update

README.md

@@ -1,5 +1,5 @@
 ---
-title: Mllava
+title: Mantis
 emoji: 👁
 colorFrom: green
 colorTo: yellow

app.py

@@ -4,8 +4,8 @@ import time
 from PIL import Image
 from models.mllava import MLlavaProcessor, LlavaForConditionalGeneration, chat_mllava, MLlavaForConditionalGeneration
 from typing import List
-processor = MLlavaProcessor.from_pretrained("MFuyu/mllava_llava_debug_nlvr2_v5_4096")
-model = LlavaForConditionalGeneration.from_pretrained("MFuyu/mllava_llava_debug_nlvr2_v5_4096")
+processor = MLlavaProcessor.from_pretrained("TIGER-Lab/Mantis-llava-7b-v1.1")
+model = LlavaForConditionalGeneration.from_pretrained("TIGER-Lab/Mantis-llava-7b-v1.1")
 
 @spaces.GPU
 def generate(text:str, images:List[Image.Image], history: List[dict], **kwargs):
@@ -95,6 +95,10 @@ def bot(history):
         
 def build_demo():
     with gr.Blocks() as demo:
+        
+        gr.Markdown(""" # Mantis
+                    Mantis is a multimodal conversational AI model that can chat with users about images and text. It's optimized for multi-image reasoning, where inverleaved text and images can be used to generate responses.
+        """)
         chatbot = gr.Chatbot(line_breaks=True)
         chat_input = gr.MultimodalTextbox(interactive=True, file_types=["image"], placeholder="Enter message or upload images. Please use <image> to indicate the position of uploaded images", show_label=True)
         
@@ -112,6 +116,10 @@ def build_demo():
         ).then(
             bot, chatbot, chatbot, api_name="bot_response"
         )
+        
+        
+        
+        
     return demo