KS150
testDPO
Based on Qwen/Qwen3-4B-Instruct-2507
Tags
- safetensors
- qwen3
- dpo
- unsloth
- qwen
- alignment
- conversational
- en
- dataset:u-10bei/dpo-dataset-qwen-cot
- base_model:Qwen/Qwen3-4B-Instruct-2507
- base_model:finetune:Qwen/Qwen3-4B-Instruct-2507
- license:apache-2.0
Languages
en
- Author
- KS150
- Task
- text-generation
- Library
- transformers
- Architecture
- qwen3
- License
- apache-2.0
- Base model
- Qwen/Qwen3-4B-Instruct-2507
- Downloads
- 8
- Likes
- 0
