feat: simplified mon tokenizer in hf format, updated tags
Browse files- .gitattributes +1 -35
- .gitignore +1 -0
- README.md +2 -1
- convert_to_hf.py +2 -1
.gitattributes
CHANGED
|
@@ -1,35 +1 @@
|
|
| 1 |
-
|
| 2 |
-
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
-
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
-
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
-
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
-
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
-
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
-
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
-
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
-
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
-
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
-
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
-
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
-
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
-
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
-
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
-
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
-
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
-
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
-
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
-
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
-
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
-
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
-
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
-
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
-
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
-
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
-
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
-
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
-
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
-
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
-
*.xz 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
|
|
|
|
| 1 |
+
mon_tokenizer.model filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
.gitignore
CHANGED
|
@@ -8,3 +8,4 @@ wheels/
|
|
| 8 |
|
| 9 |
# Virtual environments
|
| 10 |
.venv
|
|
|
|
|
|
| 8 |
|
| 9 |
# Virtual environments
|
| 10 |
.venv
|
| 11 |
+
.env
|
README.md
CHANGED
|
@@ -1,11 +1,12 @@
|
|
| 1 |
---
|
| 2 |
language:
|
| 3 |
-
-
|
| 4 |
library_name: transformers
|
| 5 |
license: mit
|
| 6 |
tags:
|
| 7 |
- tokenizer
|
| 8 |
- mon
|
|
|
|
| 9 |
- myanmar
|
| 10 |
- sentencepiece
|
| 11 |
---
|
|
|
|
| 1 |
---
|
| 2 |
language:
|
| 3 |
+
- mnw
|
| 4 |
library_name: transformers
|
| 5 |
license: mit
|
| 6 |
tags:
|
| 7 |
- tokenizer
|
| 8 |
- mon
|
| 9 |
+
- mnw
|
| 10 |
- myanmar
|
| 11 |
- sentencepiece
|
| 12 |
---
|
convert_to_hf.py
CHANGED
|
@@ -134,12 +134,13 @@ def create_readme(analysis: Dict[str, Any], metadata: Dict[str, Any]) -> str:
|
|
| 134 |
"""create readme model card"""
|
| 135 |
return f"""---
|
| 136 |
language:
|
| 137 |
-
-
|
| 138 |
library_name: transformers
|
| 139 |
license: mit
|
| 140 |
tags:
|
| 141 |
- tokenizer
|
| 142 |
- mon
|
|
|
|
| 143 |
- myanmar
|
| 144 |
- sentencepiece
|
| 145 |
---
|
|
|
|
| 134 |
"""create readme model card"""
|
| 135 |
return f"""---
|
| 136 |
language:
|
| 137 |
+
- mnw
|
| 138 |
library_name: transformers
|
| 139 |
license: mit
|
| 140 |
tags:
|
| 141 |
- tokenizer
|
| 142 |
- mon
|
| 143 |
+
- mnw
|
| 144 |
- myanmar
|
| 145 |
- sentencepiece
|
| 146 |
---
|