Chinese-Vicuna

\| English \| 中文 \| 注意事项/NOTEs

This is the repo for the Chinese-Vicuna project, which aims to build and share an instruction-following Chinese LLaMA model which can run on a single Nvidia RTX-2080TI, that why we named this project Vicuna, small but strong enough !

Why is it called Vicuna：In view of the successful development of alpaca models such as llama, alpaca, guanaco，We want to train a Chinese small alpaca like Vicuna.

The repo contains:

code for finetune the model
code for generation based on trained model
code for run on CPU (fp16 or int4 is support, in purely C++)
tools to download/convert/quantify original facebook llama.ckpt

This is our instruction demo (with beam-size=4, so you will see 4 process output in the meantime):

tmp.mp4

This is our multi-turn instruction demo (with beam-size=4, so you will see 4 process output in the meantime):

tmp.mp4

What‘s New

March 23, 2023：Released checkpoint-4000 with 50w data training
March 23, 2023：Deploy the code for fine-tuning and inferencing in colab
March 23, 2023：Provides code that can be used for inference in pure c++
March 24, 2023：Released checkpoint-8000 for training about 1.5 epochs on belle+guanaco（100w data）
March 26, 2023：Provides a quantitative approach
March 27, 2023：Released checkpoint-final for training 3 epochs on belle+guanaco
March 27, 2023：Added multi-round interactive dialog script with alpaca-lora-serve service
March 28, 2023：Released our model on huggingface
March 29, 2023：Added gradio typewriter-like output with beam search, better user interaction support.
March 29, 2023：Added breakpoint retraining interface to support continued training of other datasets from our checkpoint
March 29, 2023: Released our new 13B-based lora model
March 29, 2023: Add more detailed test samples. performance
April 1, 2023: Add better support for multi-turn chat in chat.py ( Now support 4 generation mode in stream mode/typewriter style: beam search, greedy, sample, beam sample ; We also add cancel button for regeneration )
April 4, 2023: Add performance for 13B, which trains on a single 3090.
April 11, 2023：Released our continuous-finetune on the vertical corpus of Chinese medical quizzes Chinese-Vicuna-medical.Provides examples of vertical corpus training