Thinik_Orpo_v2.0 / README.md
J-LAB's picture
Trained with Unsloth
edc5fb7 verified
metadata
base_model: unsloth/qwen2.5-3b-bnb-4bit
language:
  - en
license: apache-2.0
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - qwen2
  - trl
  - orpo

Uploaded model

  • Developed by: J-LAB
  • License: apache-2.0
  • Finetuned from model : unsloth/qwen2.5-3b-bnb-4bit

This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.