README.md

metadata

license: apache-2.0
language:
  - zh
  - en
base_model:
  - Qwen/Qwen2-7B-Instruct
  - meta-llama/Llama-3.1-8B-Instruct
pipeline_tag: text-generation

Training procedure

• total_batch_size: 32
• epoch: 3
• lr: 1.0e-4
• warm-up rate: 0.1
• type: Lora

Framework versions

• LLaMA-Factory: v0.9.0

Paper

• link: arxiv.org/abs/2412.04905

Data

• link: https://github.com/MozerWang/DEMO