huizhang0110 / catvision
A multimodal large-scale model, which performs close to the closed-source Qwen-VL-PLUS on many datasets and significantly surpasses the performance of the open-source model Qwen-VL-7B-Chat.
β14Updated 9 months ago
Related projects β
Alternatives and complementary repositories for catvision
- Chinese CLIP models with SOTA performance.β48Updated last year
- Exploration of the multi modal fuyu-8b model of Adept. π€ πβ28Updated last year
- β35Updated 5 months ago
- A Dead Simple and Modularized Multi-Modal Training and Finetune Framework. Compatible to any LLaVA/Flamingo/QwenVL/MiniGemini etc series β¦β17Updated 7 months ago
- β22Updated 2 years ago
- paddle code convert toolkitβ22Updated last year
- β13Updated last year
- β31Updated last week
- WikiTableSet: A largest publicly available image-based table recognition dataset in three languages built from Wikipediaβ25Updated last year
- β26Updated 3 years ago
- PyTorch implementation of BMVC2022 paper Masked Vision-Language Transformers for Scene Text Recognitionβ29Updated 2 years ago
- A Simple MLLM Surpassed QwenVL-Max with OpenSource Data Only in 14B LLM.β36Updated 2 months ago
- Official implementation of High Fidelity Scene Text Synthesis.β36Updated last week
- CLIPδΈζencoderβ21Updated 2 years ago
- β39Updated 4 years ago
- Empirical Study Towards Building An Effective Multi-Modal Large Language Modelβ23Updated last year
- Vision-Language Pre-Training for Boosting Scene Text Detectors (CVPR2022)β12Updated 2 years ago
- BTS: A Bi-lingual Benchmark for Text Segmentation in the Wildβ27Updated 7 months ago
- TIoU metric in python3. Forked from https://github.com/Yuliang-Liu/TIoU-metric.β25Updated 4 years ago
- ImageSlider custom component for gradio.β30Updated 6 months ago
- An object detection codebase based on MegEngine.β28Updated last year
- VimTS: A Unified Video and Image Text Spotterβ72Updated 2 weeks ago
- β18Updated 3 years ago
- β12Updated 2 years ago
- β30Updated 6 months ago
- β23Updated 3 months ago
- β13Updated last month