Hugging Face's logo

interlive
/
STRIDE-M005-indep-PMDM-Qwen3-VL-2B

Transformers
Safetensors
qwen3_vl
Generated from Trainer
Model card Files
xet
 Community
arkimjh commited on
Commit
9bc35ef
·
verified ·
1 Parent(s): 8e4e99e

Training in progress, step 1000

Browse files
Files changed (12) hide show
  1. added_tokens.json +31 -0
  2. config.json +3 -5
  3. generation_config.json +1 -2
  4. merges.txt +0 -0
  5. model.safetensors +1 -1
  6. preprocessor_config.json +39 -0
  7. special_tokens_map.json +31 -0
  8. tokenizer.json +2 -2
  9. tokenizer_config.json +242 -8
  10. training_args.bin +2 -2
  11. video_preprocessor_config.json +41 -0
  12. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<activation>": 151669,
6
+ "<active>": 151670,
7
+ "<inactive>": 151671,
8
+ "<think>": 151667,
9
+ "<tool_call>": 151657,
10
+ "<tool_response>": 151665,
11
+ "<|box_end|>": 151649,
12
+ "<|box_start|>": 151648,
13
+ "<|endoftext|>": 151643,
14
+ "<|file_sep|>": 151664,
15
+ "<|fim_middle|>": 151660,
16
+ "<|fim_pad|>": 151662,
17
+ "<|fim_prefix|>": 151659,
18
+ "<|fim_suffix|>": 151661,
19
+ "<|im_end|>": 151645,
20
+ "<|im_start|>": 151644,
21
+ "<|image_pad|>": 151655,
22
+ "<|object_ref_end|>": 151647,
23
+ "<|object_ref_start|>": 151646,
24
+ "<|quad_end|>": 151651,
25
+ "<|quad_start|>": 151650,
26
+ "<|repo_name|>": 151663,
27
+ "<|video_pad|>": 151656,
28
+ "<|vision_end|>": 151653,
29
+ "<|vision_pad|>": 151654,
30
+ "<|vision_start|>": 151652
31
+ }
config.json CHANGED
@@ -2,7 +2,6 @@
2
  "architectures": [
3
  "Qwen3VLForProactiveMDM"
4
  ],
5
- "bos_token_id": null,
6
  "dtype": "bfloat16",
7
  "eos_token_id": 151645,
8
  "image_token_id": 151655,
@@ -27,24 +26,23 @@
27
  "num_attention_heads": 16,
28
  "num_hidden_layers": 28,
29
  "num_key_value_heads": 8,
30
- "pad_token_id": null,
31
  "rms_norm_eps": 1e-06,
32
- "rope_parameters": {
33
  "mrope_interleaved": true,
34
  "mrope_section": [
35
  24,
36
  20,
37
  20
38
  ],
39
- "rope_theta": 5000000,
40
  "rope_type": "default"
41
  },
 
42
  "tie_word_embeddings": true,
43
  "use_cache": true,
44
  "vocab_size": 151672
45
  },
46
  "tie_word_embeddings": true,
47
- "transformers_version": "5.2.0.dev0",
48
  "trigger_temporal_resolution": 1.0,
49
  "trigger_window_future": 16,
50
  "trigger_window_past": 128,
 
2
  "architectures": [
3
  "Qwen3VLForProactiveMDM"
4
  ],
 
5
  "dtype": "bfloat16",
6
  "eos_token_id": 151645,
7
  "image_token_id": 151655,
 
26
  "num_attention_heads": 16,
27
  "num_hidden_layers": 28,
28
  "num_key_value_heads": 8,
 
29
  "rms_norm_eps": 1e-06,
30
+ "rope_scaling": {
31
  "mrope_interleaved": true,
32
  "mrope_section": [
33
  24,
34
  20,
35
  20
36
  ],
 
37
  "rope_type": "default"
38
  },
39
+ "rope_theta": 5000000,
40
  "tie_word_embeddings": true,
41
  "use_cache": true,
42
  "vocab_size": 151672
43
  },
44
  "tie_word_embeddings": true,
45
+ "transformers_version": "4.57.3",
46
  "trigger_temporal_resolution": 1.0,
47
  "trigger_window_future": 16,
48
  "trigger_window_past": 128,
generation_config.json CHANGED
@@ -6,9 +6,8 @@
6
  151643
7
  ],
8
  "pad_token_id": 151643,
9
- "repetition_penalty": 1.0,
10
  "temperature": 0.7,
11
  "top_k": 20,
12
  "top_p": 0.8,
13
- "transformers_version": "5.2.0.dev0"
14
  }
 
6
  151643
7
  ],
8
  "pad_token_id": 151643,
 
9
  "temperature": 0.7,
10
  "top_k": 20,
11
  "top_p": 0.8,
12
+ "transformers_version": "4.57.3"
13
  }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2dde054abe01f9f3952a3cc321a6c5e6f7f9d33f7813a1c2a923f650ee00a61b
3
  size 4875307648
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fa2a371cdc52413f26ed0bdf26ba8b2a0f30eace4b60d253a77e02e1c50f5cf
3
  size 4875307648
preprocessor_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "disable_grouping": null,
7
+ "do_center_crop": null,
8
+ "do_convert_rgb": true,
9
+ "do_normalize": true,
10
+ "do_pad": null,
11
+ "do_rescale": true,
12
+ "do_resize": true,
13
+ "image_mean": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "image_processor_type": "Qwen2VLImageProcessorFast",
19
+ "image_std": [
20
+ 0.5,
21
+ 0.5,
22
+ 0.5
23
+ ],
24
+ "input_data_format": null,
25
+ "max_pixels": null,
26
+ "merge_size": 2,
27
+ "min_pixels": null,
28
+ "pad_size": null,
29
+ "patch_size": 16,
30
+ "processor_class": "Qwen3VLProcessor",
31
+ "resample": 3,
32
+ "rescale_factor": 0.00392156862745098,
33
+ "return_tensors": null,
34
+ "size": {
35
+ "longest_edge": 16777216,
36
+ "shortest_edge": 65536
37
+ },
38
+ "temporal_patch_size": 2
39
+ }
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 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e2961f6a112e2a3ee9ddbf650d652cc267fbbd555008bbfb3faeb7baa084601
3
- size 11423211
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfeb96dca38996eab3b45756ba2b80ba22060f38277dff7c075253f41bd593b6
3
+ size 11423215
tokenizer_config.json CHANGED
@@ -1,12 +1,241 @@
1
  {
 
2
  "add_prefix_space": false,
3
- "backend": "tokenizers",
4
- "bos_token": null,
5
- "clean_up_tokenization_spaces": false,
6
- "do_sample_frames": false,
7
- "eos_token": "<|im_end|>",
8
- "errors": "replace",
9
- "extra_special_tokens": [
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10
  "<|im_start|>",
11
  "<|im_end|>",
12
  "<|object_ref_start|>",
@@ -21,7 +250,12 @@
21
  "<|image_pad|>",
22
  "<|video_pad|>"
23
  ],
24
- "is_local": false,
 
 
 
 
 
25
  "model_max_length": 4096000,
26
  "pad_to_multiple_of": 256,
27
  "pad_token": "<|endoftext|>",
 
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": "<activation>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "151670": {
222
+ "content": "<active>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "151671": {
230
+ "content": "<inactive>",
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|>",
 
250
  "<|image_pad|>",
251
  "<|video_pad|>"
252
  ],
253
+ "bos_token": null,
254
+ "clean_up_tokenization_spaces": false,
255
+ "do_sample_frames": false,
256
+ "eos_token": "<|im_end|>",
257
+ "errors": "replace",
258
+ "extra_special_tokens": {},
259
  "model_max_length": 4096000,
260
  "pad_to_multiple_of": 256,
261
  "pad_token": "<|endoftext|>",
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:314b949d8a5528a84dc0536fcb53b9375d0d5a9a3dc2d24c3e090c84ff0ed899
3
- size 7057
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da52220be4947fc2f1ff0b70a70cd058e92b4a463c72d26b7e0594f2bd9eecd3
3
+ size 7619
video_preprocessor_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": true,
5
+ "device": null,
6
+ "do_center_crop": null,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "do_sample_frames": false,
12
+ "fps": 2,
13
+ "image_mean": [
14
+ 0.5,
15
+ 0.5,
16
+ 0.5
17
+ ],
18
+ "image_std": [
19
+ 0.5,
20
+ 0.5,
21
+ 0.5
22
+ ],
23
+ "input_data_format": null,
24
+ "max_frames": 768,
25
+ "merge_size": 2,
26
+ "min_frames": 4,
27
+ "num_frames": null,
28
+ "pad_size": null,
29
+ "patch_size": 16,
30
+ "processor_class": "Qwen3VLProcessor",
31
+ "resample": 3,
32
+ "rescale_factor": 0.00392156862745098,
33
+ "return_metadata": false,
34
+ "size": {
35
+ "longest_edge": 25165824,
36
+ "shortest_edge": 4096
37
+ },
38
+ "temporal_patch_size": 2,
39
+ "video_metadata": null,
40
+ "video_processor_type": "Qwen3VLVideoProcessor"
41
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff