arco-reflection-v4

27 downloads 1 likes on Hugging Face updated

Model card

Uploaded model

  • Developed by: appvoid
  • License: apache-2.0
  • Finetuned from model : h2oai/h2o-danube3-500m-base

super experimental, better use the arco-reflection if you dont get good results

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