metadata
library_name: peft
base_model: meta-llama/Meta-Llama-3-8B-Instruct
license: other
datasets:
- argilla/dpo-mix-7k
language:
- en
pipeline_tag: text-generation
tags:
- text-generation
- llama
- orpo
- llama3
- text-generation-inference
A finetuning experiment on llama3 8b it with selected 5k examples from argilla dpo 7k