Update app.py

app.py

@@ -12,7 +12,7 @@ import threading
 
 model_id = "PhysicsWallahAI/Aryabhata-1.0"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="auto", attn_implementation="flash_attention_2")
+model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, device_map="cuda", attn_implementation="flash_attention_2")
 
 def process_questions(example):
     example["question_text"] = example["question"]
@@ -52,7 +52,7 @@ def generate_answer_stream(question):
         add_generation_prompt=True
     )
 
-    inputs = tokenizer([text], return_tensors="pt")
+    inputs = tokenizer([text], return_tensors="pt").to("cuda")
 
     streamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
     stopping = StoppingCriteriaList([StopStringCriteria(tokenizer, stop_strings)])