LZHgrla's picture
upload adapter
6602c36
metadata
library_name: peft
datasets:
  - timdettmers/openassistant-guanaco
pipeline_tag: conversational
base_model: internlm/internlm-chat-7b

Generic badge

Model

internlm-chat-7b-qlora-oasst1 is fine-tuned from InternLM-Chat-7B with openassistant-guanaco dataset by XTuner.

Quickstart

Usage with XTuner CLI

Installation

pip install xtuner

Chat

xtuner chat internlm/internlm-chat-7b --adapter xtuner/internlm-chat-7b-qlora-oasst1 --prompt-template internlm_chat

Fine-tune

Use the following command to quickly reproduce the fine-tuning results.

xtuner train internlm_chat_7b_qlora_oasst1_e3