first commit

Dockerfile

@@ -0,0 +1,20 @@
+# Use the provided base image
+FROM ghcr.io/berriai/litellm:main-latest
+
+# Set the working directory to /app
+WORKDIR /app
+
+# Copy the configuration file into the container at /app
+COPY config.yaml .
+
+# Make sure your entrypoint.sh is executable
+RUN chmod +x entrypoint.sh
+
+# Expose the necessary port
+EXPOSE 4000/tcp
+
+# Override the CMD instruction with your desired command and arguments
+# WARNING: FOR PROD DO NOT USE `--detailed_debug` it slows down response times, instead use the following CMD
+# CMD ["--port", "4000", "--config", "config.yaml"]
+
+CMD ["--port", "4000", "--config", "config.yaml"]

README.md

@@ -5,6 +5,8 @@ colorFrom: blue
 colorTo: purple
 sdk: docker
 pinned: false
+app_port: 4000
+license: mit
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

config.yaml

@@ -0,0 +1,24 @@
+model_list:
+  - model_name: gpt-4o
+    litellm_params:
+      model: github/gpt-4o
+      api_base: https://models.inference.ai.azure.com
+      api_key: "os.environ/GITHUB_API_KEY"
+  - model_name: gpt-4o-mini
+    litellm_params:
+      model: github/gpt-4o-mini
+      api_base: https://models.inference.ai.azure.com
+      api_key: "os.environ/GITHUB_API_KEY"
+  - model_name: meta-llama-3.1-405b-instruct
+    litellm_params:
+      model: github/meta-llama-3.1-405b-instruct
+      api_base: https://models.inference.ai.azure.com
+      api_key: "os.environ/GITHUB_API_KEY"
+  - model_name: meta-llama-3.1-8b-instruct
+    litellm_params:
+      model: github/meta-llama-3.1-8b-instruct
+      api_base: https://models.inference.ai.azure.com
+      api_key: "os.environ/GITHUB_API_KEY"
+
+litellm_settings:
+  drop_params: True