jsk0214/Seagull-llama-3-8B-orpo-v0.5
112
Uploaded model
- Developed by: kuotient
- License: apache-2.0
- Finetuned from model : kuotient/Meta-Llama-3-8B
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.