davenliu commited on
Commit
d642632
·
verified ·
1 Parent(s): 51c95db

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -10,6 +10,7 @@ library_name: transformers
10
  <a href='https://huggingface.co/OPPOer'><img src='https://img.shields.io/badge/🤗%20HuggingFace-AndesVL-ffd21f.svg'></a> &nbsp;
11
  <a href='https://github.com/OPPO-Mente-Lab/AndesVL_Evaluation'><img src="https://img.shields.io/badge/GitHub-OPPOer-blue.svg?logo=github" alt="GitHub"></a>
12
  </div>
 
13
  AndesVL is a suite of mobile-optimized Multimodal Large Language Models (MLLMs) with **0.6B to 4B parameters**, built upon Qwen3's LLM and various visual encoders. Designed for efficient edge deployment, it achieves first-tier performance on diverse benchmarks, including those for text-rich tasks, reasoning tasks, Visual Question Answering (VQA), multi-image tasks, multilingual tasks, and GUI tasks. Its "1+N" LoRA architecture and QALFT framework facilitate efficient task adaptation and model compression, enabling a 6.7x peak decoding speedup and a 1.8 bits-per-weight compression ratio on mobile chips.
14
 
15
  Detailed model sizes and components are provided below:
 
10
  <a href='https://huggingface.co/OPPOer'><img src='https://img.shields.io/badge/🤗%20HuggingFace-AndesVL-ffd21f.svg'></a> &nbsp;
11
  <a href='https://github.com/OPPO-Mente-Lab/AndesVL_Evaluation'><img src="https://img.shields.io/badge/GitHub-OPPOer-blue.svg?logo=github" alt="GitHub"></a>
12
  </div>
13
+
14
  AndesVL is a suite of mobile-optimized Multimodal Large Language Models (MLLMs) with **0.6B to 4B parameters**, built upon Qwen3's LLM and various visual encoders. Designed for efficient edge deployment, it achieves first-tier performance on diverse benchmarks, including those for text-rich tasks, reasoning tasks, Visual Question Answering (VQA), multi-image tasks, multilingual tasks, and GUI tasks. Its "1+N" LoRA architecture and QALFT framework facilitate efficient task adaptation and model compression, enabling a 6.7x peak decoding speedup and a 1.8 bits-per-weight compression ratio on mobile chips.
15
 
16
  Detailed model sizes and components are provided below: