add

app.py

@@ -119,7 +119,6 @@ def add_text(state, text, image, image_process_mode, request: gr.Request):
 def http_bot(state, temperature, top_p, max_new_tokens, request: gr.Request):
     logger.info(f"http_bot. ip: {request.client.host}")
     start_tstamp = time.time()
-
     if state.skip_next:
         # This generate call is skipped due to invalid inputs
         yield (state, state.to_gradio_chatbot()) + (no_change_btn,) * 5
@@ -205,17 +204,17 @@ def http_bot(state, temperature, top_p, max_new_tokens, request: gr.Request):
 
 
 title_markdown = ("""
-<h1 align="center"><a href="https://github.com/X-PLUG/mPLUG-Owl"><img src="https://z1.ax1x.com/2023/11/03/piM1rGQ.md.png", alt="mPLUG-Owl" border="0" style="margin: 0 auto; height: 200px;" /></a> </h1>
+<h1 align="center"><a href="https://github.com/Q-Future/Q-Instruct"><img src="https://avatars.githubusercontent.com/u/148673336?s=200&v=4", alt="Q-Instruct (mPLUG-Owl-2)" border="0" style="margin: 0 auto; height: 200px;" /></a> </h1>
 
-<h2 align="center"> mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration</h2>
+<h2 align="center">Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models</h2>
 
 <h5 align="center"> If you like our project, please give us a star ✨ on Github for latest update.  </h2>
 
 <div align="center">
     <div style="display:flex; gap: 0.25rem;" align="center">
-        <a href='https://github.com/X-PLUG/mPLUG-Owl'><img src='https://img.shields.io/badge/Github-Code-blue'></a>
-        <a href="https://arxiv.org/abs/2304.14178"><img src="https://img.shields.io/badge/Arxiv-2304.14178-red"></a>
-        <a href='https://github.com/X-PLUG/mPLUG-Owl/stargazers'><img src='https://img.shields.io/github/stars/X-PLUG/mPLUG-Owl.svg?style=social'></a>
+        <a href='https://github.com/Q-Future/Q-Instruct'><img src='https://img.shields.io/badge/Github-Code-blue'></a>
+        <a href="https://Q-Instruct.github.io/Q-Instruct/fig/Q_Instruct_v0_1_preview.pdf"><img src="https://img.shields.io/badge/Arxiv-2311.0xxxx-red"></a>
+        <a href='https://github.com/Q-Future/Q-Instruct/stargazers'><img src='https://img.shields.io/github/stars/Q-Future/Q-Instruct.svg?style=social'></a>
     </div>
 </div>
 
@@ -246,7 +245,7 @@ block_css = """
 
 def build_demo(embed_mode):
     textbox = gr.Textbox(show_label=False, placeholder="Enter text and press ENTER", container=False)
-    with gr.Blocks(title="mPLUG-Owl2", theme=gr.themes.Default(), css=block_css) as demo:
+    with gr.Blocks(title="Q-Instruct-on-mPLUG-Owl-2", theme=gr.themes.Default(), css=block_css) as demo:
         state = gr.State()
 
         if not embed_mode:
@@ -262,8 +261,8 @@ def build_demo(embed_mode):
 
                 cur_dir = os.path.dirname(os.path.abspath(__file__))
                 gr.Examples(examples=[
-                    [f"{cur_dir}/examples/extreme_ironing.jpg", "What is unusual about this image?"],
-                    [f"{cur_dir}/examples/Rebecca_(1939_poster)_Small.jpeg", "What is the name of the movie in the poster?"],
+                    [f"{cur_dir}/examples/sausage.jpg", "Describe and evaluate the quality of the image."],
+                    [f"{cur_dir}/examples/211.jpg", "Is this image clear?"],
                 ], inputs=[imagebox, textbox])
 
                 with gr.Accordion("Parameters", open=True) as parameter_row:
@@ -272,7 +271,7 @@ def build_demo(embed_mode):
                     max_output_tokens = gr.Slider(minimum=0, maximum=1024, value=512, step=64, interactive=True, label="Max output tokens",)
 
             with gr.Column(scale=8):
-                chatbot = gr.Chatbot(elem_id="Chatbot", label="mPLUG-Owl2 Chatbot", height=600)
+                chatbot = gr.Chatbot(elem_id="Chatbot", label="Q-Instruct-Chatbot", height=600)
                 with gr.Row():
                     with gr.Column(scale=8):
                         textbox.render()
@@ -376,7 +375,7 @@ if __name__ == "__main__":
     parser.add_argument("--concurrency-count", type=int, default=10)
     parser.add_argument("--model-list-mode", type=str, default="once",
         choices=["once", "reload"])
-    parser.add_argument("--model-path", type=str, default="MAGAer13/mplug-owl2-llama2-7b")
+    parser.add_argument("--model-path", type=str, default="teowu/mplug_owl2_7b_448_qinstruct_preview_v0.1")
     parser.add_argument("--device", type=str, default="cuda")
     parser.add_argument("--load-8bit", action="store_true")
     parser.add_argument("--load-4bit", action="store_true")
@@ -394,5 +393,5 @@ if __name__ == "__main__":
     ).launch(
         server_name=args.host,
         server_port=args.port,
-        share=False
+        share=True
     )