Update app.py

app.py

@@ -11,8 +11,17 @@ import os
 
 
 #chatbot = pipeline(model="NCSOFT/Llama-3-OffsetBias-8B")
-token = os.getenv("HF_TOKEN")
-chatbot = pipeline(model="meta-llama/Llama-3.2-1B")
+#token = os.getenv("HF_TOKEN")
+login(token = os.getenv('HF_TOKEN'))
+#chatbot = pipeline(model="meta-llama/Llama-3.2-1B")
+
+tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.2-1B")
+model = AutoModelForCausalLM.from_pretrained(
+    "meta-llama/Llama-3.2-1B",
+    device_map="auto",
+    torch_dtype="auto",
+)
+
 #chatbot = pipeline(model="facebook/blenderbot-400M-distill")
 
 message_list = []
@@ -20,9 +29,13 @@ response_list = []
 
 
 def vanilla_chatbot(message, history):
-    conversation = chatbot(message)
+    inputs = tokenizer(message['text'], return_tensors="pt").to("cpu")
+    with torch.no_grad():
+        outputs = model.generate(inputs.input_ids, max_length=100)
+    return tokenizer.decode(outputs[0], skip_special_tokens=True)
+    #conversation = chatbot(message)
     
-    return conversation[0]['generated_text']
+    #return conversation[0]['generated_text']
 
 demo_chatbot = gr.ChatInterface(vanilla_chatbot, title="Vanilla Chatbot", description="Enter text to start chatting.")