Update app.py

app.py

@@ -14,21 +14,21 @@ import requests
 CSS ="""
 .contain { display: flex; flex-direction: column; }
 #component-0 { height: 500px; }
-#chatbot { flex-grow: 1; }
+#chatbot { flex-grow: 1; height: 500px; }
 """
 
 model_id = "xtuner/llava-llama-3-8b-v1_1-transformers"
 
-processor = AutoProcessor.from_pretrained(model_id)
+# processor = AutoProcessor.from_pretrained(model_id)
 
-model = LlavaForConditionalGeneration.from_pretrained(
-    model_id, 
-    torch_dtype=torch.float16, 
-    low_cpu_mem_usage=True, 
-)
+# model = LlavaForConditionalGeneration.from_pretrained(
+#     model_id, 
+#     torch_dtype=torch.float16, 
+#     low_cpu_mem_usage=True, 
+# )
 
-model.to("cuda:0")
-model.generation_config.eos_token_id = 128009
+# model.to("cuda:0")
+# model.generation_config.eos_token_id = 128009
 
 @spaces.GPU
 def bot_streaming(message, history):