Spaces:
Sleeping
Sleeping
Update Dockerfile
Browse files- Dockerfile +3 -18
Dockerfile
CHANGED
|
@@ -1,21 +1,6 @@
|
|
| 1 |
-
FROM
|
| 2 |
|
| 3 |
-
#
|
| 4 |
-
RUN apt-get update && apt-get install -y --no-install-recommends \
|
| 5 |
-
build-essential \
|
| 6 |
-
cmake \
|
| 7 |
-
git \
|
| 8 |
-
curl \
|
| 9 |
-
ca-certificates \
|
| 10 |
-
&& rm -rf /var/lib/apt/lists/*
|
| 11 |
-
|
| 12 |
-
# (Optional but good) upgrade pip
|
| 13 |
-
RUN pip install --no-cache-dir --upgrade pip
|
| 14 |
-
|
| 15 |
-
# Install llama-cpp-python server (will compile)
|
| 16 |
-
RUN pip install --no-cache-dir "llama-cpp-python[server]"
|
| 17 |
-
|
| 18 |
-
# Download a small CPU-friendly model (GGUF)
|
| 19 |
RUN mkdir -p /models && \
|
| 20 |
curl -L -o /models/tinyllama.gguf \
|
| 21 |
https://huggingface.co/TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF/resolve/main/tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf
|
|
@@ -23,4 +8,4 @@ RUN mkdir -p /models && \
|
|
| 23 |
ENV PORT=7860
|
| 24 |
EXPOSE 7860
|
| 25 |
|
| 26 |
-
CMD ["
|
|
|
|
| 1 |
+
FROM ghcr.io/ggerganov/llama.cpp:server
|
| 2 |
|
| 3 |
+
# Download small GGUF model
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
RUN mkdir -p /models && \
|
| 5 |
curl -L -o /models/tinyllama.gguf \
|
| 6 |
https://huggingface.co/TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF/resolve/main/tinyllama-1.1b-chat-v1.0.Q4_K_M.gguf
|
|
|
|
| 8 |
ENV PORT=7860
|
| 9 |
EXPOSE 7860
|
| 10 |
|
| 11 |
+
CMD ["--model","/models/tinyllama.gguf","--host","0.0.0.0","--port","7860"]
|