update

README.md

@@ -1,21 +1,46 @@
 ---
 library_name: peft
+datasets:
+- tatsu-lab/alpaca
+- silk-road/alpaca-data-gpt4-chinese
+pipeline_tag: conversational
+base_model: internlm/internlm-7b
 ---
-## Training procedure
 
+<div align="center">
+  <img src="https://github.com/InternLM/lmdeploy/assets/36994684/0cf8d00f-e86b-40ba-9b54-dc8f1bc6c8d8" width="600"/>
 
-The following `bitsandbytes` quantization config was used during training:
-- quant_method: bitsandbytes
-- load_in_8bit: False
-- load_in_4bit: True
-- llm_int8_threshold: 6.0
-- llm_int8_skip_modules: None
-- llm_int8_enable_fp32_cpu_offload: False
-- llm_int8_has_fp16_weight: False
-- bnb_4bit_quant_type: nf4
-- bnb_4bit_use_double_quant: True
-- bnb_4bit_compute_dtype: float16
-### Framework versions
 
+[![Generic badge](https://img.shields.io/badge/GitHub-%20XTuner-black.svg)](https://github.com/InternLM/xtuner)
 
-- PEFT 0.5.0
+
+</div>
+
+## Model
+
+internlm-7b-qlora-alpaca-enzh is fine-tuned from [InternLM-7B](https://huggingface.co/internlm/internlm-7b) with [alpaca en](https://huggingface.co/datasets/tatsu-lab/alpaca) / [zh](https://huggingface.co/datasets/silk-road/alpaca-data-gpt4-chinese) datasets by [XTuner](https://github.com/InternLM/xtuner).
+
+
+## Quickstart
+
+### Usage with XTuner CLI
+
+#### Installation
+
+```shell
+pip install xtuner
+```
+
+#### Chat
+
+```shell
+xtuner chat internlm/internlm-7b --adapter xtuner/internlm-7b-qlora-alpaca-enzh --prompt-template internlm_chat --system-template alpaca
+```
+
+#### Fine-tune
+
+Use the following command to quickly reproduce the fine-tuning results.
+
+```shell
+xtuner train internlm_7b_qlora_alpaca_enzh_e3
+```