17 lines
482 B
Markdown
17 lines
482 B
Markdown
---
|
|
license: other
|
|
license_name: llama3
|
|
license_link: LICENSE
|
|
language:
|
|
- en
|
|
tags:
|
|
- llama
|
|
- ORPO
|
|
---
|
|
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 🇲🇽 |