metadata

language:
  - en
license: apache-2.0
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - llama
  - trl
  - sft
base_model: chargoddard/Yi-6B-Llama

An alpaca fine-tune of chargoddard's Llamafied Yi-6B. This works fine, unlike the lobotomized Llama model I tried merging it with.

Uploaded model

Developed by: reallad
License: apache-2.0
Finetuned from model : chargoddard/Yi-6B-Llama

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.