Llama-3-8B ORPOtuned on Intel/orca_dpo_pairs dataset
Further Testing Needed
- Developed by: cookinai
- License: apache-2.0
- Finetuned from model : unsloth/llama-3-8b-bnb-4bit
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
- Downloads last month
- 639