Edit model card

Model Card for Model ID

Model Details

Fine tuned version of Llama3 8B. 4 bit quantized with Bits and Bytes. Fine tuned for 1 epoch for 58 hours on an Nvidia a5000.

Model Description

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

  • Developed by: Michael Svendsen
  • Finetuned from model [Llama3-8b]:
Downloads last month
435
Safetensors
Model size
8.03B params
Tensor type
FP16
·

Dataset used to train thesven/thesven-OrpoLlama-3-8B-bnb-4bit