Update app.py

app.py

@@ -2,6 +2,7 @@ import gradio as gr
 from huggingface_hub import InferenceClient
 from transformers import AutoTokenizer
 from llava.model.language_model import *
+from llava.mobel.builder import load_pretrained_model
 
 """
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
@@ -9,13 +10,19 @@ For more information on `huggingface_hub` Inference API support, please check th
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
 model_path = "liuhaotian/llava-v1.6-mistral-7b"
-tokenizer = AutoTokenizer.from_pretrained(model_path)
+model_name = get_model_name_from_path(model_path)
+# tokenizer = AutoTokenizer.from_pretrained(model_path)
 # model = LlavaMistralForCausalLM.from_pretrained(
 #                     model_path,
 #                     low_cpu_mem_usage=True,
 #                     # offload_folder="/content/sample_data"
 #                 )
 
+tokenizer, model, image_processor, context_len = load_pretrained_model(
+        model_path, None, model_name
+    )
+
+
 def respond(
     message,
     history: list[tuple[str, str]],