Update README.md

README.md

@@ -11,9 +11,10 @@ pipeline_tag: image-text-to-text
 
 ![efficiency](./assets/singleGPU.png) 
 
+
 ## 🌈 Update
 
-* **[2024.09.05]** LongLLaVA repo is published！🎉 
+* **[2024.09.05]** LongLLaVA repo is published！🎉 The Code will
 
 ## Architecture
 
@@ -41,17 +42,52 @@ pipeline_tag: image-text-to-text
 
 
 
-## Evaluation and demo
+## Results reproduction
+
+
+### Evaluation
+
+- Preparation
+
+Get the model inference code from [Github](https://github.com/FreedomIntelligence/LongLLaVA).
+
+```bash
+  git clone https://github.com/FreedomIntelligence/LongLLaVA.git
+```
+
+- Environment Setup
+
+```bash
+  pip install -r requirements.txt
+```
+
+
+- Command Line Interface
+
+```bash
+  python cli.py --model_dir path-to-longllava
+```
+
 
-   > Coming Soon~
+- Model Inference
 
-## To do
+```python
+query = 'What does the picture show?'
+image_paths = ['image_path1'] # image or video path
 
-  [] Release inference code
+from cli import Chatbot
+bot = Chatbot(path-to-longllava)
+output = bot.inference(query, image_paths)
+print(output) # Prints the output of the model
+```
 
+## TO DO
 
+- [ ] Release Data Construction Code
 
+## Acknowledgement
 
+- [LLaVA](https://github.com/haotian-liu/LLaVA): Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
 
 ## Citation
 
@@ -65,4 +101,7 @@ pipeline_tag: image-text-to-text
       primaryClass={cs.CL},
       url={https://arxiv.org/abs/2409.02889}, 
 }
-```
+```
+
+
+