Update app.py

app.py

@@ -85,8 +85,8 @@ def predict(message, history, system_prompt, temperature, max_new_tokens, top_k,
         attention_mask = attention_mask[:, -CONTEXT_LENGTH:]
 
     generate_kwargs = dict(
-        input_ids=input_ids.to(device),
-        attention_mask=attention_mask.to(device),
+        input_ids=input_ids,
+        attention_mask=attention_mask,
         streamer=streamer,
         do_sample=True,
         temperature=temperature,
@@ -115,7 +115,7 @@ tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
 model = AutoModelForCausalLM.from_pretrained(
     MODEL_ID,
     device_map="auto",
-    #quantization_config=quantization_config,
+    quantization_config=quantization_config,
     #attn_implementation="flash_attention_2",
 )