Update README.md

README.md

@@ -4,39 +4,102 @@ base_model:
 - Qwen/Qwen2.5-7B-Instruct
 ---
 # Valley 2.0
+
+<p align="center">
+    <img src="https://raw.githubusercontent.com/bytedance/Valley/refs/heads/main/assets/valley_logo.jpg" width="500"/>
+<p>
+
+<p align="center">
+        🤗 <a href="https://huggingface.co/bytedance-research/Valley-Eagle-7B">Hugging Face</a>&nbsp&nbsp | &nbsp&nbsp 📑 <a href="https://hyggge.github.io/projects/valley/index.html">Home Page</a> 
+</p>
+
+
 ## Introduction
-Valley [github](https://github.com/bytedance/Valley) is a cutting-edge multimodal large model designed to handle a variety of tasks involving text, images, and video data, which is developed by ByteDance. Our model not only
+Valley is a cutting-edge multimodal large model designed to handle a variety of tasks involving text, images, and video data, which is developed by ByteDance. Our model
 
-- Achieved the best results in the inhouse e-commerce and short-video benchmarks
-- Demonstrated comparatively outstanding performance in the OpenCompass (average scores > 67) tests
+- Achieved the best results in the inhouse e-commerce and short-video benchmarks, much better then other SOTA opensource models.
+- Demonstrated comparatively outstanding performance in the OpenCompass (average scores >= 67.40, *TOP2* among <10B models) tests
 
-when evaluated against models of the same scale. 
+when evaluated against models of the same scale.
+
+<div style="display:flex;">
+  <!-- <img src="assets/open_compass_1223.jpg" alt="opencompass" style="height:300px;" />
+  <img src="assets/tts_inhouse_benchmark_1223.jpg" alt="inhouse" style="height:300px;" /> -->
+    <img src="https://raw.githubusercontent.com/bytedance/Valley/refs/heads/main/assets/combine.jpg" alt="opencompass"/>
+</div>
+<br>
+
+<p align="center" style="display:flex;">
+    <img src="https://raw.githubusercontent.com/bytedance/Valley/refs/heads/main/assets/table.jpeg"/>
+<p>
 
-## Release
-- [12/23] 🔥 Announcing [Valley-Qwen2.5-7B](https://huggingface.co/ByteDance)!
 
 ## Valley-Eagle
 The foundational version of Valley is a multimodal large model aligned with Siglip and Qwen2.5, incorporating LargeMLP and ConvAdapter to construct the projector. 
 
-- In the final version, we also referenced Eagle, introducing an additional VisionEncoder that can flexibly adjust the number of tokens and is parallelized with the original visual tokens. 
+- In the final version, we also referenced [Eagle](https://arxiv.org/pdf/2408.15998), introducing an additional VisionEncoder that can flexibly adjust the number of tokens and is parallelized with the original visual tokens. 
 - This enhancement supplements the model’s performance in extreme scenarios, and we chose the Qwen2vl VisionEncoder for this purpose. 
 
 and the model structure is shown as follows:
 
 <div style="display:flex;">
-  <img src="valley_structure.jpeg" alt="opencompass" style="height:600px;" />
+  <img src="https://raw.githubusercontent.com/bytedance/Valley/refs/heads/main/assets/valley_structure.jpeg" alt="opencompass" />
 </div>
 
 
+## Release
+- [12/23] 🔥 Announcing [Valley-Eagle-7B](https://huggingface.co/bytedance-research/Valley-Eagle-7B)!
+
 ## Environment Setup
 ``` bash
 pip install torch==2.4.0 torchvision==0.19.0 torchaudio==2.4.0 --index-url https://download.pytorch.org/whl/cu121
 pip install -r requirements.txt
 ```
 
-## License Agreement
-All of our open-source models are licensed under the Apache-2.0 license.
+## Inference Demo
+- Single image
+``` python
+from valley_eagle_chat import ValleyEagleChat
+model = ValleyEagleChat(
+    model_path='bytedance-research/Valley-Eagle-7B',
+    padding_side = 'left',
+)
+
+url = 'http://p16-goveng-va.ibyteimg.com/tos-maliva-i-wtmo38ne4c-us/4870400481414052507~tplv-wtmo38ne4c-jpeg.jpeg'
+img = urllib.request.urlopen(url=url, timeout=5).read()
+
+request = {
+    "chat_history": [
+        {'role': 'system', 'content': 'You are Valley, developed by ByteDance. Your are a helpfull Assistant.'},
+        {'role': 'user', 'content': 'Describe the given image.'},
+    ],
+    "images": [img],
+}
+
+result = model(request)
+print(f"\n>>> Assistant:\n")
+print(result)
+```
+
+- Video
+``` python
+from valley_eagle_chat import ValleyEagleChat
+import decord
+import requests
+import numpy as np
+from torchvision import transforms
 
+model = ValleyEagleChat(
+    model_path='bytedance-research/Valley-Eagle-7B',
+    padding_side = 'left',
+)
 
-## Citation
-Coming Soon!
+url = 'https://videos.pexels.com/video-files/29641276/12753127_1920_1080_25fps.mp4'
+video_file = './video.mp4'
+response = requests.get(url)
+if response.status_code == 200:
+    with open("video.mp4", "wb") as f:
+        f.write(response.content)
+else:
+    print("download error!")
+    exit(1)