Update app.py

app.py

@@ -1,23 +1,22 @@
-from fastapi import FastAPI, Request
 #from transformers import AutoTokenizer, AutoModelForCausalLM, pipeline
-import torch
+from fastapi import FastAPI, Request
 from transformers import AutoTokenizer, AutoModelForSeq2SeqLM, pipeline
 
 app = FastAPI()
-
 model_id = "google/flan-t5-small"
+
 #"unsloth/mistral-7b-v0.2-bnb-4bit"
 #deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
-tokenizer = AutoTokenizer.from_pretrained(model_id,trust_remote_code=True)
-model = AutoModelForSeq2SeqLM.from_pretrained(model_id
-                                             ,    trust_remote_code=True
-)
 
-generator = pipeline("text-generation", model=model, tokenizer=tokenizer)
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForSeq2SeqLM.from_pretrained(model_id)
+generator = pipeline("text2text-generation", model=model, tokenizer=tokenizer)
 
 @app.post("/generate")
 async def generate(request: Request):
     data = await request.json()
     prompt = data.get("prompt", "")
-    result = generator(prompt, max_new_tokens=100, do_sample=True)[0]["generated_text"]
+    result = generator(prompt, max_new_tokens=100)[0]["generated_text"]
     return {"output": result}
+