nlg_dapt_study: upload trained model (private)

f63cc77 verified 20 days ago

513 Bytes

language:
  - ml
library_name: transformers
pipeline_tag: summarization
tags:
  - malayalam
  - dapt

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.