Hugging Face's logo

5CD-AI
/
Vintern-1B-v2

Image-Text-to-Text
Transformers
Safetensors
Vietnamese
English
internvl_chat
feature-extraction
vision
conversational
custom_code
Model card Files
xet
Community
13
khang119966 commited on
Commit
5ec0053
·
verified ·
1 Parent(s): 9c550b7

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -1
README.md CHANGED
@@ -28,7 +28,9 @@ tags:
28
  <img src="Vintern_logo.png" width="700"/>
29
  </div>
30
 
31
- ## Vintern-1B-v2 ❄️ (Viet-InternVL2-1B-v2) [\[🤗 HF Demo\]](https://huggingface.co/spaces/khang119966/Vintern) - The LLaVA 🌋 Challenger
 
 
32
 
33
  We are excited to introduce **Vintern-1B-v2** the Vietnamese 🇻🇳 multimodal model that combines the advanced Vietnamese language model [Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct)[1] with the latest visual model, [InternViT-300M-448px](https://huggingface.co/OpenGVLab/InternViT-300M-448px)[2], CVPR 2024. This model excels in tasks such as OCR-VQA, Doc-VQA, and Chart-VQA,... With only 1 billion parameters, it is **4096 context length** finetuned from the Viet-InternVL-1B model on over 3 million specialized image-question-answer pairs for optical character recognition 🔍, text recognition 🔤, document extraction 📑, and general QA. The model can be integrated into various on-device applications 📱, demonstrating its versatility and robust capabilities.
34
 
 
28
  <img src="Vintern_logo.png" width="700"/>
29
  </div>
30
 
31
+ [\[🤗 HF Demo\]](https://huggingface.co/spaces/khang119966/Vintern-v2)
32
+
33
+ ## Vintern-1B-v2 ❄️ (Viet-InternVL2-1B-v2) - The LLaVA 🌋 Challenger
34
 
35
  We are excited to introduce **Vintern-1B-v2** the Vietnamese 🇻🇳 multimodal model that combines the advanced Vietnamese language model [Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct)[1] with the latest visual model, [InternViT-300M-448px](https://huggingface.co/OpenGVLab/InternViT-300M-448px)[2], CVPR 2024. This model excels in tasks such as OCR-VQA, Doc-VQA, and Chart-VQA,... With only 1 billion parameters, it is **4096 context length** finetuned from the Viet-InternVL-1B model on over 3 million specialized image-question-answer pairs for optical character recognition 🔍, text recognition 🔤, document extraction 📑, and general QA. The model can be integrated into various on-device applications 📱, demonstrating its versatility and robust capabilities.
36