AlphaHitchhiker-7B-v2

Finetuned for 2 epochs instead of 1. This improved loss by roughly 15%

• Developed by: macadeliccc
• License: apache-2.0
• Finetuned from model : mlabonne/AlphaMonarch-7B

This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.