Downloads · 30 days
189
16% of all-time downloads
jfiekdjdk/vicuna-13B-1.1-Chinese-GPTQ-4bit-128g
vicuna-13B-1.1-Chinese-GPTQ-4bit-128g is a text generation model from jfiekdjdk. Use it when you need the model to write or continue text. It is set up for transformers.
This model was obtained from following repo: uukuguy/vicuna-13b-v1.1 ziqingyang/chinese-alpaca-lora-13b
Downloads · 30 days
189
16% of all-time downloads
All-time downloads
1.2K
Public
Repo size
7.8 GB
Likes
18
Public
Click a slice to open those files.
.safetensors7.8 GB · 100%
From the Hugging Face model README
This model was obtained from following repo:
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
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
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.
70K conversations collected from ShareGPT.com.
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.