init

Dockerfile

@@ -0,0 +1,23 @@
+# Hugging Face TGI image
+FROM ghcr.io/huggingface/text-generation-inference:3.0.2
+
+# Set working directory
+WORKDIR /app
+
+# Create the /data directory inside the container
+RUN mkdir -p /data
+RUN chmod 777 /data
+RUN mkdir -p /.cache
+RUN chmod 777 /.cache
+RUN mkdir -p /.triton
+RUN chmod 777 /.triton
+
+# Expose the model on port 8080
+EXPOSE 8080
+
+# Set the Hugging Face token as an environment variable
+ARG HF_TOKEN
+ENV HF_TOKEN=${HF_TOKEN}
+
+# Run the TGI server directly
+CMD ["--model-id", "allenai/OLMo-2-1124-7B-Instruct", "--port", "8080"]

README.md

@@ -4,6 +4,7 @@ emoji: 👀
 colorFrom: green
 colorTo: red
 sdk: docker
+app_port: 8080
 pinned: false
 short_description: TGI deployment of OLMo2
 ---