add gradio interface

app.py

@@ -28,7 +28,11 @@ import shutil
 title = "# 🙋🏻‍♂️Welcome to 🌟Tonic's 🌋📹LLaVA-Video!"
 description1 ="""The **🌋📹LLaVA-Video-7B-Qwen2** is a 7B parameter model  trained on the 🌋📹LLaVA-Video-178K dataset and the LLaVA-OneVision dataset. It is [based on the **Qwen2 language model**](https://huggingface.co/collections/Qwen/qwen2-6659360b33528ced941e557f), supporting a context window of up to 32K tokens. The model can process and interact with images, multi-images, and videos, with specific optimizations for video analysis.
 This model leverages the **SO400M vision backbone** for visual input and Qwen2 for language processing, making it highly efficient in multi-modal reasoning, including visual and video-based tasks.
+<<<<<<< HEAD
 🌋📹LLaVA-Video has larger variants of [32B](https://huggingface.co/lmms-lab/LLaVA-NeXT-Video-32B-Qwen) and [72B](https://huggingface.co/lmms-lab/LLaVA-Video-72B-Qwen2) and with a [variant](https://huggingface.co/lmms-lab/LLaVA-Video-7B-Qwen2-Video-Only) only trained on the new synthetic data
+=======
+🌋📹LLaVA-Video has larger variants of [32B](https://huggingface.co/lmms-lab/LLaVA-NeXT-Video-32B-Qwen) and [72B](https://huggingface.co/lmms-lab/LLaVA-Video-72B-Qwen2) and with a [variant](https://huggingface.co/lmms-lab/LLaVA-Video-7B-Qwen2-Video-Only only trained on the new synthetic data
+>>>>>>> b297085e69127cc23e50f4a85219c4057e5ce2c5
 For further details, please visit the [Project Page](https://github.com/LLaVA-VL/LLaVA-NeXT) or check out the corresponding [research paper](https://arxiv.org/abs/2410.02713).
 """
 description2 ="""- **Architecture**: `LlavaQwenForCausalLM`
@@ -46,7 +50,7 @@ description2 ="""- **Architecture**: `LlavaQwenForCausalLM`
 - **Hardware Used for Training**: 256 * Nvidia Tesla A100 GPUs
 """
 
-joinus = """
+join_us = """
 ## Join us :
 🌟TeamTonic🌟 is always making cool demos! Join our active builder's 🛠️community 👻 [![Join us on Discord](https://img.shields.io/discord/1109943800132010065?label=Discord&logo=discord&style=flat-square)](https://discord.gg/qdfnvSPcqP) On 🤗Huggingface:[MultiTransformer](https://huggingface.co/MultiTransformer) On 🌐Github: [Tonic-AI](https://github.com/tonic-ai) & contribute to🌟 [Build Tonic](https://git.tonic-ai.com/contribute)🤗Big thanks to Yuvi Sharma and all the folks at huggingface for the community grant 🤗
 """
@@ -119,9 +123,14 @@ def gradio_interface(video_file, question):
     return response
 
 with gr.Blocks() as demo:
-    gr.Markdown("# LLaVA-Video-7B-Qwen2 Demo")
-    gr.Markdown("Upload a video and ask a question about it.")
-    
+    gr.Markdown(title)
+    with gr.Row():
+        with gr.Group():
+            gr.Markdown(description1)
+        with gr.Group():
+            gr.Markdown(description2)
+    with gr.Accordion("Join Us", open=False):
+        gr.Markdown(join_us)
     with gr.Row():
         with gr.Column():
             video_input = gr.Video()