Update app.py

app.py

@@ -1,11 +1,12 @@
-from fastapi import FastAPI
+from fastapi import FastAPI, HTTPException
 from pydantic import BaseModel
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
-# Load the model and tokenizer
 model_name = "meta-llama/Llama-3.1-8B-Instruct"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name)
+
+# Use the Hugging Face token
+tokenizer = AutoTokenizer.from_pretrained(model_name, use_auth_token=True)
+model = AutoModelForCausalLM.from_pretrained(model_name, use_auth_token=True)
 
 # Initialize FastAPI
 app = FastAPI()
@@ -16,7 +17,10 @@ class Prompt(BaseModel):
 
 @app.post("/generate")
 def generate_text(prompt: Prompt):
-    inputs = tokenizer(prompt.text, return_tensors="pt")
-    outputs = model.generate(**inputs, max_length=100)
-    generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
-    return {"generated_text": generated_text}
+    try:
+        inputs = tokenizer(prompt.text, return_tensors="pt")
+        outputs = model.generate(**inputs, max_length=100)
+        generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
+        return {"generated_text": generated_text}
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Error generating text: {str(e)}")