Run models manually

  # Prepare the models into the `model` directory
mkdir models

# copy your models to it
cp your-model.gguf models/

# run the LocalAI container
docker run -p 8080:8080 -v $PWD/models:/models -ti --rm quay.io/go-skynet/local-ai:latest --models-path /models --context-size 700 --threads 4
# You should see:
# 
# ┌───────────────────────────────────────────────────┐
# │                   Fiber v2.42.0                   │
# │               http://127.0.0.1:8080               │
# │       (bound on host 0.0.0.0 and port 8080)       │
# │                                                   │
# │ Handlers ............. 1  Processes ........... 1 │
# │ Prefork ....... Disabled  PID ................. 1 │
# └───────────────────────────────────────────────────┘

# Try the endpoint with curl
curl http://localhost:8080/v1/completions -H "Content-Type: application/json" -d '{
     "model": "your-model.gguf",
     "prompt": "A long time ago in a galaxy far, far away",
     "temperature": 0.7
   }'
  

  mkdir models

# Download luna-ai-llama2 to models/
wget https://huggingface.co/TheBloke/Luna-AI-Llama2-Uncensored-GGUF/resolve/main/luna-ai-llama2-uncensored.Q4_0.gguf -O models/luna-ai-llama2

# Use a template from the examples
cp -rf prompt-templates/getting_started.tmpl models/luna-ai-llama2.tmpl

docker run -p 8080:8080 -v $PWD/models:/models -ti --rm quay.io/go-skynet/local-ai:latest --models-path /models --context-size 700 --threads 4

# Now API is accessible at localhost:8080
curl http://localhost:8080/v1/models
# {"object":"list","data":[{"id":"luna-ai-llama2","object":"model"}]}

curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{
     "model": "luna-ai-llama2",
     "messages": [{"role": "user", "content": "How are you?"}],
     "temperature": 0.9
   }'
# {"model":"luna-ai-llama2","choices":[{"message":{"role":"assistant","content":"I'm doing well, thanks. How about you?"}}]}