Update main.py

main.py

@@ -3,7 +3,7 @@ from fastapi import FastAPI
 from pydantic import BaseModel
 
 # Load Gemma-2B model
-llm = AutoModelForCausalLM.from_pretrained("gemma-2b.Q4_K_S.gguf", max_new_tokens=8192, threads=3)
+llm = AutoModelForCausalLM.from_pretrained("2b_it_v1p1.gguf", max_new_tokens=8192, threads=3)
 
 # Define Pydantic object for input validation
 class Validation(BaseModel):