AlekseyKorshuk / optimum-transformers
Accelerated NLP pipelines for fast inference on CPU and GPU. Built with Transformers, Optimum and ONNX Runtime.
☆126Updated 2 years ago
Related projects: ⓘ
- ☆58Updated 7 months ago
- BSNLP 2021☆32Updated 2 years ago
- A small library with distillation, quantization and pruning pipelines☆26Updated 3 years ago
- MMLU eval for RU/EN☆14Updated last year
- Pipeline for easy fine-tuning of BERT architecture for sequence classification☆22Updated last year
- Tools for shrinking fastText models (in gensim format)☆168Updated 4 months ago
- MERA (Multimodal Evaluation for Russian-language Architectures) is a new open benchmark for the Russian language for evaluating fundament…☆57Updated this week
- MOdel ResOurCe COnsumption. Evaluate Russian SuperGLUE models performance: inference speed, RAM usage. Reproducible scores using Docker☆21Updated last year
- Distillation of BERT model with catalyst framework☆75Updated last year
- Train punctuation and capitalization models for different languages☆24Updated 2 years ago
- RuTransform: python framework for adversarial attacks and text data augmentation for Russian☆17Updated last year
- SAGE: Spelling correction, corruption and evaluation for multiple languages☆129Updated last month
- ☆18Updated last year
- Code and data of "Methods for Detoxification of Texts for the Russian Language" paper☆45Updated 3 weeks ago
- Russian paraphrasers. Generate paraphrases with mt5, gpt2, etc.☆52Updated last year
- Russian Corpus of Linguistic Acceptability