MikeDolg commited on
Commit
f660a2b
Β·
verified Β·
1 Parent(s): 5c90ba6

Name the folders <task>/surya-<date>, rename the license file

Browse files
Files changed (50) hide show
  1. MODEL_LICENSE β†’ DATALAB_MODEL_LICENSE +0 -0
  2. README.md +16 -14
  3. layout/{2025_09_23 β†’ surya-2025_09_23}/.gitattributes +0 -0
  4. layout/{2025_09_23 β†’ surya-2025_09_23}/README.md +0 -0
  5. layout/{2025_09_23 β†’ surya-2025_09_23}/config.json +0 -0
  6. layout/{2025_09_23 β†’ surya-2025_09_23}/manifest.json +0 -0
  7. layout/{2025_09_23 β†’ surya-2025_09_23}/model.safetensors +0 -0
  8. layout/{2025_09_23 β†’ surya-2025_09_23}/preprocessor_config.json +0 -0
  9. layout/{2025_09_23 β†’ surya-2025_09_23}/processor_config.json +0 -0
  10. layout/{2025_09_23 β†’ surya-2025_09_23}/special_tokens_map.json +0 -0
  11. layout/{2025_09_23 β†’ surya-2025_09_23}/specials.json +0 -0
  12. layout/{2025_09_23 β†’ surya-2025_09_23}/specials_dict.json +0 -0
  13. layout/{2025_09_23 β†’ surya-2025_09_23}/tokenizer_config.json +0 -0
  14. layout/{2025_09_23 β†’ surya-2025_09_23}/training_args.bin +0 -0
  15. layout/{2025_09_23 β†’ surya-2025_09_23}/vocab_math.json +0 -0
  16. ocr_error_detection/{2025_02_18 β†’ surya-2025_02_18}/.gitattributes +0 -0
  17. ocr_error_detection/{2025_02_18 β†’ surya-2025_02_18}/README.md +0 -0
  18. ocr_error_detection/{2025_02_18 β†’ surya-2025_02_18}/config.json +0 -0
  19. ocr_error_detection/{2025_02_18 β†’ surya-2025_02_18}/manifest.json +0 -0
  20. ocr_error_detection/{2025_02_18 β†’ surya-2025_02_18}/model.safetensors +0 -0
  21. ocr_error_detection/{2025_02_18 β†’ surya-2025_02_18}/special_tokens_map.json +0 -0
  22. ocr_error_detection/{2025_02_18 β†’ surya-2025_02_18}/tokenizer.json +0 -0
  23. ocr_error_detection/{2025_02_18 β†’ surya-2025_02_18}/tokenizer_config.json +0 -0
  24. ocr_error_detection/{2025_02_18 β†’ surya-2025_02_18}/vocab.txt +0 -0
  25. table_recognition/{2025_02_18 β†’ surya-2025_02_18}/.gitattributes +0 -0
  26. table_recognition/{2025_02_18 β†’ surya-2025_02_18}/README.md +0 -0
  27. table_recognition/{2025_02_18 β†’ surya-2025_02_18}/config.json +0 -0
  28. table_recognition/{2025_02_18 β†’ surya-2025_02_18}/manifest.json +0 -0
  29. table_recognition/{2025_02_18 β†’ surya-2025_02_18}/model.safetensors +0 -0
  30. table_recognition/{2025_02_18 β†’ surya-2025_02_18}/preprocessor_config.json +0 -0
  31. text_detection/{2025_05_07 β†’ surya-2025_05_07}/.gitattributes +0 -0
  32. text_detection/{2025_05_07 β†’ surya-2025_05_07}/README.md +0 -0
  33. text_detection/{2025_05_07 β†’ surya-2025_05_07}/config.json +0 -0
  34. text_detection/{2025_05_07 β†’ surya-2025_05_07}/manifest.json +0 -0
  35. text_detection/{2025_05_07 β†’ surya-2025_05_07}/model.safetensors +0 -0
  36. text_detection/{2025_05_07 β†’ surya-2025_05_07}/preprocessor_config.json +0 -0
  37. text_detection/{2025_05_07 β†’ surya-2025_05_07}/training_args.bin +0 -0
  38. text_recognition/{2025_09_23 β†’ surya-2025_09_23}/.gitattributes +0 -0
  39. text_recognition/{2025_09_23 β†’ surya-2025_09_23}/README.md +0 -0
  40. text_recognition/{2025_09_23 β†’ surya-2025_09_23}/config.json +0 -0
  41. text_recognition/{2025_09_23 β†’ surya-2025_09_23}/manifest.json +0 -0
  42. text_recognition/{2025_09_23 β†’ surya-2025_09_23}/model.safetensors +0 -0
  43. text_recognition/{2025_09_23 β†’ surya-2025_09_23}/preprocessor_config.json +0 -0
  44. text_recognition/{2025_09_23 β†’ surya-2025_09_23}/processor_config.json +0 -0
  45. text_recognition/{2025_09_23 β†’ surya-2025_09_23}/special_tokens_map.json +0 -0
  46. text_recognition/{2025_09_23 β†’ surya-2025_09_23}/specials.json +0 -0
  47. text_recognition/{2025_09_23 β†’ surya-2025_09_23}/specials_dict.json +0 -0
  48. text_recognition/{2025_09_23 β†’ surya-2025_09_23}/tokenizer_config.json +0 -0
  49. text_recognition/{2025_09_23 β†’ surya-2025_09_23}/training_args.bin +0 -0
  50. text_recognition/{2025_09_23 β†’ surya-2025_09_23}/vocab_math.json +0 -0
MODEL_LICENSE β†’ DATALAB_MODEL_LICENSE RENAMED
File without changes
README.md CHANGED
@@ -27,26 +27,28 @@ at the tag `v0.17.1`.
27
 
28
  | Folder | Task | Size |
29
  | --- | --- | ---: |
30
- | `layout/2025_09_23` | page layout | 1.4 GB |
31
- | `text_recognition/2025_09_23` | text recognition (OCR) | 1.4 GB |
32
- | `ocr_error_detection/2025_02_18` | detection of a bad text layer | 271 MB |
33
- | `table_recognition/2025_02_18` | table structure | 211 MB |
34
- | `text_detection/2025_05_07` | text line detection | 77 MB |
35
 
36
  ## Changes
37
 
38
  The files are not changed. Each folder holds the same bytes as the original
39
  checkpoint, and `manifest.json` lists the files of the checkpoint. The layout
40
- `<name>/<date>/` is the same as in the cache of `surya`.
 
41
 
42
  ## License
43
 
44
  The weights are under the AI Pubs Open RAIL-M License (Modified) of Datalab.
45
- [`MODEL_LICENSE`](MODEL_LICENSE) holds the full text. It is the file of the
46
- same name in surya `v0.17.1`, without changes. The GPL-3.0-or-later license
47
- of the raw2md code does not apply to these files.
48
 
49
- You receive the files under `MODEL_LICENSE`, and these terms apply to you:
 
50
 
51
  - Section 8 applies the same license to all copies and derivatives of the
52
  model, and to the output.
@@ -55,7 +57,7 @@ You receive the files under `MODEL_LICENSE`, and these terms apply to you:
55
  - A use outside Attachment A needs a commercial license from Datalab:
56
  <https://www.datalab.to/>.
57
 
58
- Attachment A of `MODEL_LICENSE`, quoted in full:
59
 
60
  ```text
61
  Attachment A
@@ -71,10 +73,10 @@ As conditions to the Licenses set forth in this Agreement, You agree not to use,
71
  Commercial and broader use licenses may be available from Licensor at the following URL: https://www.datalab.to/
72
  ```
73
 
74
- The `README.md` files in `ocr_error_detection/2025_02_18` and
75
- `table_recognition/2025_02_18` come from the original checkpoints. Their
76
  metadata names `cc-by-nc-sa-4.0`. The surya repository at `v0.17.1` states
77
- that its model weights use the license in `MODEL_LICENSE`.
78
 
79
  ## Credits
80
 
 
27
 
28
  | Folder | Task | Size |
29
  | --- | --- | ---: |
30
+ | `layout/surya-2025_09_23` | page layout | 1.4 GB |
31
+ | `text_recognition/surya-2025_09_23` | text recognition (OCR) | 1.4 GB |
32
+ | `ocr_error_detection/surya-2025_02_18` | detection of a bad text layer | 271 MB |
33
+ | `table_recognition/surya-2025_02_18` | table structure | 211 MB |
34
+ | `text_detection/surya-2025_05_07` | text line detection | 77 MB |
35
 
36
  ## Changes
37
 
38
  The files are not changed. Each folder holds the same bytes as the original
39
  checkpoint, and `manifest.json` lists the files of the checkpoint. The layout
40
+ `<task>/<source>-<date>/` names the task, the source of the model, and the
41
+ date of the checkpoint.
42
 
43
  ## License
44
 
45
  The weights are under the AI Pubs Open RAIL-M License (Modified) of Datalab.
46
+ [`DATALAB_MODEL_LICENSE`](DATALAB_MODEL_LICENSE) holds the full text. It is
47
+ the file `MODEL_LICENSE` in surya `v0.17.1`, without changes. The
48
+ GPL-3.0-or-later license of the raw2md code does not apply to these files.
49
 
50
+ You receive the files under `DATALAB_MODEL_LICENSE`, and these terms apply
51
+ to you:
52
 
53
  - Section 8 applies the same license to all copies and derivatives of the
54
  model, and to the output.
 
57
  - A use outside Attachment A needs a commercial license from Datalab:
58
  <https://www.datalab.to/>.
59
 
60
+ Attachment A of `DATALAB_MODEL_LICENSE`, quoted in full:
61
 
62
  ```text
63
  Attachment A
 
73
  Commercial and broader use licenses may be available from Licensor at the following URL: https://www.datalab.to/
74
  ```
75
 
76
+ The `README.md` files in `ocr_error_detection/surya-2025_02_18` and
77
+ `table_recognition/surya-2025_02_18` come from the original checkpoints. Their
78
  metadata names `cc-by-nc-sa-4.0`. The surya repository at `v0.17.1` states
79
+ that its model weights use the license in `DATALAB_MODEL_LICENSE`.
80
 
81
  ## Credits
82
 
layout/{2025_09_23 β†’ surya-2025_09_23}/.gitattributes RENAMED
File without changes
layout/{2025_09_23 β†’ surya-2025_09_23}/README.md RENAMED
File without changes
layout/{2025_09_23 β†’ surya-2025_09_23}/config.json RENAMED
File without changes
layout/{2025_09_23 β†’ surya-2025_09_23}/manifest.json RENAMED
File without changes
layout/{2025_09_23 β†’ surya-2025_09_23}/model.safetensors RENAMED
File without changes
layout/{2025_09_23 β†’ surya-2025_09_23}/preprocessor_config.json RENAMED
File without changes
layout/{2025_09_23 β†’ surya-2025_09_23}/processor_config.json RENAMED
File without changes
layout/{2025_09_23 β†’ surya-2025_09_23}/special_tokens_map.json RENAMED
File without changes
layout/{2025_09_23 β†’ surya-2025_09_23}/specials.json RENAMED
File without changes
layout/{2025_09_23 β†’ surya-2025_09_23}/specials_dict.json RENAMED
File without changes
layout/{2025_09_23 β†’ surya-2025_09_23}/tokenizer_config.json RENAMED
File without changes
layout/{2025_09_23 β†’ surya-2025_09_23}/training_args.bin RENAMED
File without changes
layout/{2025_09_23 β†’ surya-2025_09_23}/vocab_math.json RENAMED
File without changes
ocr_error_detection/{2025_02_18 β†’ surya-2025_02_18}/.gitattributes RENAMED
File without changes
ocr_error_detection/{2025_02_18 β†’ surya-2025_02_18}/README.md RENAMED
File without changes
ocr_error_detection/{2025_02_18 β†’ surya-2025_02_18}/config.json RENAMED
File without changes
ocr_error_detection/{2025_02_18 β†’ surya-2025_02_18}/manifest.json RENAMED
File without changes
ocr_error_detection/{2025_02_18 β†’ surya-2025_02_18}/model.safetensors RENAMED
File without changes
ocr_error_detection/{2025_02_18 β†’ surya-2025_02_18}/special_tokens_map.json RENAMED
File without changes
ocr_error_detection/{2025_02_18 β†’ surya-2025_02_18}/tokenizer.json RENAMED
File without changes
ocr_error_detection/{2025_02_18 β†’ surya-2025_02_18}/tokenizer_config.json RENAMED
File without changes
ocr_error_detection/{2025_02_18 β†’ surya-2025_02_18}/vocab.txt RENAMED
File without changes
table_recognition/{2025_02_18 β†’ surya-2025_02_18}/.gitattributes RENAMED
File without changes
table_recognition/{2025_02_18 β†’ surya-2025_02_18}/README.md RENAMED
File without changes
table_recognition/{2025_02_18 β†’ surya-2025_02_18}/config.json RENAMED
File without changes
table_recognition/{2025_02_18 β†’ surya-2025_02_18}/manifest.json RENAMED
File without changes
table_recognition/{2025_02_18 β†’ surya-2025_02_18}/model.safetensors RENAMED
File without changes
table_recognition/{2025_02_18 β†’ surya-2025_02_18}/preprocessor_config.json RENAMED
File without changes
text_detection/{2025_05_07 β†’ surya-2025_05_07}/.gitattributes RENAMED
File without changes
text_detection/{2025_05_07 β†’ surya-2025_05_07}/README.md RENAMED
File without changes
text_detection/{2025_05_07 β†’ surya-2025_05_07}/config.json RENAMED
File without changes
text_detection/{2025_05_07 β†’ surya-2025_05_07}/manifest.json RENAMED
File without changes
text_detection/{2025_05_07 β†’ surya-2025_05_07}/model.safetensors RENAMED
File without changes
text_detection/{2025_05_07 β†’ surya-2025_05_07}/preprocessor_config.json RENAMED
File without changes
text_detection/{2025_05_07 β†’ surya-2025_05_07}/training_args.bin RENAMED
File without changes
text_recognition/{2025_09_23 β†’ surya-2025_09_23}/.gitattributes RENAMED
File without changes
text_recognition/{2025_09_23 β†’ surya-2025_09_23}/README.md RENAMED
File without changes
text_recognition/{2025_09_23 β†’ surya-2025_09_23}/config.json RENAMED
File without changes
text_recognition/{2025_09_23 β†’ surya-2025_09_23}/manifest.json RENAMED
File without changes
text_recognition/{2025_09_23 β†’ surya-2025_09_23}/model.safetensors RENAMED
File without changes
text_recognition/{2025_09_23 β†’ surya-2025_09_23}/preprocessor_config.json RENAMED
File without changes
text_recognition/{2025_09_23 β†’ surya-2025_09_23}/processor_config.json RENAMED
File without changes
text_recognition/{2025_09_23 β†’ surya-2025_09_23}/special_tokens_map.json RENAMED
File without changes
text_recognition/{2025_09_23 β†’ surya-2025_09_23}/specials.json RENAMED
File without changes
text_recognition/{2025_09_23 β†’ surya-2025_09_23}/specials_dict.json RENAMED
File without changes
text_recognition/{2025_09_23 β†’ surya-2025_09_23}/tokenizer_config.json RENAMED
File without changes
text_recognition/{2025_09_23 β†’ surya-2025_09_23}/training_args.bin RENAMED
File without changes
text_recognition/{2025_09_23 β†’ surya-2025_09_23}/vocab_math.json RENAMED
File without changes