GLM-4.7-Flash-Chat / Dockerfile
gefdsv's picture
Update Dockerfile
7faf1af verified
raw
history blame contribute delete
446 Bytes
FROM ghcr.io/ggml-org/llama.cpp:full
RUN apt update && apt install wget -y
RUN wget "https://huggingface.co/unsloth/GLM-4.7-Flash-REAP-23B-A3B-GGUF/resolve/main/GLM-4.7-Flash-REAP-23B-A3B-Q2_K.gguf" -O /model.gguf
CMD ["--server", "-m", "/model.gguf", "--port", "7860", "--host", "0.0.0.0", "-n", "768", "--no-mmap", "--jinja", "--temp", "1.0", "--top-p", "0.95", "--top-k", "64", "--reasoning-budget", "0", "--reasoning", "off", "-c", "4096"]