Downloads · 30 days
26
30% of all-time downloads
sarvam1-dapt-general
Navneeth017/sarvam1-dapt-general
sarvam1-dapt-general is a summarization model from Navneeth017. Use it when you need a shorter version of a longer text. It is set up for transformers.
sarvam-1 (2.5B) after general-world Malayalam DAPT (causal, 297.05M tokens). Intermediate checkpoint.
All-time downloads
87
Public
Parameters
2.5B
5.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors5.1 GB · 100%
At a glance
- Task
- Summarization
- Library
- transformers
- Model type
- llama
- Access
- Public
- Created
- Jul 17, 2026
- Updated
- Jul 17, 2026
- SHA
- f63cc779
Model card
From the Hugging Face model README
sarvam1-dapt-general
sarvam-1 (2.5B) after general-world Malayalam DAPT (causal, 297.05M tokens). Intermediate checkpoint.
Part of the nlg_dapt_study corpus-controlled DAPT study for Malayalam summarisation. Central finding: documented DAPT (cultural or general-world, 23M–297M tokens) yields no statistically significant downstream gain on either mBART or sarvam-1. Private research artifact.
- Task
- Summarization
- Library
- transformers
- Type
- llama
- Languages
- ml
- Created
- Jul 17, 2026
- Updated
- Jul 17, 2026