diff --git a/README.md b/README.md
index cdb508bdd..84521a7bc 100644
--- a/README.md
+++ b/README.md
@@ -154,6 +154,48 @@ The quantized model is sensitive to input types and CUDA handling. To avoid pote
 
 Additional tools for evaluating OLMo models are available at the [OLMo Eval](https://github.com/allenai/OLMo-eval) repo.
 
+## Hosting
+
+An example script is provided for hosting an OLMo 2 model on Modal.com using a the OpenAI API in ./scripts/olmo2_modal_openai.py.
+To run that:
+<ol>
+<li>Follow the instructions under Getting Started in [the Modal.com Guide](https://modal.com/docs/guide) to install
+the Modal library and command line tools.</li>
+<li>Follow the instructions under [Secrets](https://modal.com/docs/guide/secrets) in the Modal.com Guide to create a Modal secret named "example-secret-token"
+that defines a value for the variable MODAL_TOKEN for your server.</li>
+<li>Then run
+```bash
+modal deploy ./scripts/olmo2_modal_openai.py
+```
+</li>
+</ol>
+
+You can check your endpoint using curl similar to the following:
+```bash
+curl -X POST \
+  -H "Authorization: Bearer [the secret token from above]" \
+  -H "Content-Type: application/json" \
+  -d @body.json \
+  https://[the web endpoint modal creates above]/v1/chat/completions
+```
+
+where `body.json` is of the form:
+```
+{
+    "model": "OLMo-2-1124-13B-Instruct",
+    "messages": [
+        {
+            "role": "user",
+            "content": "Who was Alan Turing?"
+        }
+      ],
+    "max_tokens": 100,
+    "temperature": 0.9,
+    "stream": true
+}
+```
+
+
 ## Citing
 
 ```bibtex
diff --git a/scripts/olmo2_modal_openai.py b/scripts/olmo2_modal_openai.py
index c8687dc5c..009591c14 100644
--- a/scripts/olmo2_modal_openai.py
+++ b/scripts/olmo2_modal_openai.py
@@ -50,7 +50,7 @@ def download_model_to_image(model_dir, model_name, model_revision):
 # Our first order of business is to define the environment our server will run in
 # the container image. (See https://modal.com/docs/guide/custom-container)
 
-# This differs from vllm_interface.py in two major ways: first, as of the time this
+# This differs from vllm_inference.py in two major ways: first, as of the time this
 # is being written, the OLMo 2 model architecture requires building vLLM and transformers
 # from github commits that are too recent to have tagged versions, requiring that they
 # be built. The nvidia/cuda base image, git and build-essential apt_install, and the
@@ -145,7 +145,7 @@ def serve():
 
     # This example uses a token defined in the Modal secret linked above,
     # as described here: https://modal.com/docs/guide/secrets
-    async def is_authenticated(api_key: str = fastapi.Security(http_bearer)):
+    async def is_authenticated(api_key = fastapi.Security(http_bearer)):
         if api_key.credentials != os.getenv("MODAL_TOKEN"):
             raise fastapi.HTTPException(
                 status_code=fastapi.status.HTTP_401_UNAUTHORIZED,
@@ -207,7 +207,7 @@ async def is_authenticated(api_key: str = fastapi.Security(http_bearer)):
 
 # To deploy the API on Modal, just run
 # ```bash
-# modal deploy vllm_inference.py
+# modal deploy olmo2_modal_openai.py
 # ```
 
 # This will create a new app on Modal, build the container image for it, and deploy.
@@ -218,7 +218,7 @@ async def is_authenticated(api_key: str = fastapi.Security(http_bearer)):
 # something like `https://your-workspace-name--olmo-2-1124-instruct-openai-serve.modal.run`.
 
 # You can find [interactive Swagger UI docs](https://swagger.io/tools/swagger-ui/)
-# at the `/docs` route of that URL, i.e. `https://your-workspace-name--example-vllm-openai-compatible-serve.modal.run/docs`.
+# at the `/docs` route of that URL, i.e. `https://your-workspace-name--olmo-2-1124-instruct-openai-serve.modal.run/docs`.
 # These docs describe each route and indicate the expected input and output
 # and translate requests into `curl` commands. They also demonstrate authentication.