Vicuna 13B V1.1 Chinese

This model was obtained from following repo:

uukuguy/vicuna-13b-v1.1
ziqingyang/chinese-alpaca-lora-13b

Merged using sciprts from: https://github.com/ymcui/Chinese-LLaMA-Alpaca

Then quanized using following command (no act order):

python llama.py ~/Chinese-LLaMA-Alpaca/alpaca-combined-hf c4 \
    --wbits 4 \
    --true-sequential \
    --groupsize 128 \
    --save_safetensors vicuna-13B-1.1-Chinese-GPTQ-4bit-128g.safetensors

Can confirm model output normal text, but question-answering quality is unknown

Vicuna Model Card

Model details

Model type: Vicuna is an open-source chatbot trained by fine-tuning LLaMA on user-shared conversations collected from ShareGPT. It is an auto-regressive language model, based on the transformer architecture.

Model date: Vicuna was trained between March 2023 and April 2023.

Organizations developing the model: The Vicuna team with members from UC Berkeley, CMU, Stanford, and UC San Diego.

Paper or resources for more information: https://vicuna.lmsys.org/

License: Apache License 2.0

Where to send questions or comments about the model: https://github.com/lm-sys/FastChat/issues

Intended use

Primary intended uses: The primary use of Vicuna is research on large language models and chatbots.

Primary intended users: The primary intended users of the model are researchers and hobbyists in natural language processing, machine learning, and artificial intelligence.

Training dataset

70K conversations collected from ShareGPT.com.

Evaluation dataset

A preliminary evaluation of the model quality is conducted by creating a set of 80 diverse questions and utilizing GPT-4 to judge the model outputs. See https://vicuna.lmsys.org/ for more details.