qwen2_gpro / README.md
chenmingxuan's picture
Update README.md
939853f verified
metadata
base_model: unsloth/qwen2.5-3b-instruct-unsloth-bnb-4bit
tags:
  - text-generation-inference
  - transformers
  - unsloth
  - qwen2
  - gguf
license: apache-2.0
language:
  - en

Uploaded model

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

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

对于qwen来说,对比英文数据使用中文数据训练的会更好

image/png 训练效果:

image/png