A small LLM interface designed for sandboxed clients
- TheBloke GGUF quantized model
- llama.cpp for interface calls
python 3.8+
wget -P models https://huggingface.co/TheBloke/Mistral-7B-v0.1-GGUF/resolve/main/mistral-7b-v0.1.Q4_K_M.gguf
dhern023/sandbox-llm
Folders and files
| Name | Name | Last commit date | ||
|---|---|---|---|---|