Hugging Face's logo

nkkbr
/
ViCA2-init

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
1
nkkbr commited on
Commit
e6712e6
·
1 Parent(s): 31ece29

Initial commit

Browse files
Files changed (16) hide show
  1. added_tokens.json +6 -0
  2. config.json +202 -0
  3. generation_config.json +6 -0
  4. merges.txt +0 -0
  5. model-00001-of-00007.safetensors +3 -0
  6. model-00002-of-00007.safetensors +3 -0
  7. model-00003-of-00007.safetensors +3 -0
  8. model-00004-of-00007.safetensors +3 -0
  9. model-00005-of-00007.safetensors +3 -0
  10. model-00006-of-00007.safetensors +3 -0
  11. model-00007-of-00007.safetensors +3 -0
  12. model.safetensors.index.json +0 -0
  13. special_tokens_map.json +20 -0
  14. tokenizer.json +0 -0
  15. tokenizer_config.json +53 -0
  16. 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 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Vica-7B-Qwen2",
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
+ "force_sample": true,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 3584,
14
+ "image_aspect_ratio": "anyres_max_9",
15
+ "image_crop_resolution": null,
16
+ "image_grid_pinpoints": [
17
+ [
18
+ 384,
19
+ 384
20
+ ],
21
+ [
22
+ 384,
23
+ 768
24
+ ],
25
+ [
26
+ 384,
27
+ 1152
28
+ ],
29
+ [
30
+ 384,
31
+ 1536
32
+ ],
33
+ [
34
+ 384,
35
+ 1920
36
+ ],
37
+ [
38
+ 384,
39
+ 2304
40
+ ],
41
+ [
42
+ 768,
43
+ 384
44
+ ],
45
+ [
46
+ 768,
47
+ 768
48
+ ],
49
+ [
50
+ 768,
51
+ 1152
52
+ ],
53
+ [
54
+ 768,
55
+ 1536
56
+ ],
57
+ [
58
+ 768,
59
+ 1920
60
+ ],
61
+ [
62
+ 768,
63
+ 2304
64
+ ],
65
+ [
66
+ 1152,
67
+ 384
68
+ ],
69
+ [
70
+ 1152,
71
+ 768
72
+ ],
73
+ [
74
+ 1152,
75
+ 1152
76
+ ],
77
+ [
78
+ 1152,
79
+ 1536
80
+ ],
81
+ [
82
+ 1152,
83
+ 1920
84
+ ],
85
+ [
86
+ 1152,
87
+ 2304
88
+ ],
89
+ [
90
+ 1536,
91
+ 384
92
+ ],
93
+ [
94
+ 1536,
95
+ 768
96
+ ],
97
+ [
98
+ 1536,
99
+ 1152
100
+ ],
101
+ [
102
+ 1536,
103
+ 1536
104
+ ],
105
+ [
106
+ 1536,
107
+ 1920
108
+ ],
109
+ [
110
+ 1536,
111
+ 2304
112
+ ],
113
+ [
114
+ 1920,
115
+ 384
116
+ ],
117
+ [
118
+ 1920,
119
+ 768
120
+ ],
121
+ [
122
+ 1920,
123
+ 1152
124
+ ],
125
+ [
126
+ 1920,
127
+ 1536
128
+ ],
129
+ [
130
+ 1920,
131
+ 1920
132
+ ],
133
+ [
134
+ 1920,
135
+ 2304
136
+ ],
137
+ [
138
+ 2304,
139
+ 384
140
+ ],
141
+ [
142
+ 2304,
143
+ 768
144
+ ],
145
+ [
146
+ 2304,
147
+ 1152
148
+ ],
149
+ [
150
+ 2304,
151
+ 1536
152
+ ],
153
+ [
154
+ 2304,
155
+ 1920
156
+ ],
157
+ [
158
+ 2304,
159
+ 2304
160
+ ]
161
+ ],
162
+ "image_split_resolution": null,
163
+ "image_token_index": 151646,
164
+ "initializer_range": 0.02,
165
+ "intermediate_size": 18944,
166
+ "max_position_embeddings": 32768,
167
+ "max_window_layers": 28,
168
+ "mm_hidden_size": 1152,
169
+ "mm_newline_position": "grid",
170
+ "mm_patch_merge_type": "spatial_unpad",
171
+ "mm_projector_lr": null,
172
+ "mm_projector_type": "mlp2x_gelu",
173
+ "mm_resampler_type": null,
174
+ "mm_spatial_pool_mode": "bilinear",
175
+ "mm_tunable_parts": "mm_vision_tower,mm_mlp_adapter,mm_language_model",
176
+ "mm_use_im_patch_token": false,
177
+ "mm_use_im_start_end": false,
178
+ "mm_vision_select_feature": "patch",
179
+ "mm_vision_select_layer": -2,
180
+ "mm_vision_tower": "google/siglip-so400m-patch14-384",
181
+ "mm_vision_tower_lr": 2e-06,
182
+ "model_type": "vica_qwen",
183
+ "num_attention_heads": 28,
184
+ "num_hidden_layers": 28,
185
+ "num_key_value_heads": 4,
186
+ "pos_skipping_range": 4096,
187
+ "rms_norm_eps": 1e-06,
188
+ "rope_scaling": null,
189
+ "rope_theta": 1000000.0,
190
+ "sliding_window": 131072,
191
+ "tie_word_embeddings": false,
192
+ "tokenizer_model_max_length": 32768,
193
+ "tokenizer_padding_side": "right",
194
+ "torch_dtype": "float32",
195
+ "transformers_version": "4.40.0",
196
+ "use_cache": true,
197
+ "use_mm_proj": true,
198
+ "use_pos_skipping": false,
199
+ "use_sliding_window": false,
200
+ "vision_tower_pretrained": null,
201
+ "vocab_size": 151647
202
+ }
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"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5380e31907c543aabc341e0047bef7d046fcc295cb8c4f212d99469e8f515c5e
3
+ size 4970723528
model-00002-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09425aadf6299f136b36bffe0d06027a8374f9d9843f3a593474adf2eab48bb8
3
+ size 4778622352
model-00003-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65bcc47bc075a68f43267673e1120e186242027ed8e5854b776a38c6e6cd8225
3
+ size 4932743960
model-00004-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50d624c0d3bb9d888db3da23618ac61760bd86d7f38e5931d7eb2c0ff4b22838
3
+ size 4932743992
model-00005-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:782675bb85539c99ba6cea28d3f104273c0d8bc59edfcc3ffaddd7aefa25719e
3
+ size 4998852296
model-00006-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84d912e15f456fbc2d0f2328c6acfe37688be9ebb697c43a51e9ae1e983d462b
3
+ size 4990223056
model-00007-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cdc23b7e9cf89292ccd4cf3c41e18434bd98bb3729629655d0ee45955f36d58
3
+ size 2844629680
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
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff