v0.0.5

Simplified image, updated log outputs

v0.0.4

Fixed issue with model worker arguments

v0.0.3

You can now include CLI arguments to adjust the FastChat model_worker settings.

Also added environment variables that can be used to enable/disable the web server and OpenAI API endpoint.

v0.0.2

Allow the model to be specified via the docker run command.

docker run -d \
    --device /dev/dri \
    -v ~/ai/apps:/apps \
    -v ~/ai/deps:/deps \
    -v ~/ai/huggingface:/root/.cache/huggingface \
    -p 7860:7860 \
    -p 21001:21001 \
    -p 21002:21002 \
    -p 8000:8000 \
    itlackey/ipex-arc-fastchat:latest codellama/CodeLlama-7b-Instruct-hf

v0.0.1

WIP