Hugging Face's logo

Jazzcharles
/
AuroLA-3B

Safetensors
qwen2_5_omni_thinker
Model card Files
xet
Community
1
Jazzcharles commited on
Commit
15206da
·
verified ·
1 Parent(s): c5ea051

Upload folder using huggingface_hub

Browse files
Files changed (15) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +25 -0
  3. chat_template.jinja +7 -0
  4. config.json +147 -0
  5. generation_config.json +4 -0
  6. merges.txt +0 -0
  7. model-00001-of-00002.safetensors +3 -0
  8. model-00002-of-00002.safetensors +3 -0
  9. model.safetensors.index.json +0 -0
  10. preprocessor_config.json +31 -0
  11. special_tokens_map.json +38 -0
  12. tokenizer.json +3 -0
  13. tokenizer_config.json +230 -0
  14. video_preprocessor_config.json +55 -0
  15. vocab.json +0 -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
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<emb>": 151665,
4
+ "<tool_call>": 151657,
5
+ "<|AUDIO|>": 151646,
6
+ "<|IMAGE|>": 151655,
7
+ "<|VIDEO|>": 151656,
8
+ "<|audio_bos|>": 151647,
9
+ "<|audio_eos|>": 151648,
10
+ "<|box_end|>": 151649,
11
+ "<|endoftext|>": 151643,
12
+ "<|file_sep|>": 151664,
13
+ "<|fim_middle|>": 151660,
14
+ "<|fim_pad|>": 151662,
15
+ "<|fim_prefix|>": 151659,
16
+ "<|fim_suffix|>": 151661,
17
+ "<|im_end|>": 151645,
18
+ "<|im_start|>": 151644,
19
+ "<|quad_end|>": 151651,
20
+ "<|quad_start|>": 151650,
21
+ "<|repo_name|>": 151663,
22
+ "<|vision_bos|>": 151652,
23
+ "<|vision_eos|>": 151653,
24
+ "<|vision_pad|>": 151654
25
+ }
chat_template.jinja ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {% set audio_count = namespace(value=0) %}{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system
2
+ You are a helpful assistant.<|im_end|>
3
+ {% endif %}<|im_start|>{{ message['role'] }}
4
+ {% if message['content'] is string %}{{ message['content'] }}<|im_end|>
5
+ {% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_bos|><|IMAGE|><|vision_eos|>{% elif content['type'] == 'audio' or 'audio' in content or 'audio_url' in content %}{% set audio_count.value = audio_count.value + 1 %}{% if add_audio_id %}Audio {{ audio_count.value }}: {% endif %}<|audio_bos|><|AUDIO|><|audio_eos|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_bos|><|VIDEO|><|vision_eos|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>
6
+ {% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
7
+ {% endif %}
config.json ADDED
@@ -0,0 +1,147 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "architectures": [
4
+ "Qwen2_5OmniThinkerForConditionalGeneration"
5
+ ],
6
+ "audio_config": {
7
+ "_attn_implementation_autoset": true,
8
+ "activation_dropout": 0.0,
9
+ "activation_function": "gelu",
10
+ "attention_dropout": 0.0,
11
+ "d_model": 1280,
12
+ "dropout": 0.0,
13
+ "dtype": "bfloat16",
14
+ "encoder_attention_heads": 20,
15
+ "encoder_ffn_dim": 5120,
16
+ "encoder_layerdrop": 0.0,
17
+ "encoder_layers": 32,
18
+ "init_std": 0.02,
19
+ "initializer_range": 0.02,
20
+ "max_source_positions": 1500,
21
+ "model_type": "qwen2_5_omni_audio_encoder",
22
+ "n_window": 100,
23
+ "num_hidden_layers": 32,
24
+ "num_mel_bins": 128,
25
+ "output_dim": 2048,
26
+ "scale_embedding": false
27
+ },
28
+ "audio_end_token_id": 151648,
29
+ "audio_start_token_id": 151647,
30
+ "audio_token_index": 151646,
31
+ "bos_token_id": 151644,
32
+ "dtype": "bfloat16",
33
+ "emb_token_ids": [
34
+ 151665
35
+ ],
36
+ "eos_token_id": 151645,
37
+ "ignore_index": -100,
38
+ "image_token_index": 151655,
39
+ "init_std": 0.02,
40
+ "initializer_range": 0.02,
41
+ "model_type": "qwen2_5_omni_thinker",
42
+ "pad_token_id": 151643,
43
+ "position_id_per_seconds": 25,
44
+ "seconds_per_chunk": 2,
45
+ "text_config": {
46
+ "attention_dropout": 0.0,
47
+ "dtype": "bfloat16",
48
+ "hidden_act": "silu",
49
+ "hidden_size": 2048,
50
+ "init_std": 0.02,
51
+ "initializer_range": 0.02,
52
+ "intermediate_size": 11008,
53
+ "layer_types": [
54
+ "full_attention",
55
+ "full_attention",
56
+ "full_attention",
57
+ "full_attention",
58
+ "full_attention",
59
+ "full_attention",
60
+ "full_attention",
61
+ "full_attention",
62
+ "full_attention",
63
+ "full_attention",
64
+ "full_attention",
65
+ "full_attention",
66
+ "full_attention",
67
+ "full_attention",
68
+ "full_attention",
69
+ "full_attention",
70
+ "full_attention",
71
+ "full_attention",
72
+ "full_attention",
73
+ "full_attention",
74
+ "full_attention",
75
+ "full_attention",
76
+ "full_attention",
77
+ "full_attention",
78
+ "full_attention",
79
+ "full_attention",
80
+ "full_attention",
81
+ "full_attention",
82
+ "full_attention",
83
+ "full_attention",
84
+ "full_attention",
85
+ "full_attention",
86
+ "full_attention",
87
+ "full_attention",
88
+ "full_attention",
89
+ "full_attention"
90
+ ],
91
+ "max_position_embeddings": 32768,
92
+ "max_window_layers": 70,
93
+ "model_type": "qwen2_5_omni_text",
94
+ "num_attention_heads": 16,
95
+ "num_hidden_layers": 36,
96
+ "num_key_value_heads": 2,
97
+ "rms_norm_eps": 1e-06,
98
+ "rope_scaling": {
99
+ "mrope_section": [
100
+ 16,
101
+ 24,
102
+ 24
103
+ ],
104
+ "rope_type": "default",
105
+ "type": "default"
106
+ },
107
+ "rope_theta": 1000000.0,
108
+ "sliding_window": null,
109
+ "use_cache": true,
110
+ "use_sliding_window": false,
111
+ "vocab_size": 151666
112
+ },
113
+ "transformers_version": "4.57.1",
114
+ "user_token_id": 872,
115
+ "video_token_index": 151656,
116
+ "vision_config": {
117
+ "_attn_implementation_autoset": true,
118
+ "depth": 32,
119
+ "dtype": "bfloat16",
120
+ "embed_dim": 1280,
121
+ "fullatt_block_indexes": [
122
+ 7,
123
+ 15,
124
+ 23,
125
+ 31
126
+ ],
127
+ "hidden_act": "silu",
128
+ "hidden_size": 1280,
129
+ "in_channels": 3,
130
+ "in_chans": 3,
131
+ "init_std": 0.02,
132
+ "initializer_range": 0.02,
133
+ "intermediate_size": 3420,
134
+ "model_type": "qwen2_5_omni_vision_encoder",
135
+ "num_heads": 16,
136
+ "out_hidden_size": 2048,
137
+ "patch_size": 14,
138
+ "spatial_merge_size": 2,
139
+ "spatial_patch_size": 14,
140
+ "temporal_patch_size": 2,
141
+ "tokens_per_second": 25,
142
+ "window_size": 112
143
+ },
144
+ "vision_end_token_id": 151653,
145
+ "vision_start_token_id": 151652,
146
+ "vision_token_id": 151654
147
+ }
generation_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "transformers_version": "4.57.1"
4
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d8a28f30eb848214a93709cc754c5115ac3ea184e2a98068934d9d8c78fddac
3
+ size 4993735776
model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30e53c92faae9141b7fed7c972988ed12ab044deaab7137be64ba63ce85d3899
3
+ size 4411143136
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
preprocessor_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 300,
3
+ "dither": 0.0,
4
+ "feature_extractor_type": "WhisperFeatureExtractor",
5
+ "feature_size": 128,
6
+ "hop_length": 160,
7
+ "image_mean": [
8
+ 0.48145466,
9
+ 0.4578275,
10
+ 0.40821073
11
+ ],
12
+ "image_processor_type": "Qwen2VLImageProcessor",
13
+ "image_std": [
14
+ 0.26862954,
15
+ 0.26130258,
16
+ 0.27577711
17
+ ],
18
+ "max_pixels": 12845056,
19
+ "merge_size": 2,
20
+ "min_pixels": 3136,
21
+ "n_fft": 400,
22
+ "n_samples": 4800000,
23
+ "nb_max_frames": 30000,
24
+ "padding_side": "right",
25
+ "padding_value": 0.0,
26
+ "patch_size": 14,
27
+ "processor_class": "Qwen2_5OmniProcessor",
28
+ "return_attention_mask": true,
29
+ "sampling_rate": 16000,
30
+ "temporal_patch_size": 2
31
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|AUDIO|>",
6
+ "<|audio_bos|>",
7
+ "<|audio_eos|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_bos|>",
12
+ "<|vision_eos|>",
13
+ "<|vision_pad|>",
14
+ "<|IMAGE|>",
15
+ "<|VIDEO|>"
16
+ ],
17
+ "audio_bos_token": "<|audio_bos|>",
18
+ "audio_eos_token": "<|audio_eos|>",
19
+ "audio_token": "<|AUDIO|>",
20
+ "eos_token": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "image_token": "<|IMAGE|>",
28
+ "pad_token": {
29
+ "content": "<|endoftext|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ },
35
+ "video_token": "<|VIDEO|>",
36
+ "vision_bos_token": "<|vision_bos|>",
37
+ "vision_eos_token": "<|vision_eos|>"
38
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:541d0ff4e17e316b359ba1e11f13c7c0f9ed92c6f435d004465b6f0c743684a1
3
+ size 11422052
tokenizer_config.json ADDED
@@ -0,0 +1,230 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "151646": {
29
+ "content": "<|AUDIO|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "151647": {
37
+ "content": "<|audio_bos|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "151648": {
45
+ "content": "<|audio_eos|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "151649": {
53
+ "content": "<|box_end|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "151650": {
61
+ "content": "<|quad_start|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "151651": {
69
+ "content": "<|quad_end|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "151652": {
77
+ "content": "<|vision_bos|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "151653": {
85
+ "content": "<|vision_eos|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "151654": {
93
+ "content": "<|vision_pad|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "151655": {
101
+ "content": "<|IMAGE|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "151656": {
109
+ "content": "<|VIDEO|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "151657": {
117
+ "content": "<tool_call>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "151658": {
125
+ "content": "</tool_call>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "151659": {
133
+ "content": "<|fim_prefix|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "151660": {
141
+ "content": "<|fim_middle|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "151661": {
149
+ "content": "<|fim_suffix|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "151662": {
157
+ "content": "<|fim_pad|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "151663": {
165
+ "content": "<|repo_name|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "151664": {
173
+ "content": "<|file_sep|>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "151665": {
181
+ "content": "<emb>",
182
+ "lstrip": false,
183
+ "normalized": true,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ }
188
+ },
189
+ "additional_special_tokens": [
190
+ "<|im_start|>",
191
+ "<|im_end|>",
192
+ "<|AUDIO|>",
193
+ "<|audio_bos|>",
194
+ "<|audio_eos|>",
195
+ "<|box_end|>",
196
+ "<|quad_start|>",
197
+ "<|quad_end|>",
198
+ "<|vision_bos|>",
199
+ "<|vision_eos|>",
200
+ "<|vision_pad|>",
201
+ "<|IMAGE|>",
202
+ "<|VIDEO|>"
203
+ ],
204
+ "audio_bos_token": "<|audio_bos|>",
205
+ "audio_eos_token": "<|audio_eos|>",
206
+ "audio_token": "<|AUDIO|>",
207
+ "bos_token": null,
208
+ "clean_up_tokenization_spaces": false,
209
+ "eos_token": "<|im_end|>",
210
+ "errors": "replace",
211
+ "extra_special_tokens": {
212
+ "audio_bos_token": "<|audio_bos|>",
213
+ "audio_eos_token": "<|audio_eos|>",
214
+ "audio_token": "<|AUDIO|>",
215
+ "image_token": "<|IMAGE|>",
216
+ "video_token": "<|VIDEO|>",
217
+ "vision_bos_token": "<|vision_bos|>",
218
+ "vision_eos_token": "<|vision_eos|>"
219
+ },
220
+ "image_token": "<|IMAGE|>",
221
+ "model_max_length": 32768,
222
+ "pad_token": "<|endoftext|>",
223
+ "processor_class": "Qwen2_5OmniProcessor",
224
+ "split_special_tokens": false,
225
+ "tokenizer_class": "Qwen2Tokenizer",
226
+ "unk_token": null,
227
+ "video_token": "<|VIDEO|>",
228
+ "vision_bos_token": "<|vision_bos|>",
229
+ "vision_eos_token": "<|vision_eos|>"
230
+ }
video_preprocessor_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 300,
3
+ "crop_size": null,
4
+ "data_format": "channels_first",
5
+ "default_to_square": true,
6
+ "device": null,
7
+ "dither": 0.0,
8
+ "do_center_crop": null,
9
+ "do_convert_rgb": true,
10
+ "do_normalize": true,
11
+ "do_rescale": true,
12
+ "do_resize": true,
13
+ "do_sample_frames": false,
14
+ "feature_extractor_type": "WhisperFeatureExtractor",
15
+ "feature_size": 128,
16
+ "fps": null,
17
+ "hop_length": 160,
18
+ "image_mean": [
19
+ 0.48145466,
20
+ 0.4578275,
21
+ 0.40821073
22
+ ],
23
+ "image_std": [
24
+ 0.26862954,
25
+ 0.26130258,
26
+ 0.27577711
27
+ ],
28
+ "input_data_format": null,
29
+ "max_frames": 768,
30
+ "max_pixels": 12845056,
31
+ "merge_size": 2,
32
+ "min_frames": 4,
33
+ "min_pixels": 3136,
34
+ "n_fft": 400,
35
+ "n_samples": 4800000,
36
+ "nb_max_frames": 30000,
37
+ "num_frames": null,
38
+ "pad_size": null,
39
+ "padding_side": "right",
40
+ "padding_value": 0.0,
41
+ "patch_size": 14,
42
+ "processor_class": "Qwen2_5OmniProcessor",
43
+ "resample": 3,
44
+ "rescale_factor": 0.00392156862745098,
45
+ "return_attention_mask": true,
46
+ "return_metadata": false,
47
+ "sampling_rate": 16000,
48
+ "size": {
49
+ "longest_edge": 12845056,
50
+ "shortest_edge": 3136
51
+ },
52
+ "temporal_patch_size": 2,
53
+ "video_metadata": null,
54
+ "video_processor_type": "Qwen2VLVideoProcessor"
55
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff