metadata
library_name: peft
pipeline_tag: conversational
base_model: internlm/internlm-7b
Model
internlm-7b-qlora-msagent-react is fine-tuned from InternLM-7B with MSAgent-Bench dataset by XTuner.
Quickstart
Usage with XTuner CLI
Installation
pip install xtuner
Chat
xtuner chat internlm/internlm-7b --adapter xtuner/internlm-7b-qlora-msagent-react --lagent
Fine-tune
Use the following command to quickly reproduce the fine-tuning results.
NPROC_PER_NODE=8 xtuner train internlm_7b_qlora_msagent_react_e3_gpu8