Spaces:
Sleeping
Sleeping
Update Dockerfile
Browse files- Dockerfile +23 -1
Dockerfile
CHANGED
@@ -1,8 +1,30 @@
|
|
1 |
FROM python:3.10-slim
|
2 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
WORKDIR /app
|
|
|
|
|
4 |
COPY requirements.txt .
|
5 |
-
RUN pip install --no-cache-dir -r requirements.txt
|
6 |
|
|
|
|
|
|
|
|
|
|
|
7 |
COPY . .
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]
|
|
|
1 |
FROM python:3.10-slim
|
2 |
|
3 |
+
# Install system dependencies for llama.cpp
|
4 |
+
RUN apt-get update && apt-get install -y --no-install-recommends \
|
5 |
+
build-essential \
|
6 |
+
cmake \
|
7 |
+
git \
|
8 |
+
&& rm -rf /var/lib/apt/lists/*
|
9 |
+
|
10 |
WORKDIR /app
|
11 |
+
|
12 |
+
# Copy requirement list first for caching
|
13 |
COPY requirements.txt .
|
|
|
14 |
|
15 |
+
# Install Python dependencies (llama-cpp-python compiled with BLAS disabled for HF CPU Spaces)
|
16 |
+
RUN CMAKE_ARGS="-DLLAMA_BLAS=OFF -DLLAMA_CUBLAS=OFF" \
|
17 |
+
pip install --no-cache-dir -r requirements.txt
|
18 |
+
|
19 |
+
# Copy app files
|
20 |
COPY . .
|
21 |
+
|
22 |
+
# Pre-download model at build time to speed up startup
|
23 |
+
RUN python -c "from huggingface_hub import hf_hub_download; \
|
24 |
+
hf_hub_download(repo_id='bartowski/Llama-3.2-3B-Instruct-GGUF', \
|
25 |
+
filename='Llama-3.2-3B-Instruct-Q4_K_M.gguf', \
|
26 |
+
cache_dir='/app/models', local_dir_use_symlinks=False)"
|
27 |
+
|
28 |
+
EXPOSE 7860
|
29 |
+
|
30 |
CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]
|