PR feedback

README.md

@@ -156,19 +156,17 @@ Additional tools for evaluating OLMo models are available at the [OLMo Eval](htt
 
 ## Modal.com 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.
+An example script is provided for hosting an OLMo 2 model on Modal.com using 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
+
+1. 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"
+2. 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
+3. Then run
 ```bash
 modal deploy ./scripts/olmo2_modal_openai.py
 ```
-</li>
-</ol>
 
 You can check your endpoint using curl similar to the following:
 ```bash

scripts/olmo2_modal_openai.py

@@ -18,8 +18,8 @@
 APP_NAME = "OLMo-2-1124-13B-Instruct-openai"
 APP_LABEL = APP_NAME.lower()
 
-MINUTES = 60  # seconds
-HOURS = 60 * MINUTES
+ONE_MINUTE = 60  # seconds
+ONE_HOUR = 60 * ONE_MINUTE
 
 # ## Download the model weights
 
@@ -78,7 +78,7 @@ def download_model_to_image(model_dir, model_name, model_revision):
     .env({"HF_HUB_ENABLE_HF_TRANSFER": "1"})
     .run_function(
         download_model_to_image,
-        timeout=60 * MINUTES,  # typically much faster but set high to be conservative
+        timeout=60 * ONE_MINUTE,  # typically much faster but set high to be conservative
         kwargs={
             "model_dir": MODEL_DIR,
             "model_name": MODEL_NAME,
@@ -107,8 +107,8 @@ def download_model_to_image(model_dir, model_name, model_revision):
     image=vllm_image,
     gpu=GPU_CONFIG,
     keep_warm=0,  # Spin down entirely when idle
-    container_idle_timeout=5 * MINUTES,
-    timeout=24 * HOURS,
+    container_idle_timeout=5 * ONE_MINUTE,
+    timeout=24 * ONE_HOUR,
     allow_concurrent_inputs=1000,
     secrets=[modal.Secret.from_name("example-secret-token")],  # contains MODAL_TOKEN used below
 )