2-dpo_model_tr / README.md
Ba2han's picture
Upload model trained with Unsloth
a56ed65 verified
metadata
base_model: Ba2han/turkish_model-sft
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - llama
  - trl
  - dpo
license: apache-2.0
language:
  - en

Uploaded model

  • Developed by: Ba2han
  • License: apache-2.0
  • Finetuned from model : Ba2han/turkish_model-sft

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