Update chatbot.py

chatbot.py

@@ -26,9 +26,9 @@ from gradio_client import Client, file
 from groq import Groq
 
 # You can also use models that are commented below
-# model_id = "llava-hf/llava-interleave-qwen-0.5b-hf"
+model_id = "llava-hf/llava-interleave-qwen-0.5b-hf"
 # model_id = "llava-hf/llava-interleave-qwen-7b-hf"
-model_id = "llava-hf/llava-interleave-qwen-7b-dpo-hf"
+# model_id = "llava-hf/llava-interleave-qwen-7b-dpo-hf"
 processor = LlavaProcessor.from_pretrained(model_id)
 model = LlavaForConditionalGeneration.from_pretrained(model_id,torch_dtype=torch.float16) #,  use_flash_attention_2=True)
 model.to("cpu")
@@ -212,7 +212,7 @@ client_mixtral = InferenceClient("NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO")
 client_llama = InferenceClient("meta-llama/Meta-Llama-3-8B-Instruct")
 client_mistral_nemo = InferenceClient("mistralai/Mistral-Nemo-Instruct-2407")
 
-@spaces.GPU(duration=60, queue=False)
+# @spaces.GPU(duration=60, queue=False)
 def model_inference( user_prompt, chat_history):
     if user_prompt["files"]:
         inputs = llava(user_prompt, chat_history)