Added timeouts to give Modal time

week8/llama.py

@@ -7,11 +7,11 @@ app = modal.App("llama")
 image = Image.debian_slim().pip_install("torch", "transformers", "bitsandbytes", "accelerate")
 secrets = [modal.Secret.from_name("hf-secret")]
 GPU = "T4"
-MODEL_NAME = "meta-llama/Meta-Llama-3.1-8B"
+MODEL_NAME = "meta-llama/Meta-Llama-3.1-8B" # "google/gemma-2-2b"
 
 
 
-@app.function(image=image, secrets=secrets, gpu=GPU)
+@app.function(image=image, secrets=secrets, gpu=GPU, timeout=1800)
 def generate(prompt: str) -> str:
     import os
     import torch

week8/pricer_ephemeral.py

@@ -19,7 +19,7 @@ REVISION = "e8d637df551603dc86cd7a1598a8f44af4d7ae36"
 FINETUNED_MODEL = f"{HF_USER}/{PROJECT_RUN_NAME}"
 
 
-@app.function(image=image, secrets=secrets, gpu=GPU)
+@app.function(image=image, secrets=secrets, gpu=GPU, timeout=1800)
 def price(description: str) -> float:
     import os
     import re

week8/pricer_service.py

@@ -19,7 +19,7 @@ REVISION = "e8d637df551603dc86cd7a1598a8f44af4d7ae36"
 FINETUNED_MODEL = f"{HF_USER}/{PROJECT_RUN_NAME}"
 
 
-@app.function(image=image, secrets=secrets, gpu=GPU)
+@app.function(image=image, secrets=secrets, gpu=GPU, timeout=1800)
 def price(description: str) -> float:
     import os
     import re

week8/pricer_service2.py

@@ -22,7 +22,7 @@ QUESTION = "How much does this cost to the nearest dollar?"
 PREFIX = "Price is $"
 
 
-@app.cls(image=image, secrets=secrets, gpu=GPU)
+@app.cls(image=image, secrets=secrets, gpu=GPU, timeout=1800)
 class Pricer:
     @modal.build()
     def download_model_to_folder(self):