ai4bharat
/

Cadence

Token Classification

cadence-punctuation

cadence_punctuation

punctuation-restoration

indic-languages

Model card Files Files and versions

4.03 GB

2 contributors

History: 35 commits

psidharth567's picture

Updated config. Removed "use_cache": true and also "cache_implementation". They were interfering in some versions of transformers.

015d942 verified 3 months ago

.gitattributes

1.57 kB

Upload model 4 months ago
README.md

7.3 kB

Updated the docs of the python package as we now officially support passing attn_implementation too. (#11) 4 months ago
arxiv_logo.svg

874 Bytes

Upload arxiv_logo.svg (#8) 4 months ago
config.json

2.24 kB

Updated config. Removed "use_cache": true and also "cache_implementation". They were interfering in some versions of transformers. 3 months ago
generation_config.json

168 Bytes

Upload model 4 months ago
model.safetensors

4 GB
xet

Upload model 4 months ago
modeling_gemma3_punctuation.py

10.1 kB

Completely overhauled the attention implementation. Using the existing Gemma-3 attention implementation rather than custom monkey-patched implementation. (#10) 4 months ago
special_tokens_map.json

802 Bytes

Upload model 4 months ago
tokenizer.json

33.4 MB
xet

Upload model 4 months ago
tokenizer_config.json

1.16 MB

Upload model 4 months ago