zwgao commited on
Commit
d119521
1 Parent(s): 3baec71

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -22,7 +22,7 @@ pipeline_tag: visual-question-answering
22
  We introduce InternVL 1.5, an open-source multimodal large language model (MLLM) to bridge the capability gap between open-source and proprietary commercial models in multimodal understanding.
23
  We introduce three simple designs:
24
  1. Strong Vision Encoder: we explored a continuous learning strategy for the large-scale vision foundation model---InternViT-6B, boosting its visual understanding capabilities, and making it can be transferred and reused in different LLMs.
25
- 2. Dynamic High-Resolution: we divide images into tiles ranging from 1 to 32 of 448$\times$448 pixels according to the aspect ratio and resolution of the input images, which supports up to 4K resolution input.
26
  3. High-Quality Bilingual Dataset: we carefully collected a high-quality bilingual dataset that covers common scenes, document images, and annotated them with English and Chinese question-answer pairs, significantly enhancing performance in OCR- and Chinese-related tasks.
27
 
28
 
 
22
  We introduce InternVL 1.5, an open-source multimodal large language model (MLLM) to bridge the capability gap between open-source and proprietary commercial models in multimodal understanding.
23
  We introduce three simple designs:
24
  1. Strong Vision Encoder: we explored a continuous learning strategy for the large-scale vision foundation model---InternViT-6B, boosting its visual understanding capabilities, and making it can be transferred and reused in different LLMs.
25
+ 2. Dynamic High-Resolution: we divide images into tiles ranging from 1 to 32 of 448 × 448 pixels according to the aspect ratio and resolution of the input images, which supports up to 4K resolution input.
26
  3. High-Quality Bilingual Dataset: we carefully collected a high-quality bilingual dataset that covers common scenes, document images, and annotated them with English and Chinese question-answer pairs, significantly enhancing performance in OCR- and Chinese-related tasks.
27
 
28