base_model, tags, license, language
base_model tags license language
TR_SFT/checkpoint-12500
text-generation-inference
transformers
unsloth
qwen3
trl
dpo
apache-2.0
en

Uploaded model

  • Developed by: Ba2han
  • License: apache-2.0
  • Finetuned from model : TR_SFT/checkpoint-12500

This qwen3 model was trained 2x faster with Unsloth

Description
Model synced from source: Ba2han/tr-dpo-test
Readme 990 KiB