9.61 GB

5 contributors

UPDATE: Complete Tamil tokenizer with 291 characters (was 286) - Full Unicode coverage including all vowels, consonants, uyirmei combinations, Grantha characters, digits, and symbols

1d5977d verified 26 days ago

.gitattributes
1.52 kB

initial commit 10 months ago
Cangjie5_TC.json
1.92 MB

Upload 3 files 6 months ago
README.md
5.7 kB

Update README.md 6 months ago
conds.pt
107 kB
xet

Upload conds.pt with huggingface_hub 10 months ago
grapheme_mtl_accurate_tamil.json
7.36 kB

UPDATE: Complete Tamil tokenizer with 291 characters (was 286) - Full Unicode coverage including all vowels, consonants, uyirmei combinations, Grantha characters, digits, and symbols 26 days ago
grapheme_mtl_merged_expanded_v1.json
70 kB

Multilingual v2 update 5 months ago
mtl_tokenizer.json
68.1 kB

Upload 3 files 6 months ago
s3gen.pt
1.06 GB
xet

Upload folder using huggingface_hub 10 months ago
s3gen.safetensors
1.06 GB
xet

Upload s3gen.safetensors with huggingface_hub 9 months ago
t3_23lang.safetensors
2.14 GB
xet

Upload 3 files 6 months ago
t3_cfg.pt
1.06 GB
xet

Upload t3_cfg.pt with huggingface_hub 9 months ago
t3_cfg.safetensors
2.13 GB
xet

Upload t3_cfg.safetensors with huggingface_hub 9 months ago
t3_mtl23ls_v2.safetensors
2.14 GB
xet

Multilingual v2 update 5 months ago
tokenizer.json
25.5 kB

Upload folder using huggingface_hub 10 months ago
ve.pt
5.7 MB
xet

Upload folder using huggingface_hub 10 months ago
ve.safetensors
5.7 MB
xet

Upload ve.safetensors with huggingface_hub 9 months ago