Update app.py

app.py

@@ -4,7 +4,7 @@ from fastapi import FastAPI
 from pydantic import BaseModel
 
 # Load the model and tokenizer
-model_name = "google/gemma-2b"
+model_name = "databricks/dolly-v2-3b"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16, device_map="auto")
 
@@ -18,7 +18,7 @@ class ChatInput(BaseModel):
 @app.post("/chat")
 async def chat(chat_input: ChatInput):
     inputs = tokenizer(chat_input.user_input, return_tensors="pt").to("cuda")
-    outputs = model.generate(**inputs, max_new_tokens=200, do_sample=True)
+    outputs = model.generate(**inputs, max_length=200, do_sample=True)
     response_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
     return {"response": response_text}