README.md

metadata

license: apache-2.0

MimicLlama : Finetuned Llama for generating human-like responses

In this repo, we present a Mimic_open_llama_3b is a fine-tuned version of the Open LLaMA 3B model, specifically optimized for producing human-like responses. By leveraging advanced fine-tuning techniques, this model is designed to provide natural, engaging, and contextually relevant interactions across a variety of tasks.

We have Finetuned the OpenLlama 3b by Geng, Xinyang and Liu, Hao : https://github.com/openlm-research/open_llama