metadata
library_name: peft
base_model: TokenBender/navaran_hindi_merged
Model Card for Model ID
DPO qlora adapter for Navarna, refer to https://huggingface.co/TokenBender/navarna_hindi_merged for SFT qlora merged model.
And final DPO adapter merged model is - https://huggingface.co/TokenBender/navaran_hindi_dpo_merged