BAAI
/

Aquila-VL-2B-llava-qwen_CG

Inference Endpoints

Model card Files Files and versions Community

ldwang commited on 4 days ago

Commit

31527d1

•

1 Parent(s): 7bb1b6f

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -15,7 +15,7 @@ The **Aquila-VL-2B-CG** model is a vision-language model (VLM) trained based on
 The model was trained on our self-built Infinity-MM dataset, which contains approximately 40 million image-text pairs. This dataset is a combination of open-source data collected from the internet and synthetic instruction data generated using open-source VLM models.
-We have open-sourced [Infinity-MM](https://huggingface.co/datasets/BAAI/Infinity-MM) dataset and related resources. The  Aquila-VL-2B-CG was trained using domestic GPUs, and the model files will be updated on `2024.11.01`. We hope you enjoy using them!
 ## News

 The model was trained on our self-built Infinity-MM dataset, which contains approximately 40 million image-text pairs. This dataset is a combination of open-source data collected from the internet and synthetic instruction data generated using open-source VLM models.
+We have open-sourced [Infinity-MM](https://huggingface.co/datasets/BAAI/Infinity-MM) dataset and related resources. The  Aquila-VL-2B-CG was trained using domestic GPUs, and the model files will be updated in early November 2024. We hope you enjoy using them!
 ## News