gpt / start.sh
Xlnk's picture
Update start.sh
9777610 verified
#!/bin/bash
/app/llama.cpp/build/bin/llama-server \
--model /models/model.gguf \
--host 0.0.0.0 \
--port 7860 \
--fit off \
--threads $(nproc) \
--mlock \
--no-mmap \