v0.2.0

- запуск unicorn заменен на llama-server

Dockerfile

@@ -6,17 +6,17 @@ ENV LLAMA_ARG_MODEL_URL=https://huggingface.co/Vikhrmodels/Vikhr-Qwen-2.5-1.5B-I
     LLAMA_ARG_N_PARALLEL=2 \
     LLAMA_ARG_ENDPOINT_METRICS=1 \
     LLAMA_ARG_PORT=8080
-#RUN ./llama-server -mu https://huggingface.co/Vikhrmodels/Vikhr-Qwen-2.5-1.5B-Instruct-GGUF/resolve/main/Vikhr-Qwen-2.5-1.5b-Instruct-Q8_0.gguf -c 2048 --port 7860 --host 0.0.0.0
+RUN ./llama-server --host 0.0.0.0
 
-FROM python:3.9
+WORKDIR /app
+FROM python:3.11-slim as builder
 RUN useradd -m -u 1000 user
 USER user
 ENV PATH="/home/user/.local/bin:$PATH"
-WORKDIR /app
 
 COPY --chown=user ./requirements.txt requirements.txt
 RUN pip install --no-cache-dir --upgrade -r requirements.txt
 
 COPY --chown=user . /app
 
-CMD ["llama-server", "-mu", "https://huggingface.co/Vikhrmodels/Vikhr-Qwen-2.5-1.5B-Instruct-GGUF/resolve/main/Vikhr-Qwen-2.5-1.5b-Instruct-Q8_0.gguf", "--host", "0.0.0.0", "--port", "7860"]
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]