Spaces:
Sleeping
Sleeping
Merge remote-tracking branch 'origin/main'
Browse files- Dockerfile +11 -6
Dockerfile
CHANGED
@@ -1,17 +1,22 @@
|
|
1 |
# Read the doc: https://huggingface.co/docs/hub/spaces-sdks-docker
|
2 |
# you will also find guides on how best to write your Dockerfile
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
|
4 |
-
|
5 |
-
|
6 |
RUN useradd -m -u 1000 user
|
7 |
USER user
|
8 |
ENV PATH="/home/user/.local/bin:$PATH"
|
9 |
|
10 |
-
WORKDIR /app
|
11 |
-
|
12 |
COPY --chown=user ./requirements.txt requirements.txt
|
13 |
RUN pip install --no-cache-dir --upgrade -r requirements.txt
|
14 |
-
RUN pip install llama-cpp-python --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu
|
15 |
|
16 |
COPY --chown=user . /app
|
17 |
-
|
|
|
|
1 |
# Read the doc: https://huggingface.co/docs/hub/spaces-sdks-docker
|
2 |
# you will also find guides on how best to write your Dockerfile
|
3 |
+
FROM ghcr.io/ggerganov/llama.cpp:server
|
4 |
+
ENV LLAMA_ARG_MODEL_URL=https://huggingface.co/Vikhrmodels/Vikhr-Qwen-2.5-1.5B-Instruct-GGUF/resolve/main/Vikhr-Qwen-2.5-1.5b-Instruct-Q8_0.gguf \
|
5 |
+
LLAMA_ARG_CTX_SIZE=4096 \
|
6 |
+
LLAMA_ARG_N_PARALLEL=2 \
|
7 |
+
LLAMA_ARG_ENDPOINT_METRICS=1 \
|
8 |
+
LLAMA_ARG_PORT=8080
|
9 |
+
RUN ./llama-server --host 0.0.0.0
|
10 |
|
11 |
+
WORKDIR /app
|
12 |
+
FROM python:3.11-slim as builder
|
13 |
RUN useradd -m -u 1000 user
|
14 |
USER user
|
15 |
ENV PATH="/home/user/.local/bin:$PATH"
|
16 |
|
|
|
|
|
17 |
COPY --chown=user ./requirements.txt requirements.txt
|
18 |
RUN pip install --no-cache-dir --upgrade -r requirements.txt
|
|
|
19 |
|
20 |
COPY --chown=user . /app
|
21 |
+
|
22 |
+
CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]
|