llama-checkpoint-200-merged

This model is a merged checkpoint created from a LoRA fine-tune of meta-llama/Meta-Llama-3.1-8B-Instruct.

Base Model

• meta-llama/Meta-Llama-3.1-8B-Instruct

Training Data

• HydraIndicLM/hindi_alpaca_dolly_67k
• yahma/alpaca-cleaned

Notes

• This folder contains merged model weights for inference.
• The original training checkpoint was merged with the base model locally.