cene555 / ru-clip-tiny
RuCLIP tiny (Russian Contrastive Language–Image Pretraining) is a neural network trained to work with different pairs (images, texts).
☆32Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for ru-clip-tiny
- Framework for processing and filtering datasets☆25Updated 3 months ago
- ☆26Updated 3 years ago
- CLIP implementation for Russian language☆137Updated 11 months ago
- ☆21Updated last year
- Single-line inference of SOTA deep learning models☆30Updated last year
- FusionBrain Challenge 2.0: creating multimodal multitask model☆16Updated 2 years ago
- MERA (Multimodal Evaluation for Russian-language Architectures) is a new open benchmark for the Russian language for evaluating fundament…☆58Updated last month
- A simple library that implements CLIP guided loss in PyTorch.☆77Updated 2 years ago
- Infrastructure for starting TG bot project. Postgres, Minio, Grafana, Alembic☆21Updated 2 years ago
- ☆15Updated 3 years ago
- RuTransform: python framework for adversarial attacks and text data augmentation for Russian☆17Updated last year
- ☆10Updated 9 months ago
- Text reading pipeline that combines segmentation and OCR-models.☆26Updated last year
- Train punctuation and capitalization models for different languages☆24Updated 2 years ago
- Augmentex — a library for augmenting texts with errors☆51Updated 4 months ago
- ☆58Updated 9 months ago
- EasyPortrait - Face Parsing and Portrait Segmentation Dataset☆28Updated 2 months ago
- ☆28Updated 2 years ago
- ☆18Updated 2 years ago
- A small library with distillation, quantization and pruning pipelines☆26Updated 3 years ago
- MMLU eval for RU/EN☆14Updated last year
- RUDOLPH: One Hyper-Tasking Transformer can be creative as DALL-E and GPT-3 and smart as CLIP☆253Updated last year
- Russian Artificial Text Detection☆17Updated 2 years ago
- ☆17Updated 2 months ago
- Modified Arena-Hard-Auto LLM evaluation toolkit with an emphasis on Russian language☆24Updated last week
- RuCLIP-SB (Russian Contrastive Language–Image Pretraining SWIN-BERT) is a multimodal model for obtaining images and text similarities and…☆11Updated 2 years ago
- Creating multimodal multitask models☆50Updated 2 years ago
- ☆69Updated 2 years ago
- Russian dialog datasets parsers and crawlers.☆16Updated 3 years ago