Edit model card

Uploaded model

  • Developed by: ShadNygren
  • License: apache-2.0
  • Finetuned from model: Weyaxi/Einstein-v6.1-LLama3-8B-Instruct-Ties
  • Datasets Used for Fine Tuning:
    • Medilora/us_medical_license_exam_textbooks_en (slightly modifed instruction version)

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

THIS MODEL IS FOR TESTING AND EVALUATION PURPOSES ONLY

Downloads last month
9
Safetensors
Model size
8.03B params
Tensor type
BF16
·

Finetuned from