kanashi6 commited on
Commit
cc14fcd
·
verified ·
1 Parent(s): b254b9f

Upload 11 files

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
README.md CHANGED
@@ -1,3 +1,21 @@
1
- ---
2
- license: apache-2.0
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ datasets:
4
+ - BLIP3o/BLIP3o-Pretrain-Long-Caption
5
+ - BLIP3o/BLIP3o-Pretrain-Short-Caption
6
+ - BLIP3o/BLIP3o-Pretrain-JourneyDB
7
+ - UCSC-VLAA/GPT-Image-Edit-1.5M
8
+ - BLIP3o/BLIP3o-60k
9
+ - FreedomIntelligence/ShareGPT-4o-Image
10
+ base_model:
11
+ - OpenGVLab/InternVL3-2B
12
+ ---
13
+ This repository contains the model (3B version) presented in the paper UniLiP: Adapting CLIP for Unified Multimodal Understanding, Generation and Editing.
14
+
15
+ UniLIP proposes a unified, CLIP-based encoder featuring both rich semantics and fine-grained image details. Through a **two-stage and self-distillation training** for reconstruction, we empower CLIP to achieve excellent reconstruction results **without compromising its original understanding abilities**. Leveraging this powerful unified representation, UniLIP excels across understanding, generation, and editing tasks.
16
+
17
+ For more details, please refer to the original paper and the GitHub repository:
18
+
19
+ Paper: https://www.arxiv.org/abs/2507.23278
20
+
21
+ GitHub: https://github.com/nnnth/UniLIP
added_tokens.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</box>": 151673,
3
+ "</img>": 151666,
4
+ "</quad>": 151669,
5
+ "</ref>": 151671,
6
+ "</tool_call>": 151658,
7
+ "<IMG_CONTEXT>": 151667,
8
+ "<box>": 151672,
9
+ "<image>": 151677,
10
+ "<img>": 151665,
11
+ "<quad>": 151668,
12
+ "<ref>": 151670,
13
+ "<tool_call>": 151657,
14
+ "<video>": 151674,
15
+ "<|box_end|>": 151649,
16
+ "<|box_start|>": 151648,
17
+ "<|endoftext|>": 151643,
18
+ "<|file_sep|>": 151664,
19
+ "<|fim_middle|>": 151660,
20
+ "<|fim_pad|>": 151662,
21
+ "<|fim_prefix|>": 151659,
22
+ "<|fim_suffix|>": 151661,
23
+ "<|im_end|>": 151645,
24
+ "<|im_start|>": 151644,
25
+ "<|image_pad|>": 151655,
26
+ "<|object_ref_end|>": 151647,
27
+ "<|object_ref_start|>": 151646,
28
+ "<|quad_end|>": 151651,
29
+ "<|quad_start|>": 151650,
30
+ "<|repo_name|>": 151663,
31
+ "<|video_pad|>": 151656,
32
+ "<|vision_end|>": 151653,
33
+ "<|vision_pad|>": 151654,
34
+ "<|vision_start|>": 151652,
35
+ "[/IMG]": 151676,
36
+ "[IMG]": 151675
37
+ }
chat_template.jinja ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {% for message in messages %}{{'<|im_start|>' + message['role'] + '
2
+ '}}{% if message['content'] is string %}{{ message['content'] }}{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' %}{{ '<IMG_CONTEXT>
3
+ ' }}{% elif content['type'] == 'video' %}{{ '<video>
4
+ ' }}{% elif content['type'] == 'text' %}{{ content['text'] }}{% endif %}{% endfor %}{% endif %}{{'<|im_end|>
5
+ '}}{% endfor %}{% if add_generation_prompt %}{{'<|im_start|>assistant
6
+ ' }}{% endif %}
config.json ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "UniLIP_InternVLForCausalLM"
4
+ ],
5
+ "mllm_path":"OpenGVLab/InternVL3-2B",
6
+ "mllm_hf_path":"OpenGVLab/InternVL3-2B-hf",
7
+ "dit_path":"Efficient-Large-Model/Sana_1600M_512px_diffusers",
8
+ "vae_path":"mit-han-lab/dc-ae-f32c32-sana-1.1-diffusers",
9
+ "connect_layer": 6,
10
+ "downsample_ratio": 0.5,
11
+ "freeze_mm_mlp_adapter": false,
12
+ "gen_pooling": "early_pool2d_4",
13
+ "gen_vision_tower": "eva-clip-E-14-plus",
14
+ "image_aspect_ratio": "square",
15
+ "image_seq_length": 256,
16
+ "image_token_id": 151667,
17
+ "mm_patch_merge_type": "flat",
18
+ "mm_projector_lr": null,
19
+ "mm_projector_type": "mlp2x_gelu",
20
+ "mm_use_im_patch_token": false,
21
+ "mm_use_im_start_end": false,
22
+ "mm_vision_select_feature": "patch",
23
+ "mm_vision_select_layer": -2,
24
+ "model_type": "unilip_internvl",
25
+ "n_query": 256,
26
+ "pad_token_id": 151643,
27
+ "projector_hidden_act": "gelu",
28
+ "text_config": {
29
+ "architectures": [
30
+ "Qwen2ForCausalLM"
31
+ ],
32
+ "attention_dropout": 0.0,
33
+ "bos_token_id": 151643,
34
+ "eos_token_id": 151645,
35
+ "hidden_act": "silu",
36
+ "hidden_size": 1536,
37
+ "initializer_range": 0.02,
38
+ "intermediate_size": 8960,
39
+ "max_position_embeddings": 32768,
40
+ "max_window_layers": 70,
41
+ "model_type": "qwen2",
42
+ "num_attention_heads": 12,
43
+ "num_hidden_layers": 28,
44
+ "num_key_value_heads": 2,
45
+ "rms_norm_eps": 1e-06,
46
+ "rope_scaling": {
47
+ "factor": 2.0,
48
+ "rope_type": "dynamic",
49
+ "type": "dynamic"
50
+ },
51
+ "rope_theta": 1000000.0,
52
+ "sliding_window": null,
53
+ "torch_dtype": "bfloat16",
54
+ "use_cache": true,
55
+ "use_sliding_window": false,
56
+ "vocab_size": 151678
57
+ },
58
+ "tokenizer_model_max_length": 1024,
59
+ "tokenizer_padding_side": "right",
60
+ "torch_dtype": "bfloat16",
61
+ "transformers_version": "4.52.1",
62
+ "tune_mm_mlp_adapter": false,
63
+ "use_cache": false,
64
+ "use_mm_proj": true,
65
+ "vision_config": {
66
+ "architectures": [
67
+ "InternVisionModel"
68
+ ],
69
+ "attention_bias": true,
70
+ "attention_dropout": 0.0,
71
+ "dropout": 0.0,
72
+ "hidden_act": "gelu",
73
+ "hidden_dropout_prob": 0.0,
74
+ "hidden_size": 1024,
75
+ "image_size": [
76
+ 448,
77
+ 448
78
+ ],
79
+ "initializer_factor": 0.1,
80
+ "initializer_range": 1e-10,
81
+ "intermediate_size": 4096,
82
+ "layer_norm_eps": 1e-06,
83
+ "layer_scale_init_value": 0.1,
84
+ "model_type": "internvl_vision",
85
+ "norm_type": "layer_norm",
86
+ "num_attention_heads": 16,
87
+ "num_channels": 3,
88
+ "num_hidden_layers": 24,
89
+ "patch_size": [
90
+ 14,
91
+ 14
92
+ ],
93
+ "projection_dropout": 0.0,
94
+ "torch_dtype": "bfloat16",
95
+ "use_absolute_position_embeddings": true,
96
+ "use_mask_token": false,
97
+ "use_mean_pooling": true,
98
+ "use_qk_norm": false
99
+ },
100
+ "vision_feature_layer": -1,
101
+ "vision_feature_select_strategy": "default",
102
+ "vision_tower_pretrained": null
103
+ }
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": "4.52.1"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
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 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "[IMG]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "[/IMG]",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<image>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ ],
25
+ "context_image_token": "<IMG_CONTEXT>",
26
+ "end_image_token": "</img>",
27
+ "eos_token": {
28
+ "content": "<|im_end|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ },
34
+ "pad_token": {
35
+ "content": "<|endoftext|>",
36
+ "lstrip": false,
37
+ "normalized": false,
38
+ "rstrip": false,
39
+ "single_word": false
40
+ },
41
+ "start_image_token": "<img>",
42
+ "video_token": "<video>"
43
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e614f95d72d49154810ce2c9e87ad5d3e92a73f5eb2fed5688f4650034a8f81d
3
+ size 11424281
tokenizer_config.json ADDED
@@ -0,0 +1,311 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<img>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "151666": {
190
+ "content": "</img>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "151667": {
198
+ "content": "<IMG_CONTEXT>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": true
204
+ },
205
+ "151668": {
206
+ "content": "<quad>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": true
212
+ },
213
+ "151669": {
214
+ "content": "</quad>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "151670": {
222
+ "content": "<ref>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "151671": {
230
+ "content": "</ref>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "151672": {
238
+ "content": "<box>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "151673": {
246
+ "content": "</box>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "151674": {
254
+ "content": "<video>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "151675": {
262
+ "content": "[IMG]",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": true
268
+ },
269
+ "151676": {
270
+ "content": "[/IMG]",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": true
276
+ },
277
+ "151677": {
278
+ "content": "<image>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": true
284
+ }
285
+ },
286
+ "additional_special_tokens": [
287
+ "[IMG]",
288
+ "[/IMG]",
289
+ "<image>"
290
+ ],
291
+ "bos_token": null,
292
+ "clean_up_tokenization_spaces": false,
293
+ "context_image_token": "<IMG_CONTEXT>",
294
+ "end_image_token": "</img>",
295
+ "eos_token": "<|im_end|>",
296
+ "errors": "replace",
297
+ "extra_special_tokens": {
298
+ "context_image_token": "<IMG_CONTEXT>",
299
+ "end_image_token": "</img>",
300
+ "start_image_token": "<img>",
301
+ "video_token": "<video>"
302
+ },
303
+ "model_max_length": 1024,
304
+ "pad_token": "<|endoftext|>",
305
+ "return_token_type_ids": false,
306
+ "split_special_tokens": false,
307
+ "start_image_token": "<img>",
308
+ "tokenizer_class": "Qwen2Tokenizer",
309
+ "unk_token": null,
310
+ "video_token": "<video>"
311
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff