llama-qwopus-v2 / Dockerfile
programmersd's picture
Create Dockerfile
0a151b5 verified
raw
history blame contribute delete
272 Bytes
FROM ghcr.io/ggml-org/llama.cpp:server
ENV LLAMA_CACHE=/tmp/llama-cache
ENV HF_HUB_CACHE=/tmp/hf-cache
ENV LLAMA_ARG_WEBUI=1
EXPOSE 7860
CMD ["-hf", "Jackrong/Qwopus3.5-4B-v3-MTP-GGUF:Q4_K_M", "-c", "8192", "--host", "0.0.0.0", "--port", "7860", "--webui", "-ngl", "0"]