metadata

tags:
  - llama
  - vicuna
  - text-generation-inference

complete model with delta patch applied

No unnecessary changes
Same format
No quantization

Setup

# Install FastChat
pip3 install fschat

# Install the latest main branch of huggingface/transformers
pip3 install git+https://github.com/huggingface/transformers

Usage

python3 -m fastchat.serve.cli --model-name eachadea/vicuna-13b

See more at https://github.com/lm-sys/FastChat