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