shared_expert*",
565
+ "model.layers.41.mlp.shared_expert_gate*",
566
+ "model.layers.42.self_attn*",
567
+ "model.layers.42.mlp.gate*",
568
+ "model.layers.42.mlp.shared_expert*",
569
+ "model.layers.42.mlp.shared_expert_gate*",
570
+ "model.layers.43.self_attn*",
571
+ "model.layers.43.mlp.gate*",
572
+ "model.layers.43.mlp.shared_expert*",
573
+ "model.layers.43.mlp.shared_expert_gate*",
574
+ "model.layers.44.self_attn*",
575
+ "model.layers.44.mlp.gate*",
576
+ "model.layers.44.mlp.shared_expert*",
577
+ "model.layers.44.mlp.shared_expert_gate*",
578
+ "model.layers.45.self_attn*",
579
+ "model.layers.45.mlp.gate*",
580
+ "model.layers.45.mlp.shared_expert*",
581
+ "model.layers.45.mlp.shared_expert_gate*",
582
+ "model.layers.46.self_attn*",
583
+ "model.layers.46.mlp.gate*",
584
+ "model.layers.46.mlp.shared_expert*",
585
+ "model.layers.46.mlp.shared_expert_gate*",
586
+ "model.layers.47.self_attn*",
587
+ "model.layers.47.mlp.gate*",
588
+ "model.layers.47.mlp.shared_expert*",
589
+ "model.layers.47.mlp.shared_expert_gate*"
590
+ ],
591
+ "quant_algo": "NVFP4",
592
+ "producer": {
593
+ "name": "modelopt",
594
+ "version": "0.39.0.dev290+gf9d9a71de.d20260407"
595
+ },
596
+ "quant_method": "modelopt"
597
+ }
598
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": false,
4
+ "eos_token_id": [151643, 151645, 1561672],
5
+ "temperature": 1.0,
6
+ "top_p": 0.95,
7
+ "max_new_tokens": 2048,
8
+ "transformers_version": "4.37.0"
9
+ }
hf_quant_config.json ADDED
@@ -0,0 +1,227 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "audio_encoder*",
23
+ "speech_embeddings*",
24
+ "visual*",
25
+ "lm_head",
26
+ "model.embed_tokens",
27
+ "model.norm",
28
+ "model.rotary_emb*",
29
+ "model.swa_rotary_emb*",
30
+ "model.mtp*",
31
+ "model.layers.0*",
32
+ "model.layers.1.self_attn*",
33
+ "model.layers.1.mlp.gate*",
34
+ "model.layers.1.mlp.shared_expert*",
35
+ "model.layers.1.mlp.shared_expert_gate*",
36
+ "model.layers.2.self_attn*",
37
+ "model.layers.2.mlp.gate*",
38
+ "model.layers.2.mlp.shared_expert*",
39
+ "model.layers.2.mlp.shared_expert_gate*",
40
+ "model.layers.3.self_attn*",
41
+ "model.layers.3.mlp.gate*",
42
+ "model.layers.3.mlp.shared_expert*",
43
+ "model.layers.3.mlp.shared_expert_gate*",
44
+ "model.layers.4.self_attn*",
45
+ "model.layers.4.mlp.gate*",
46
+ "model.layers.4.mlp.shared_expert*",
47
+ "model.layers.4.mlp.shared_expert_gate*",
48
+ "model.layers.5.self_attn*",
49
+ "model.layers.5.mlp.gate*",
50
+ "model.layers.5.mlp.shared_expert*",
51
+ "model.layers.5.mlp.shared_expert_gate*",
52
+ "model.layers.6.self_attn*",
53
+ "model.layers.6.mlp.gate*",
54
+ "model.layers.6.mlp.shared_expert*",
55
+ "model.layers.6.mlp.shared_expert_gate*",
56
+ "model.layers.7.self_attn*",
57
+ "model.layers.7.mlp.gate*",
58
+ "model.layers.7.mlp.shared_expert*",
59
+ "model.layers.7.mlp.shared_expert_gate*",
60
+ "model.layers.8.self_attn*",
61
+ "model.layers.8.mlp.gate*",
62
+ "model.layers.8.mlp.shared_expert*",
63
+ "model.layers.8.mlp.shared_expert_gate*",
64
+ "model.layers.9.self_attn*",
65
+ "model.layers.9.mlp.gate*",
66
+ "model.layers.9.mlp.shared_expert*",
67
+ "model.layers.9.mlp.shared_expert_gate*",
68
+ "model.layers.10.self_attn*",
69
+ "model.layers.10.mlp.gate*",
70
+ "model.layers.10.mlp.shared_expert*",
71
+ "model.layers.10.mlp.shared_expert_gate*",
72
+ "model.layers.11.self_attn*",
73
+ "model.layers.11.mlp.gate*",
74
+ "model.layers.11.mlp.shared_expert*",
75
+ "model.layers.11.mlp.shared_expert_gate*",
76
+ "model.layers.12.self_attn*",
77
+ "model.layers.12.mlp.gate*",
78
+ "model.layers.12.mlp.shared_expert*",
79
+ "model.layers.12.mlp.shared_expert_gate*",
80
+ "model.layers.13.self_attn*",
81
+ "model.layers.13.mlp.gate*",
82
+ "model.layers.13.mlp.shared_expert*",
83
+ "model.layers.13.mlp.shared_expert_gate*",
84
+ "model.layers.14.self_attn*",
85
+ "model.layers.14.mlp.gate*",
86
+ "model.layers.14.mlp.shared_expert*",
87
+ "model.layers.14.mlp.shared_expert_gate*",
88
+ "model.layers.15.self_attn*",
89
+ "model.layers.15.mlp.gate*",
90
+ "model.layers.15.mlp.shared_expert*",
91
+ "model.layers.15.mlp.shared_expert_gate*",
92
+ "model.layers.16.self_attn*",
93
+ "model.layers.16.mlp.gate*",
94
+ "model.layers.16.mlp.shared_expert*",
95
+ "model.layers.16.mlp.shared_expert_gate*",
96
+ "model.layers.17.self_attn*",
97
+ "model.layers.17.mlp.gate*",
98
+ "model.layers.17.mlp.shared_expert*",
99
+ "model.layers.17.mlp.shared_expert_gate*",
100
+ "model.layers.18.self_attn*",
101
+ "model.layers.18.mlp.gate*",
102
+ "model.layers.18.mlp.shared_expert*",
103
+ "model.layers.18.mlp.shared_expert_gate*",
104
+ "model.layers.19.self_attn*",
105
+ "model.layers.19.mlp.gate*",
106
+ "model.layers.19.mlp.shared_expert*",
107
+ "model.layers.19.mlp.shared_expert_gate*",
108
+ "model.layers.20.self_attn*",
109
+ "model.layers.20.mlp.gate*",
110
+ "model.layers.20.mlp.shared_expert*",
111
+ "model.layers.20.mlp.shared_expert_gate*",
112
+ "model.layers.21.self_attn*",
113
+ "model.layers.21.mlp.gate*",
114
+ "model.layers.21.mlp.shared_expert*",
115
+ "model.layers.21.mlp.shared_expert_gate*",
116
+ "model.layers.22.self_attn*",
117
+ "model.layers.22.mlp.gate*",
118
+ "model.layers.22.mlp.shared_expert*",
119
+ "model.layers.22.mlp.shared_expert_gate*",
120
+ "model.layers.23.self_attn*",
121
+ "model.layers.23.mlp.gate*",
122
+ "model.layers.23.mlp.shared_expert*",
123
+ "model.layers.23.mlp.shared_expert_gate*",
124
+ "model.layers.24.self_attn*",
125
+ "model.layers.24.mlp.gate*",
126
+ "model.layers.24.mlp.shared_expert*",
127
+ "model.layers.24.mlp.shared_expert_gate*",
128
+ "model.layers.25.self_attn*",
129
+ "model.layers.25.mlp.gate*",
130
+ "model.layers.25.mlp.shared_expert*",
131
+ "model.layers.25.mlp.shared_expert_gate*",
132
+ "model.layers.26.self_attn*",
133
+ "model.layers.26.mlp.gate*",
134
+ "model.layers.26.mlp.shared_expert*",
135
+ "model.layers.26.mlp.shared_expert_gate*",
136
+ "model.layers.27.self_attn*",
137
+ "model.layers.27.mlp.gate*",
138
+ "model.layers.27.mlp.shared_expert*",
139
+ "model.layers.27.mlp.shared_expert_gate*",
140
+ "model.layers.28.self_attn*",
141
+ "model.layers.28.mlp.gate*",
142
+ "model.layers.28.mlp.shared_expert*",
143
+ "model.layers.28.mlp.shared_expert_gate*",
144
+ "model.layers.29.self_attn*",
145
+ "model.layers.29.mlp.gate*",
146
+ "model.layers.29.mlp.shared_expert*",
147
+ "model.layers.29.mlp.shared_expert_gate*",
148
+ "model.layers.30.self_attn*",
149
+ "model.layers.30.mlp.gate*",
150
+ "model.layers.30.mlp.shared_expert*",
151
+ "model.layers.30.mlp.shared_expert_gate*",
152
+ "model.layers.31.self_attn*",
153
+ "model.layers.31.mlp.gate*",
154
+ "model.layers.31.mlp.shared_expert*",
155
+ "model.layers.31.mlp.shared_expert_gate*",
156
+ "model.layers.32.self_attn*",
157
+ "model.layers.32.mlp.gate*",
158
+ "model.layers.32.mlp.shared_expert*",
159
+ "model.layers.32.mlp.shared_expert_gate*",
160
+ "model.layers.33.self_attn*",
161
+ "model.layers.33.mlp.gate*",
162
+ "model.layers.33.mlp.shared_expert*",
163
+ "model.layers.33.mlp.shared_expert_gate*",
164
+ "model.layers.34.self_attn*",
165
+ "model.layers.34.mlp.gate*",
166
+ "model.layers.34.mlp.shared_expert*",
167
+ "model.layers.34.mlp.shared_expert_gate*",
168
+ "model.layers.35.self_attn*",
169
+ "model.layers.35.mlp.gate*",
170
+ "model.layers.35.mlp.shared_expert*",
171
+ "model.layers.35.mlp.shared_expert_gate*",
172
+ "model.layers.36.self_attn*",
173
+ "model.layers.36.mlp.gate*",
174
+ "model.layers.36.mlp.shared_expert*",
175
+ "model.layers.36.mlp.shared_expert_gate*",
176
+ "model.layers.37.self_attn*",
177
+ "model.layers.37.mlp.gate*",
178
+ "model.layers.37.mlp.shared_expert*",
179
+ "model.layers.37.mlp.shared_expert_gate*",
180
+ "model.layers.38.self_attn*",
181
+ "model.layers.38.mlp.gate*",
182
+ "model.layers.38.mlp.shared_expert*",
183
+ "model.layers.38.mlp.shared_expert_gate*",
184
+ "model.layers.39.self_attn*",
185
+ "model.layers.39.mlp.gate*",
186
+ "model.layers.39.mlp.shared_expert*",
187
+ "model.layers.39.mlp.shared_expert_gate*",
188
+ "model.layers.40.self_attn*",
189
+ "model.layers.40.mlp.gate*",
190
+ "model.layers.40.mlp.shared_expert*",
191
+ "model.layers.40.mlp.shared_expert_gate*",
192
+ "model.layers.41.self_attn*",
193
+ "model.layers.41.mlp.gate*",
194
+ "model.layers.41.mlp.shared_expert*",
195
+ "model.layers.41.mlp.shared_expert_gate*",
196
+ "model.layers.42.self_attn*",
197
+ "model.layers.42.mlp.gate*",
198
+ "model.layers.42.mlp.shared_expert*",
199
+ "model.layers.42.mlp.shared_expert_gate*",
200
+ "model.layers.43.self_attn*",
201
+ "model.layers.43.mlp.gate*",
202
+ "model.layers.43.mlp.shared_expert*",
203
+ "model.layers.43.mlp.shared_expert_gate*",
204
+ "model.layers.44.self_attn*",
205
+ "model.layers.44.mlp.gate*",
206
+ "model.layers.44.mlp.shared_expert*",
207
+ "model.layers.44.mlp.shared_expert_gate*",
208
+ "model.layers.45.self_attn*",
209
+ "model.layers.45.mlp.gate*",
210
+ "model.layers.45.mlp.shared_expert*",
211
+ "model.layers.45.mlp.shared_expert_gate*",
212
+ "model.layers.46.self_attn*",
213
+ "model.layers.46.mlp.gate*",
214
+ "model.layers.46.mlp.shared_expert*",
215
+ "model.layers.46.mlp.shared_expert_gate*",
216
+ "model.layers.47.self_attn*",
217
+ "model.layers.47.mlp.gate*",
218
+ "model.layers.47.mlp.shared_expert*",
219
+ "model.layers.47.mlp.shared_expert_gate*"
220
+ ],
221
+ "quant_algo": "NVFP4",
222
+ "producer": {
223
+ "name": "modelopt",
224
+ "version": "0.39.0.dev290+gf9d9a71de.d20260407"
225
+ },
226
+ "quant_method": "modelopt"
227
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00035.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42f4a5e9de1c0cd8995f6d75e8bb42bbf196f7fe3daf513d5fd75e9d91bd24f3
3
+ size 5372235616
model-00002-of-00035.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78d1330821c90e43611ca6e1dce53518576e2025ed4191e64ade4aeb1bff2b56
3
+ size 5372276856
model-00003-of-00035.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bc20dc3244d480df62d5ab262bbb1309c9b88b79871e271775795458393edfd
3
+ size 5369134748
model-00004-of-00035.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f42112cca7e98588a4f525798c281c5763054e96cd8f3df00f3119216273af0
3
+ size 5371751960
model-00005-of-00035.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7eae1cc1136d84443dfd4fed2b8d53e4f84cae9bc715bae186d53b2cdbf0a35d
3
+ size 5372277256
model-00006-of-00035.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78c04740b4ac26d28fb61862eed035c9a39339f1650b11897a37fadf911c83ad
3
+ size 5369657836
model-00007-of-00035.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b00eff0e9b5227e562fc0304a366461e18bef2a8925d6f8e1029ccc0b1bd7134
3
+ size 5372278568
model-00008-of-00035.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38f556021f59a2be6420b8e62f1f5cd54826cdc2e27f6cb64d6e1a1456f2cfb3
3
+ size 5369137812
model-00009-of-00035.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:458f6df1c89d86338d78f9c779805300ab541a86b2dcf835a39600cff9299b57
3
+ size 5371755392
model-00010-of-00035.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fdb0484cf7ac98c4b3908d02b7c38d222b4696893938bd556fbc75fd806fb89
3
+ size 5372280552
model-00011-of-00035.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45237e6f1bff7e92e93246c4eea4fb599a667f1dd2199e85be42f753c1e3c3a6
3
+ size 5369660924
model-00012-of-00035.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d5f00ed0345198d25164aa0f1c03eea5d0e463b6d644a4e76f304a692ee9dea
3
+ size 5371232280
model-00013-of-00035.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b13d6d07df72ad3d3d9789fe188d8ca68862910496154802bdd698db66a3ba1
3
+ size 5369661364
model-00015-of-00035.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f4255f3df87060f6d34b2b0ec57e52380fb4354c26c6b582a1f969dae234cdb
3
+ size 5372280552
model-00016-of-00035.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc79fd5e3de1900f4e457acb74c7f992236bbe8eca262e217f97b210899fd187
3
+ size 5369137156
model-00017-of-00035.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1d0b014414b735cdd56f593562f3e5131f1131d842eb16ff84cc2ca0a004082
3
+ size 5371756048
model-00018-of-00035.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89b994431fa99e7292f3fa9aca1f3b2365b222da65ddd1b9c0331ee84d370816
3
+ size 5369661260
model-00019-of-00035.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:457db02428d00fc2c830dd12c8fd311d2eb9572b7f08d15c1a3e461a0a18e239
3
+ size 5372280016
model-00021-of-00035.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4efab9985e73460ab0fdfc9cb495c47d5b0ed347a60df15985050bcf7af45aa
3
+ size 5372798532
model-00022-of-00035.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ae2540f44f8034d9bb90aaa7f9c647b38f58e94cb73fb01d50525704a12ff65
3
+ size 5372280552
model-00023-of-00035.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6631c938bddc3af941725d838b0a541dcd7af0fdfdb6621abc5ef1c1d8f8a79
3
+ size 5369661124
model-00024-of-00035.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:684f0ae022b9a080066925be1a080a75a8c46198250066275ac73b4622e486a9
3
+ size 5372280152
model-00025-of-00035.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a47ac8e277d517378e5d06c1be4d9a5d44249ced7dfed42bc77c475e761e146
3
+ size 5369137940
model-00026-of-00035.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56bfe09813ab025e863b437d1be054a8375724f708db0d9aa3c7a0c25312237c
3
+ size 5371755264
model-00027-of-00035.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a85d5d7a6fbbbe77c34a9e96f36423a39601df27053cbbad297431e3ca518c29
3
+ size 5372280552
model-00028-of-00035.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccf4f830a8d1f47b08398aceeeb23a691a787b7bd34f5f08eb832f603404310b
3
+ size 5369661020
model-00029-of-00035.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf2bc24ad22ec8178e8d19b6fb85953e6c458efcf79c1dca43a83c38ee57edf0
3
+ size 5371232184
model-00030-of-00035.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa1cac4a8e77f175655461743e6aba093b41de5341ecd852afa2e62a2722c4ce
3
+ size 5369661460
model-00031-of-00035.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d2239ec3e46327ff2fd995c25856a70efa83049c4560e6616b1d3d1cf76fc64
3
+ size 5372279816
model-00032-of-00035.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a04035695604ad201b8885a23153af81d3ccbc3bcfa8bc27c17bb5959c8007ad
3
+ size 5372280552
model-00033-of-00035.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff8ae119fec50f327828bac6e6c3bb93eb91e6f2b00f0f64a01dd5f60d2d5d67
3
+ size 5369137260
model-00034-of-00035.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e39b511533abf5bc8f4398096ded7336797aeeda642596aeaf991a05f8376d3b
3
+ size 5376279968
model-00035-of-00035.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35bc1a3dc07112ece7537475cc4d2626aed53de23fe1d4d6594a74668e172818
3
+ size 1922097992
model-inputscales.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:381f70f31092063586d99f91a7a5ed82f8974116050e8276e43a8cb3782199d6
3
+ size 4157304
model-mtp.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6c24e326f2bdba86afc2b2667787d400fc956e81a8238cf6a8a82334747f009
3
+ size 1975644568
model.safetensors.index.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f73ecca1ec1053f8629766eda99cba90bc8074d338f2211fbf1c71c9f0792fd
3
+ size 13743418
preprocessor_config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "min_pixels": 3136,
3
+ "max_pixels": 12845056,
4
+ "patch_size": 16,
5
+ "temporal_patch_size": 2,
6
+ "merge_size": 2,
7
+ "image_mean": [
8
+ 0.48145466,
9
+ 0.4578275,
10
+ 0.40821073
11
+ ],
12
+ "image_std": [
13
+ 0.26862954,
14
+ 0.26130258,
15
+ 0.27577711
16
+ ],
17
+ "image_processor_type": "Qwen2VLImageProcessor",
18
+ "processor_class": "Qwen2_5_VLProcessor"
19
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,293 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "151669": {
214
+ "content": "<|audio_pad|>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "151670": {
222
+ "content": "<|mimo_video_start|>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "151671": {
230
+ "content": "<|mimo_video_end|>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "151672": {
238
+ "content": "<|mimo_audio_eod|>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "151673": {
246
+ "content": "<|mimo_audio_start|>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "151674": {
254
+ "content": "<|mimo_audio_end|>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": true
260
+ }
261
+ },
262
+ "additional_special_tokens": [
263
+ "<|im_start|>",
264
+ "<|im_end|>",
265
+ "<|object_ref_start|>",
266
+ "<|object_ref_end|>",
267
+ "<|box_start|>",
268
+ "<|box_end|>",
269
+ "<|quad_start|>",
270
+ "<|quad_end|>",
271
+ "<|vision_start|>",
272
+ "<|vision_end|>",
273
+ "<|vision_pad|>",
274
+ "<|image_pad|>",
275
+ "<|video_pad|>",
276
+ "<|audio_pad|>",
277
+ "<|mimo_video_start|>",
278
+ "<|mimo_video_end|>",
279
+ "<|mimo_audio_eod|>",
280
+ "<|mimo_audio_start|>",
281
+ "<|mimo_audio_end|>"
282
+ ],
283
+ "bos_token": null,
284
+ "chat_template": "{%- if not add_generation_prompt is defined -%}\n {%- set add_generation_prompt = false -%}\n{%- endif -%}\n{%- if not enable_thinking is defined -%}\n {%- set enable_thinking = true -%}\n{%- endif -%}\n{%- if not keep_all_reasoning is defined -%}\n {%- set keep_all_reasoning = true -%}\n{%- endif -%}\n{%- macro render_extra_keys(json_dict, handled_keys) -%}\n {%- if json_dict is mapping %}\n {%- for json_key in json_dict if json_key not in handled_keys %}\n {%- if json_dict[json_key] is mapping or (json_dict[json_key] is sequence and json_dict[json_key] is not string) %}\n {{- '\\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '</' ~ json_key ~ '>' }}\n {%- else %}\n {{-'\\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '</' ~ json_key ~ '>' }}\n {%- endif %}\n {%- endfor %}\n {%- endif %}\n{%- endmacro -%}\n{%- macro render_content(message_content) -%}\n {%- if message_content is string -%}\n {{- message_content -}}\n {%- else -%}\n {%- for content in message_content -%}\n {%- if content['type'] == 'image' or 'image' in content or 'image_url' in content -%}\n {{- '<|vision_start|><|image_pad|><|vision_end|>' -}}\n {%- elif content['type'] == 'audio' or 'audio' in content or 'audio_url' in content -%}\n {{- '<|mimo_audio_start|><|audio_pad|><|mimo_audio_end|>' -}}\n {%- elif content['type'] == 'video' or 'video' in content or 'video_url' in content -%}\n {{- '<|vision_start|><|video_pad|><|vision_end|>' -}}\n {%- elif 'text' in content -%}\n {{- content['text'] -}}\n {%- endif -%}\n {%- endfor -%}\n {%- endif -%}\n{%- endmacro -%}\n{%- if messages[0][\"role\"] == \"system\" %}\n {%- set system_message = messages[0][\"content\"] %}\n {%- set loop_messages = messages[1:] %}\n{%- else %}\n {%- set loop_messages = messages %}\n{%- endif %}\n{%- set ns = namespace(last_user_index=-1) %}\n{%- for m in loop_messages %}\n {%- if m.role == 'user' %}\n {%- set ns.last_user_index = loop.index0 -%}\n {%- endif %}\n{%- endfor %}\n{%- if not tools is defined %}\n {%- set tools = [] %}\n{%- endif %}\n{%- if system_message is defined %}\n {{- \"<|im_start|>system\\n\" + system_message }}\n{%- else %}\n {{- \"<|im_start|>system\\nYou are MiMo, a helpful AI assistant engineered by Xiaomi.\" }}\n{%- endif %}\n{%- if tools is iterable and tools | length > 0 %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou have access to the following functions:\\n\\n\" }}\n {{- \"<tools>\" }}\n {%- for tool in tools %}\n {%- if tool.function is defined %}\n {%- set tool = tool.function %}\n {%- endif %}\n {{- \"\\n<function>\\n<name>\" ~ tool.name ~ \"</name>\" }}\n {%- if tool.description is defined %}\n {{- '\\n<description>' ~ (tool.description | trim) ~ '</description>' }}\n {%- endif %}\n {{- '\\n<parameters>' }}\n {%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %}\n {%- for param_name, param_fields in tool.parameters.properties|items %}\n {{- '\\n<parameter>' }}\n {{- '\\n<name>' ~ param_name ~ '</name>' }}\n {%- if param_fields.type is defined %}\n {{- '\\n<type>' ~ (param_fields.type | string) ~ '</type>' }}\n {%- endif %}\n {%- if param_fields.description is defined %}\n {{- '\\n<description>' ~ (param_fields.description | trim) ~ '</description>' }}\n {%- endif %}\n {%- set handled_keys = ['name', 'type', 'description'] %}\n {{- render_extra_keys(param_fields, handled_keys) }}\n {{- '\\n</parameter>' }}\n {%- endfor %}\n {%- endif %}\n {%- set handled_keys = ['type', 'properties'] %}\n {{- render_extra_keys(tool.parameters, handled_keys) }}\n {{- '\\n</parameters>' }}\n {%- set handled_keys = ['type', 'name', 'description', 'parameters'] %}\n {{- render_extra_keys(tool, handled_keys) }}\n {{- '\\n</function>' }}\n {%- endfor %}\n {{- \"\\n</tools>\" }}\n {{- '\\n\\nFor each function call, output the function name and arguments in the following format:\\n<tool_call>\\n<function=example_function_name>\\n<parameter=example_parameter_1>value_1</parameter>\\n<parameter=example_parameter_2>This is the value for the second parameter\\nthat can span\\nmultiple lines</parameter>\\n</function>\\n</tool_call>\\n\\n<IMPORTANT>\\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\\n- DO NOT use function calls inside <think></think> tags.\\n- The value enclosed between parameter tags is preserved exactly as-is, including newlines and spaces.\\n</IMPORTANT>' }}\n{%- endif %}\n{{- '<|im_end|>' }}\n{%- for message in loop_messages %}\n {%- if message.content is string %}\n {%- set content = message.content %}\n {%- else %}\n {%- set content = render_content(message.content) %}\n {%- endif %}\n {%- if message.role == \"assistant\" %}\n {%- if message.reasoning_content is string %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- set reasoning_content = '' %}\n {%- if '</think>' in content %}\n {%- set reasoning_content = content.split('</think>')[0].split('<think>')[-1] %}\n {%- set content = content.split('</think>')[-1] %}\n {%- endif %}\n {%- endif %}\n {%- if (keep_all_reasoning or loop.index0 > ns.last_user_index) and reasoning_content -%}\n {{- '<|im_start|>' + message.role + '\\n<think>' + reasoning_content + '</think>' + content }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n<think></think>' + content }}\n {%- endif %}\n {%- if message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}\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 {{- '<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n {%- if tool_call.arguments is defined %}\n {%- for args_name, args_value in tool_call.arguments|items %}\n {{- '<parameter=' + args_name + '>' }}\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 {{- '</parameter>\\n' }}\n {%- endfor %}\n {%- endif %}\n {{- '</function>\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>' }}\n {%- elif message.role == \"user\" %}\n {{- '<|im_start|>' + message.role + '\\n' + render_content(message.content) + '<|im_end|>' }}\n {%- elif message.role == \"system\" %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n {{- '<|im_start|>tool\\n' }}\n {%- endif %}\n {{- '<tool_response>\\n' }}\n {{- render_content(message.content) }}\n {{- '\\n</tool_response>\\n' }}\n {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n {{- '<|im_end|>' }}\n {%- elif loop.last %}\n {{- '<|im_end|>' }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if not enable_thinking -%}\n {{- '<think></think>' -}}\n {%- else -%}\n {{- '' -}}\n {%- endif -%}\n{%- endif %}\n",
285
+ "clean_up_tokenization_spaces": false,
286
+ "eos_token": "<|im_end|>",
287
+ "errors": "replace",
288
+ "model_max_length": 131072,
289
+ "pad_token": "<|endoftext|>",
290
+ "split_special_tokens": false,
291
+ "tokenizer_class": "Qwen2Tokenizer",
292
+ "unk_token": null
293
+ }