Hugging Face's logo

bytedance-research
/
UI-TARS-72B-SFT

Image-Text-to-Text
Transformers
Safetensors
English
qwen2_vl
multimodal
gui
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
2
MingComplex commited on
Commit
d3d6357
·
1 Parent(s): 42d8b96

Add UI-TARS-72B-SFT model

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +16 -0
  3. chat_template.json +3 -0
  4. config.json +52 -0
  5. merges.txt +0 -0
  6. model-00001-of-00064.safetensors +3 -0
  7. model-00002-of-00064.safetensors +3 -0
  8. model-00003-of-00064.safetensors +3 -0
  9. model-00004-of-00064.safetensors +3 -0
  10. model-00005-of-00064.safetensors +3 -0
  11. model-00006-of-00064.safetensors +3 -0
  12. model-00007-of-00064.safetensors +3 -0
  13. model-00008-of-00064.safetensors +3 -0
  14. model-00009-of-00064.safetensors +3 -0
  15. model-00010-of-00064.safetensors +3 -0
  16. model-00011-of-00064.safetensors +3 -0
  17. model-00012-of-00064.safetensors +3 -0
  18. model-00013-of-00064.safetensors +3 -0
  19. model-00014-of-00064.safetensors +3 -0
  20. model-00015-of-00064.safetensors +3 -0
  21. model-00016-of-00064.safetensors +3 -0
  22. model-00017-of-00064.safetensors +3 -0
  23. model-00018-of-00064.safetensors +3 -0
  24. model-00019-of-00064.safetensors +3 -0
  25. model-00020-of-00064.safetensors +3 -0
  26. model-00021-of-00064.safetensors +3 -0
  27. model-00022-of-00064.safetensors +3 -0
  28. model-00023-of-00064.safetensors +3 -0
  29. model-00024-of-00064.safetensors +3 -0
  30. model-00025-of-00064.safetensors +3 -0
  31. model-00026-of-00064.safetensors +3 -0
  32. model-00027-of-00064.safetensors +3 -0
  33. model-00028-of-00064.safetensors +3 -0
  34. model-00029-of-00064.safetensors +3 -0
  35. model-00030-of-00064.safetensors +3 -0
  36. model-00031-of-00064.safetensors +3 -0
  37. model-00032-of-00064.safetensors +3 -0
  38. model-00033-of-00064.safetensors +3 -0
  39. model-00034-of-00064.safetensors +3 -0
  40. model-00035-of-00064.safetensors +3 -0
  41. model-00036-of-00064.safetensors +3 -0
  42. model-00037-of-00064.safetensors +3 -0
  43. model-00038-of-00064.safetensors +3 -0
  44. model-00039-of-00064.safetensors +3 -0
  45. model-00040-of-00064.safetensors +3 -0
  46. model-00041-of-00064.safetensors +3 -0
  47. model-00042-of-00064.safetensors +3 -0
  48. model-00043-of-00064.safetensors +3 -0
  49. model-00044-of-00064.safetensors +3 -0
  50. model-00045-of-00064.safetensors +3 -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 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|box_end|>": 151649,
3
+ "<|box_start|>": 151648,
4
+ "<|endoftext|>": 151643,
5
+ "<|im_end|>": 151645,
6
+ "<|im_start|>": 151644,
7
+ "<|image_pad|>": 151655,
8
+ "<|object_ref_end|>": 151647,
9
+ "<|object_ref_start|>": 151646,
10
+ "<|quad_end|>": 151651,
11
+ "<|quad_start|>": 151650,
12
+ "<|video_pad|>": 151656,
13
+ "<|vision_end|>": 151653,
14
+ "<|vision_pad|>": 151654,
15
+ "<|vision_start|>": 151652
16
+ }
chat_template.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "chat_template": "{% 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\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% 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_start|><|image_pad|><|vision_end|>{% 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_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
3
+ }
config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen2VLForConditionalGeneration"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151645,
8
+ "vision_start_token_id": 151652,
9
+ "vision_end_token_id": 151653,
10
+ "vision_token_id": 151654,
11
+ "image_token_id": 151655,
12
+ "video_token_id": 151656,
13
+ "hidden_act": "silu",
14
+ "hidden_size": 8192,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 29568,
17
+ "max_position_embeddings": 32768,
18
+ "max_window_layers": 80,
19
+ "model_type": "qwen2_vl",
20
+ "num_attention_heads": 64,
21
+ "num_hidden_layers": 80,
22
+ "num_key_value_heads": 8,
23
+ "rms_norm_eps": 1e-06,
24
+ "rope_theta": 1000000.0,
25
+ "sliding_window": 32768,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "bfloat16",
28
+ "transformers_version": "4.41.2",
29
+ "use_cache": true,
30
+ "use_sliding_window": false,
31
+ "vision_config": {
32
+ "depth": 32,
33
+ "embed_dim": 1280,
34
+ "mlp_ratio": 4,
35
+ "num_heads": 16,
36
+ "in_chans": 3,
37
+ "hidden_size": 8192,
38
+ "patch_size": 14,
39
+ "spatial_merge_size": 2,
40
+ "spatial_patch_size": 14,
41
+ "temporal_patch_size": 2
42
+ },
43
+ "rope_scaling": {
44
+ "type": "mrope",
45
+ "mrope_section": [
46
+ 16,
47
+ 24,
48
+ 24
49
+ ]
50
+ },
51
+ "vocab_size": 152064
52
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model-00001-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:703d4d3f358c8b0bc05899db1d1f37da17716e5623eb4f2092184e25c0623769
3
+ size 2797467096
model-00002-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:351c759a2adf84f1f71862eb95a0035adea3f917254bb87a02c5b9dade59c816
3
+ size 4982833288
model-00003-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edfb72fe22af96be8ef7469cd51c77ca6adc1e06e09d1aed013ca03e6ac4cab5
3
+ size 4114761856
model-00004-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:360e2aa860c0d7bb3e46e9ab5a5d14a78161c2010914b1e7d0ae7af3b9245f8d
3
+ size 4479624664
model-00005-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5528ef7152579b83bf9ff58e115cc8623224ced8484fcd2624e25c476692b786
3
+ size 4479624664
model-00006-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02c06f0ca27a6560044a7c1ed6e8b459f9eb1e866f61e3bba2e9581030bf7c61
3
+ size 4815276384
model-00007-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:909f9fa7b542a7664b7a1c597f0ebd793305175925e226df7766a71f61bb8e27
3
+ size 4748060240
model-00008-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11b422c7cc310e5ab2a131510864eabf34c2c43a1e3847624f2b4686eb1b3fd9
3
+ size 4479624664
model-00009-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b8e75719fd746c1d96376fd356b29435914f97670d2be10a032abe4cf704d08
3
+ size 4815276384
model-00010-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f22d2a863ba502e976500b2d72edfb98d5f88b4afa9016aee1f63a01c098a54
3
+ size 4748060256
model-00011-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3d6755862fe9c6e90809e314aafaba0b9bbedd1531d51a61e56633de0ac0617
3
+ size 4479624672
model-00012-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bad159301edc40a56a388d06ec6eb09d6f084781116987d81f5825c930e257b
3
+ size 4815276400
model-00013-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46bb7aa9212b5b38ca1a000f9f02025364fcd5a0a507b2c92d60ba9974ed3fd5
3
+ size 4748060248
model-00014-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d75192fad3038fccb6573fbdc7c0f0d1aff63b87a97c46ea27f3e435c66f4c1
3
+ size 4479624672
model-00015-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:583738b79097178cb48de8330d81c185feb6f60fa14113613c40ee029560bb53
3
+ size 4815276400
model-00016-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd543ab95fdf2d2f72cffabd98acc0dc40caba7734b1d74b983ec04126872081
3
+ size 4748060248
model-00017-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c38a79ef9fcb84b9e5830116532673e6ab7be9343496d7ad636f9e349e40276f
3
+ size 4479624672
model-00018-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44d0d1b00a8684ece60d58747b73673e03ca8895598c828e9bcf6fc57befa88a
3
+ size 4815276400
model-00019-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecd9a7e806e7deb2e526e0a1e573eb0055964eeac80dd7618f0694995915dac6
3
+ size 4748060248
model-00020-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dc51773d57f49f839f6f0840c1812a463bc29dc21acf9a578fd61647ed2c931
3
+ size 4479624672
model-00021-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a398b71ab0143c83374d2fce36ee4330cfe742cd920cad19092551513da1e10f
3
+ size 4815276400
model-00022-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4de007bd50688f431f9108f35dfd0e9051cbb3f43fa401d5fa889859372855e
3
+ size 4748060248
model-00023-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8305765b5be33ec3fc6d93b884921ee5cd36aae90aec72285439c9a2e7e93572
3
+ size 4479624672
model-00024-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab9cfa6626485c4fef47cda03471cb860923d247e61c36f2b2edbf9abf3dc8c7
3
+ size 4815276400
model-00025-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1f99ac457028ce856ec7a7a723693dcebd643d58d10c4a09a00a1b0077650bd
3
+ size 4748060248
model-00026-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8403abd928df21e8676dda4981e204e986a03cfb11d518ef12974baf68b96fa3
3
+ size 4479624672
model-00027-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1938c0be81bb5bfa76d3d64eb3d74228ccc79c21906516e49e5a0e1415362c7d
3
+ size 4815276400
model-00028-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95ec6634a0ea78edd06d4385a91439d62f76591aad11f7c23e4a6ebf34ac56ca
3
+ size 4748060248
model-00029-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90539540020571bbe691502df0453d1919c922274417131fd2f762a6d8d56618
3
+ size 4479624672
model-00030-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc49a3e6fef4c0a74250ca18878bab20fed910eb1776455afc825d55ce74713d
3
+ size 4815276400
model-00031-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64a22853012aa24afc0f981094a7ccd05f834dfc8099bb4933b1d89ee11fdb90
3
+ size 4748060248
model-00032-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64283520957b8bf97b89c590de6a48ffbe4fc82a6a7707c1c4c50835a957530c
3
+ size 4479624672
model-00033-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e7a245fd4c2b76e54dd0771ba9dc42da5d9ff40163a3eea3041bad5fe533364
3
+ size 4815276400
model-00034-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06b535393943951582869c640efa809bf1efd7822bef2cfbde8fe3b6a86a10a4
3
+ size 4748060248
model-00035-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e14e003b6dcaa371b76d4c6cddcedf5a4291cf58debde09f6484c96e26d5f734
3
+ size 4479624672
model-00036-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65a0f72fc071d5dccf31bc3fc48260429c2819f72eb1fb840f453879c7ddaa18
3
+ size 4815276400
model-00037-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9aabc48552d00b1f820758ca6a225589ed34246c6cac85da72ccd8d5104debd9
3
+ size 4748060248
model-00038-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8b054057c33fd5841a09355ea7bd4715dbd24809473ccb35e0ec42795ae4b4d
3
+ size 4479624672
model-00039-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fac8609868e2f02cc8b2bf8b9d62095302b180df58a0694256a595aed70906a
3
+ size 4815276400
model-00040-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9b2f5a2b4b7bfab385897f93b0785ae622cf9ac29ec49b18dc260bc5086fd05
3
+ size 4748060248
model-00041-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c3635aeaf17950b1d1ddd63f0bcd703b095ca585d1ffd452f57497cfa1c0246
3
+ size 4479624672
model-00042-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:653bd7e9942b2b8ef3855f3eee40e59e8dc8b8c0b27b2b748673bdc52a2ad70b
3
+ size 4815276400
model-00043-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:681a363eea4e3ded9d1db3f8ef4d8f4e942714e7870f85ab00f95817e62a8311
3
+ size 4748060248
model-00044-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5b2d368a75f69d65777d1c8e255c661d018ca68450cf89ce5d135cf368e6b2
3
+ size 4479624672
model-00045-of-00064.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10560818dbb95bb68f149e2ad958656b6b3b7d7bcb239eaae981b0630b84f12f
3
+ size 4815276400