Deploying Open Source AI LLM's with oobabooga using CPU only with Docker.
1.1K
Full example: https://fossengineer.com/Generative-AI-LLMs-locally-with-cpu/
Download the desired model:
wget -P ./text-generation-webui/models https://huggingface.co/eachadea/ggml-vicuna-7b-1.1/resolve/main/ggml-vic7b-uncensored-q5_1.bin
#https://huggingface.co/WizardLM/WizardCoder-15B-V1.0/tree/main
#https://huggingface.co/TheBloke/WizardCoder-15B-1.0-GPTQ
#https://huggingface.co/TheBloke/Llama-2-13B-Chat-fp16
and execute:
#conda init bash
#conda activate textgen
#python ./text-generation-webui/server.py --listen
Deploy with docker:
version: '3'
services:
genai_text:
image: fossengineer/oobabooga_cpu
container_name: genai_ooba
ports:
- "7860:7860"
working_dir: /app
command: tail -f /dev/null #keep it running
volumes:
- appdata_ooba:/app
# - C:/Path/to/Models/AI/Docker_Vol:/app/text-generation-webui/models
volumes:
appdata_ooba:
Content type
Image
Digest
sha256:659528922…
Size
1.8 GB
Last updated
about 3 years ago
docker pull fossengineer/oobabooga_cpu