Downloads · 30 days
339
32% of all-time downloads
TokenBender/Navarna_v0_1_OpenHermes_Hindi
Navarna_v0_1_OpenHermes_Hindi is a text generation model from TokenBender. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
Navarna 7B is an LLM fine-tuned to be good in Hindi chat performance while adding sentence retrieval (RAG) tasks capability.
Downloads · 30 days
339
32% of all-time downloads
All-time downloads
1K
Public
Parameters
7.2B
14.5 GB on disk
Likes
16
Public
Click a slice to open those files.
.safetensors14.5 GB · 100%
From the Hugging Face model README
Navarna 7B is an LLM fine-tuned to be good in Hindi chat performance while adding sentence retrieval (RAG) tasks capability.

Details of process and implementation -
https://docs.google.com/document/d/11gPWDazMLHIAm3kT2FuEZJndocd4B6-kX_fu0jMLukk/edit?usp=sharing
All SFT, DPO and chat inference notebooks are present in the HF repo itself.
