cene555 / ruCLIP-SB
RuCLIP-SB (Russian Contrastive Language–Image Pretraining SWIN-BERT) is a multimodal model for obtaining images and text similarities and rearranging captions and pictures. Unlike other versions of the model we use BERT for text encoder and SWIN transformer for image encoder.
☆11Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for ruCLIP-SB
- ☆15Updated 3 years ago
- RuCLIP tiny (Russian Contrastive Language–Image Pretraining) is a neural network trained to work with different pairs (images, texts).☆32Updated 2 years ago
- CLIP implementation for Russian language☆137Updated 11 months ago
- Creating multimodal multitask models☆50Updated 2 years ago
- ☆21Updated last year
- 2nd place solution for Next Like prediction task☆54Updated last year
- ☆18Updated 3 years ago
- The 2nd place Solution for Digital Peter competition.☆10Updated 2 years ago
- Code and data of "Methods for Detoxification of Texts for the Russian Language" paper☆46Updated 2 months ago
- Optical Character Recognition + Instance Segmentation for russian and english languages☆28Updated 2 years ago
- Baseline for Data Fusion Contest 2023 "Attack"☆8Updated last year
- ☆58Updated 9 months ago
- RuTransform: python framework for adversarial attacks and text data augmentation for Russian☆17Updated last year
- Распознавание рукописного текста в школьных тетрадях☆14Updated last year
- A new second practical assignment for Huawei's NLP course☆13Updated 7 months ago
- Development of a prototype engine for searching for goods on the tender procurement portal☆27Updated 2 years ago
- The solution and code for NTO AI Olympics 2022.☆18Updated 2 years ago
- A library built upon PyTorch for building embeddings on discrete event sequences using self-supervision☆91Updated 2 years ago
- The final solution of the problem of "Цифровой Прорыв" competition about the positioning of the image on the ground☆14Updated 2 years ago
- SAGE: Spelling correction, corruption and evaluation for multiple languages☆131Updated last month
- ☆26Updated 2 years ago
- FusionBrain Challenge 2.0: creating multimodal multitask model☆16Updated 2 years ago
- Augmentex — a library for augmenting texts with errors☆51Updated 4 months ago
- Slightly extended baseline solution☆35Updated 3 years ago
- Сжатие и ускорение моделей машинного обучения☆15Updated last year
- Repository containing our datasets for HTR (handwritten text recognition) task.☆24Updated 2 years ago
- Бенчмарк сравнивает русские аналоги ChatGPT: Saiga, YandexGPT, Gigachat☆57Updated last year
- MERA (Multimodal Evaluation for Russian-language Architectures) is a new open benchmark for the Russian language for evaluating fundament…☆58Updated last month
- Bunch of notebooks for pre-training custom Saiga-like LLM☆13Updated 9 months ago
- Modified Arena-Hard-Auto LLM evaluation toolkit with an emphasis on Russian language☆24Updated last week