metadata
library_name: peft
datasets:
- timdettmers/openassistant-guanaco
pipeline_tag: conversational
base_model: internlm/internlm2-chat-7b
Model
internlm2-chat-7b-qlora-oasst1 is fine-tuned from InternLM2-Chat-7B with openassistant-guanaco dataset by XTuner.
Quickstart
Usage with XTuner CLI
Installation
pip install xtuner
Chat
xtuner chat internlm/internlm2-chat-7b --adapter xtuner/internlm2-chat-7b-qlora-oasst1 --prompt-template internlm2_chat
Fine-tune
Use the following command to quickly reproduce the fine-tuning results.
xtuner train internlm2_chat_7b_qlora_oasst1_e3