gaostar commited on
Commit
de54543
·
verified ·
1 Parent(s): 58c9574

Upload DeViL-7B weights

Browse files
.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 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</query>": 151670,
3
+ "</tool_call>": 151658,
4
+ "<image>": 151665,
5
+ "<query>": 151669,
6
+ "<tool_call>": 151657,
7
+ "<|box_end|>": 151649,
8
+ "<|box_start|>": 151648,
9
+ "<|endoftext|>": 151643,
10
+ "<|file_sep|>": 151664,
11
+ "<|fim_middle|>": 151660,
12
+ "<|fim_pad|>": 151662,
13
+ "<|fim_prefix|>": 151659,
14
+ "<|fim_suffix|>": 151661,
15
+ "<|im_end|>": 151645,
16
+ "<|im_start|>": 151644,
17
+ "<|image_pad|>": 151655,
18
+ "<|object_ref_end|>": 151647,
19
+ "<|object_ref_start|>": 151646,
20
+ "<|quad_end|>": 151651,
21
+ "<|quad_start|>": 151650,
22
+ "<|repo_name|>": 151663,
23
+ "<|stream_end|>": 151667,
24
+ "<|stream_start|>": 151666,
25
+ "<|video_pad|>": 151656,
26
+ "<|vision_end|>": 151653,
27
+ "<|vision_pad|>": 151654,
28
+ "<|vision_start|>": 151652,
29
+ "[BOX]": 151668
30
+ }
config.json ADDED
@@ -0,0 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "weights/gdino_vllama_stage2_no_temporal/llm_lo_merge",
3
+ "architectures": [
4
+ "DeViLQwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "configuration_devil.DeViLQwen2Config",
9
+ "AutoModelForCausalLM": "modeling_devil.DeViLQwen2ForCausalLM"
10
+ },
11
+ "bos_token_id": 151643,
12
+ "eos_token_id": 151645,
13
+ "g_dino_lr": 0.0001,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 3584,
16
+ "image_aspect_ratio": "square",
17
+ "image_size": -1,
18
+ "image_token_index": 151665,
19
+ "image_token_length": 1,
20
+ "initializer_range": 0.02,
21
+ "intermediate_size": 18944,
22
+ "is_alignment": false,
23
+ "llm_lr": 1e-05,
24
+ "max_frames": 180,
25
+ "max_position_embeddings": 32768,
26
+ "max_window_layers": 28,
27
+ "mm_hidden_size": 1152,
28
+ "mm_projector_lr": 1e-05,
29
+ "mm_projector_type": "mlp2x_gelu",
30
+ "mm_vision_encoder": "weights/VL3-SigLIP-NaViT",
31
+ "mm_vision_select_feature": "patch",
32
+ "mm_vision_select_layer": -1,
33
+ "model_type": "devil_qwen2",
34
+ "num_attention_heads": 28,
35
+ "num_hidden_layers": 28,
36
+ "num_key_value_heads": 4,
37
+ "query_end_index": 151670,
38
+ "query_start_index": 151669,
39
+ "rms_norm_eps": 1e-06,
40
+ "rope_scaling": null,
41
+ "rope_theta": 1000000.0,
42
+ "sliding_window": null,
43
+ "tbox_index": 151668,
44
+ "tie_word_embeddings": false,
45
+ "tokenizer_model_max_length": 16384,
46
+ "tokenizer_padding_side": "right",
47
+ "torch_dtype": "float16",
48
+ "transformers_version": "4.49.0",
49
+ "use_cache": true,
50
+ "use_flash_loss": false,
51
+ "use_gdino": true,
52
+ "use_mm_proj": true,
53
+ "use_sliding_window": false,
54
+ "use_token_compression": true,
55
+ "vision_encoder": "weights/VL3-SigLIP-NaViT",
56
+ "vision_encoder_config": {
57
+ "_attn_implementation_autoset": false,
58
+ "_name_or_path": "",
59
+ "add_cross_attention": false,
60
+ "architectures": null,
61
+ "attention_dropout": 0.0,
62
+ "bad_words_ids": null,
63
+ "begin_suppress_tokens": null,
64
+ "bos_token_id": null,
65
+ "chunk_size_feed_forward": 0,
66
+ "cross_attention_hidden_size": null,
67
+ "decoder_start_token_id": null,
68
+ "diversity_penalty": 0.0,
69
+ "do_sample": false,
70
+ "early_stopping": false,
71
+ "encoder_no_repeat_ngram_size": 0,
72
+ "eos_token_id": null,
73
+ "exponential_decay_length_penalty": null,
74
+ "finetuning_task": null,
75
+ "forced_bos_token_id": null,
76
+ "forced_eos_token_id": null,
77
+ "hidden_act": "gelu_pytorch_tanh",
78
+ "hidden_size": 1152,
79
+ "id2label": {
80
+ "0": "LABEL_0",
81
+ "1": "LABEL_1"
82
+ },
83
+ "intermediate_size": 4304,
84
+ "is_decoder": false,
85
+ "is_encoder_decoder": false,
86
+ "label2id": {
87
+ "LABEL_0": 0,
88
+ "LABEL_1": 1
89
+ },
90
+ "layer_norm_eps": 1e-06,
91
+ "length_penalty": 1.0,
92
+ "max_length": 20,
93
+ "min_length": 0,
94
+ "model_type": "Devil_vision_encoder",
95
+ "no_repeat_ngram_size": 0,
96
+ "num_attention_heads": 16,
97
+ "num_beam_groups": 1,
98
+ "num_beams": 1,
99
+ "num_channels": 3,
100
+ "num_hidden_layers": 27,
101
+ "num_return_sequences": 1,
102
+ "output_attentions": false,
103
+ "output_hidden_states": false,
104
+ "output_scores": false,
105
+ "pad_token_id": null,
106
+ "patch_size": 14,
107
+ "prefix": null,
108
+ "problem_type": null,
109
+ "pruned_heads": {},
110
+ "remove_invalid_values": false,
111
+ "repetition_penalty": 1.0,
112
+ "return_dict": true,
113
+ "return_dict_in_generate": false,
114
+ "sep_token_id": null,
115
+ "suppress_tokens": null,
116
+ "task_specific_params": null,
117
+ "temperature": 1.0,
118
+ "tf_legacy_loss": false,
119
+ "tie_encoder_decoder": false,
120
+ "tie_word_embeddings": true,
121
+ "tokenizer_class": null,
122
+ "top_k": 50,
123
+ "top_p": 1.0,
124
+ "torch_dtype": null,
125
+ "torchscript": false,
126
+ "typical_p": 1.0,
127
+ "use_bfloat16": false
128
+ },
129
+ "vision_encoder_lr": null,
130
+ "vocab_size": 152064
131
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 151643,
4
+ "eos_token_id": 151645,
5
+ "transformers_version": "4.49.0",
6
+ "use_cache": false
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model-00001-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c86402dc16acd4da781bd562939c17afc4ba275cee10d0fc04a26d95379d7391
3
+ size 4877684182
pytorch_model-00002-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a1def742dfa52e315c792a6f193348d3ad5e39ec7011f4f54584937c39f4a94
3
+ size 4932778600
pytorch_model-00003-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99ec5905a31e676b6dd92394417c2893d9258edc8c1c45da13dbc3a7fa038ebe
3
+ size 4992992444
pytorch_model-00004-of-00004.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fd03635713b95fa3dd0642eb6bc0a4c4d2eb2132e0ba7cb939a4726ec4a2bcf
3
+ size 1538892907
pytorch_model.bin.index.json ADDED
The diff for this file is too large to render. See raw diff
 
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 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62b74665b667243a4aa44e21f941eb439013895c055b4164116392b61ac73caf
3
+ size 11423009
tokenizer_config.json ADDED
@@ -0,0 +1,261 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<image>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "151666": {
190
+ "content": "<|stream_start|>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "151667": {
198
+ "content": "<|stream_end|>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": true
204
+ },
205
+ "151668": {
206
+ "content": "[BOX]",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": true
212
+ },
213
+ "151669": {
214
+ "content": "<query>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "151670": {
222
+ "content": "</query>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ }
229
+ },
230
+ "additional_special_tokens": [
231
+ "<|im_start|>",
232
+ "<|im_end|>",
233
+ "<|object_ref_start|>",
234
+ "<|object_ref_end|>",
235
+ "<|box_start|>",
236
+ "<|box_end|>",
237
+ "<|quad_start|>",
238
+ "<|quad_end|>",
239
+ "<|vision_start|>",
240
+ "<|vision_end|>",
241
+ "<|vision_pad|>",
242
+ "<|image_pad|>",
243
+ "<|video_pad|>"
244
+ ],
245
+ "auto_map": {
246
+ "AutoProcessor": "weights/videollama3_7b_local--processing_videollama3.Videollama3Qwen2Processor"
247
+ },
248
+ "bos_token": null,
249
+ "chat_template": "\n{%- set identifier = 'im' %}\n{% for message in messages %}\n {% if message['role'] == 'stream' %}\n {% set identifier = 'stream' %}\n {% else %}\n {% set identifier = 'im' %}\n {% endif %}\n {{- '<|' + identifier + '_start|>' + message['role'] + '\n' -}}\n {% if message['content'] is string %}\n {{- message['content'] + '<|' + identifier + '_end|>\n' -}}\n {% else %}\n {% for content in message['content'] %}\n {% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}\n {% if 'time' in content %}\n {{- 'Time ' + content['time'] | round(1) | string + 's: ' -}}\n {% endif %}\n\n {{- '<image>\n' -}}\n\n {% elif content['type'] == 'video' or 'video' in content or 'video_url' in content %}\n {% for i in range(content['num_frames']) %}\n {% if 'timestamps' in content %}\n {{- 'Time ' + content['timestamps'][i] | round(1) | string + 's:' -}}\n {% endif %}\n {% if i < content['num_frames'] - 1 %}\n\n {{- '<image>,' -}}\n\n {% else %}\n\n {{- '<image>\n' -}}\n\n {% endif %}\n {% endfor %}\n {% elif content['type'] == 'text' or 'text' in content %}\n {{- content['text'] -}}\n {% endif %}\n {% endfor %}\n {{- '<|' + identifier + '_end|>\n' -}}\n {% endif %}\n{% endfor %}\n{% if add_generation_prompt %}\n {{- '<|im_start|>assistant\n' -}}\n{% endif %}\n",
250
+ "clean_up_tokenization_spaces": false,
251
+ "eos_token": "<|im_end|>",
252
+ "errors": "replace",
253
+ "extra_special_tokens": {},
254
+ "model_max_length": 16384,
255
+ "pad_token": "<|endoftext|>",
256
+ "padding_side": "right",
257
+ "processor_class": "Videollama3Qwen2Processor",
258
+ "split_special_tokens": false,
259
+ "tokenizer_class": "Qwen2Tokenizer",
260
+ "unk_token": null
261
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff