Update app.py

app.py

@@ -18,12 +18,13 @@ async def echo():
     userPrompt = prompt + "\n\nUser: " + data['request'] + "\nAssistant: "
     input_ids = tokenizer.encode(prompt, return_tensors='pt')
     with torch.no_grad():
-    output_ids = model.generate(
-        input_ids=input_ids, 
-        do_sample=random.choice([True, False]), temperature=float(random.randint(7,20)) / 10.0,
-        max_new_tokens=data.get("max_tokens") or random.randomint(200,500), 
-        eos_token_id=tokenizer.eos_token_id, return_full_text = False)
-    return {"output": tokenizer.decode(output_ids[0], skip_special_tokens=True)}
+        output_ids = model.generate(
+            input_ids=input_ids, 
+            do_sample=random.choice([True, False]), temperature=float(random.randint(7,20)) / 10.0,
+            max_new_tokens=data.get("max_tokens") or random.randomint(200,500), 
+            eos_token_id=tokenizer.eos_token_id, return_full_text = False)
+        output = tokenizer.decode(output_ids[0], skip_special_tokens=True)
+    return {"output": output}
 
 @app.get("/")
 async def get():