noneabove1182/text-gen-ui-gpu repository overview

Recommended to remove any docker volumes between versions

*** THIS IS NOT OFFICIAL *** I'm not associated with oobabooga, if you have any problems with it feel free to message me at https://sh.itjust.works/u/noneabove1182⁠ or open an issue at https://github.com/noneabove1182/text-generation-webui-docker⁠ - do not bother them on their own github/discord first please :)

As of November we're back to release cycle, oobabooga has started releasing snapshots so will release every time there's a new snapshot

** Nvidia only! If you are looking for AMD feel free to message me and I'll throw one together **

Instructions for getting nvidia docker set up: https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html⁠

Runs text-generation-webui hosted on port 7860, and receives command arguments such as --model and --chat

You can also now pass any of the following folders you'd like to store locally: models, loras, prompts, presets, characters, extensions

For more details, please visit the github repo for this image: https://github.com/noneabove1182/text-generation-webui-docker⁠

An example run command (add -d for detached):

docker run --gpus all -p 7860:7860 -v /media/teamgroup/models:/models text-generation-webui-docker:latest --model WizardLM-13B-V1.1-GPTQ --chat --listen --listen-port 7860