Stark2008's picture
Update README.md
6bc4ae1 verified
|
raw
history blame
596 Bytes
metadata
license: other
license_name: llama3
license_link: LICENSE
base_model: VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct
language:
  - en
tags:
  - llama
  - ORPO
datasets:
  - reciperesearch/dolphin-sft-v0.1-preference

Barcenas Llama3 8b ORPO

Model trained with the novel new ORPO method, based on the recent Llama 3 8b, specifically: VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct

The model was trained with the dataset: reciperesearch/dolphin-sft-v0.1-preference which uses Dolphin data with GPT 4 to improve its conversation sections.

Made with ❤️ in Guadalupe, Nuevo Leon, Mexico 🇲🇽