Hugging Face's logo

nkkbr
/
ViCA2-stage1-align

Video-Text-to-Text
Transformers
Safetensors
sam2
English
vica_qwen
text-generation
multimodal
vision-language
video understanding
visuospatial cognition
spatial reasoning
vlm
llava
qwen
siglip
hiera
dual-encoder
Model card Files
xet
Community
nkkbr commited on
Commit
b1ee778
·
1 Parent(s): 8a675c1

Initial commit

Browse files
Files changed (15) hide show
  1. added_tokens.json +6 -0
  2. config.json +204 -0
  3. generation_config.json +6 -0
  4. merges.txt +0 -0
  5. model-00001-of-00004.safetensors +3 -0
  6. model-00002-of-00004.safetensors +3 -0
  7. model-00003-of-00004.safetensors +3 -0
  8. model-00004-of-00004.safetensors +3 -0
  9. model.safetensors.index.json +0 -0
  10. special_tokens_map.json +20 -0
  11. tokenizer.json +0 -0
  12. tokenizer_config.json +53 -0
  13. trainer_state.json +0 -0
  14. training_args.bin +3 -0
  15. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "<image>": 151646,
3
+ "<|endoftext|>": 151643,
4
+ "<|im_end|>": 151645,
5
+ "<|im_start|>": 151644
6
+ }
config.json ADDED
@@ -0,0 +1,204 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./vica2_original_checkpoint",
3
+ "add_faster_video": false,
4
+ "add_time_instruction": true,
5
+ "architectures": [
6
+ "VicaQwenForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "bos_token_id": 151643,
10
+ "eos_token_id": 151645,
11
+ "faster_token_stride": 10,
12
+ "force_sample": true,
13
+ "hidden_act": "silu",
14
+ "hidden_size": 3584,
15
+ "image_aspect_ratio": "anyres_max_9",
16
+ "image_crop_resolution": null,
17
+ "image_grid_pinpoints": [
18
+ [
19
+ 384,
20
+ 384
21
+ ],
22
+ [
23
+ 384,
24
+ 768
25
+ ],
26
+ [
27
+ 384,
28
+ 1152
29
+ ],
30
+ [
31
+ 384,
32
+ 1536
33
+ ],
34
+ [
35
+ 384,
36
+ 1920
37
+ ],
38
+ [
39
+ 384,
40
+ 2304
41
+ ],
42
+ [
43
+ 768,
44
+ 384
45
+ ],
46
+ [
47
+ 768,
48
+ 768
49
+ ],
50
+ [
51
+ 768,
52
+ 1152
53
+ ],
54
+ [
55
+ 768,
56
+ 1536
57
+ ],
58
+ [
59
+ 768,
60
+ 1920
61
+ ],
62
+ [
63
+ 768,
64
+ 2304
65
+ ],
66
+ [
67
+ 1152,
68
+ 384
69
+ ],
70
+ [
71
+ 1152,
72
+ 768
73
+ ],
74
+ [
75
+ 1152,
76
+ 1152
77
+ ],
78
+ [
79
+ 1152,
80
+ 1536
81
+ ],
82
+ [
83
+ 1152,
84
+ 1920
85
+ ],
86
+ [
87
+ 1152,
88
+ 2304
89
+ ],
90
+ [
91
+ 1536,
92
+ 384
93
+ ],
94
+ [
95
+ 1536,
96
+ 768
97
+ ],
98
+ [
99
+ 1536,
100
+ 1152
101
+ ],
102
+ [
103
+ 1536,
104
+ 1536
105
+ ],
106
+ [
107
+ 1536,
108
+ 1920
109
+ ],
110
+ [
111
+ 1536,
112
+ 2304
113
+ ],
114
+ [
115
+ 1920,
116
+ 384
117
+ ],
118
+ [
119
+ 1920,
120
+ 768
121
+ ],
122
+ [
123
+ 1920,
124
+ 1152
125
+ ],
126
+ [
127
+ 1920,
128
+ 1536
129
+ ],
130
+ [
131
+ 1920,
132
+ 1920
133
+ ],
134
+ [
135
+ 1920,
136
+ 2304
137
+ ],
138
+ [
139
+ 2304,
140
+ 384
141
+ ],
142
+ [
143
+ 2304,
144
+ 768
145
+ ],
146
+ [
147
+ 2304,
148
+ 1152
149
+ ],
150
+ [
151
+ 2304,
152
+ 1536
153
+ ],
154
+ [
155
+ 2304,
156
+ 1920
157
+ ],
158
+ [
159
+ 2304,
160
+ 2304
161
+ ]
162
+ ],
163
+ "image_split_resolution": null,
164
+ "image_token_index": 151646,
165
+ "initializer_range": 0.02,
166
+ "intermediate_size": 18944,
167
+ "max_position_embeddings": 32768,
168
+ "max_window_layers": 28,
169
+ "mm_hidden_size": 1152,
170
+ "mm_newline_position": "grid",
171
+ "mm_patch_merge_type": "spatial_unpad",
172
+ "mm_projector_lr": null,
173
+ "mm_projector_type": "mlp2x_gelu",
174
+ "mm_resampler_type": null,
175
+ "mm_spatial_pool_mode": "bilinear",
176
+ "mm_spatial_pool_stride": 2,
177
+ "mm_tunable_parts": "sam_projector",
178
+ "mm_use_im_patch_token": false,
179
+ "mm_use_im_start_end": false,
180
+ "mm_vision_select_feature": "patch",
181
+ "mm_vision_select_layer": -2,
182
+ "mm_vision_tower": "google/siglip-so400m-patch14-384",
183
+ "mm_vision_tower_lr": 0.001,
184
+ "model_type": "vica_qwen",
185
+ "num_attention_heads": 28,
186
+ "num_hidden_layers": 28,
187
+ "num_key_value_heads": 4,
188
+ "pos_skipping_range": 4096,
189
+ "rms_norm_eps": 1e-06,
190
+ "rope_scaling": null,
191
+ "rope_theta": 1000000.0,
192
+ "sliding_window": 131072,
193
+ "tie_word_embeddings": false,
194
+ "tokenizer_model_max_length": 32768,
195
+ "tokenizer_padding_side": "right",
196
+ "torch_dtype": "bfloat16",
197
+ "transformers_version": "4.40.0.dev0",
198
+ "use_cache": true,
199
+ "use_mm_proj": true,
200
+ "use_pos_skipping": false,
201
+ "use_sliding_window": false,
202
+ "vision_tower_pretrained": null,
203
+ "vocab_size": 151647
204
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151645,
5
+ "transformers_version": "4.40.0.dev0"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1efd8c79254769240edbace7a71dac88960d10d3a4e808230f4485ad9c81cbe8
3
+ size 4874678976
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc4fadb1419522b41c58d36f46e29d6f0cba5fcb35b74c0d1887692852f3d98b
3
+ size 4932751008
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94aca0e44c71e4640b40cdbadd995a234937168c72c552e0d2d13036ca96cc68
3
+ size 4994571904
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85e17f0ff0851e5f54a92cf903e6d85b9c9dd6690762a876fc73df339fdb8b72
3
+ size 1422340008
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "eos_token": {
7
+ "content": "<|im_end|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ }
20
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<image>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ }
36
+ },
37
+ "additional_special_tokens": [
38
+ "<|im_start|>",
39
+ "<|im_end|>"
40
+ ],
41
+ "bos_token": null,
42
+ "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
43
+ "clean_up_tokenization_spaces": false,
44
+ "eos_token": "<|im_end|>",
45
+ "errors": "replace",
46
+ "model_max_length": 32768,
47
+ "pad_token": "<|endoftext|>",
48
+ "padding_side": "right",
49
+ "processor_class": "LlavaProcessor",
50
+ "split_special_tokens": false,
51
+ "tokenizer_class": "Qwen2Tokenizer",
52
+ "unk_token": null
53
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b8de79f646c11c8bedbf9be871755bbd9bfb1de8203cce6c08343dcf360396a
3
+ size 6840
vocab.json ADDED
The diff for this file is too large to render. See raw diff