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.
- Downloads last month
- 7
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for macadeliccc/AlphaHitchhiker-7B-v2
Base model
mlabonne/Monarch-7B
Finetuned
mlabonne/NeuralMonarch-7B
Finetuned
mlabonne/AlphaMonarch-7B