elephantmipt / compressors
A small library with distillation, quantization and pruning pipelines
☆26Updated 4 years ago
Alternatives and similar repositories for compressors:
Users that are interested in compressors are comparing it to the libraries listed below
- Distillation of BERT model with catalyst framework☆78Updated last year
- Russian RoBERTa☆29Updated 5 years ago
- Probing suite for evaluation of Russian embedding and language models☆33Updated 7 months ago
- Pytorch library for end-to-end transformer models training, inference and serving☆70Updated 2 weeks ago
- ☆12Updated 2 years ago
- http://nlp.seas.harvard.edu/2018/04/03/attention.html☆62Updated 3 years ago
- RuSimpleSentEval (RSSE) shared task repo☆21Updated 4 years ago
- Russian dialog datasets parsers and crawlers.☆16Updated 3 years ago
- Russian Artificial Text Detection☆17Updated 2 years ago
- DEREK (Domain Entities and Relations Extraction Kit)☆10Updated last year
- (re)Implementation of Learning Multi-level Dependencies for Robust Word Recognition☆17Updated 9 months ago
- MOdel ResOurCe COnsumption. Evaluate Russian SuperGLUE models performance: inference speed, RAM usage. Reproducible scores using Docker☆22Updated 2 years ago
- ☆29Updated 2 years ago
- A barebones (Distil)BERT pipeline for token classification tasks driven by catalyst☆13Updated 5 years ago
- nlp workshop at datafest siberia 2019☆22Updated 2 years ago
- Code and data of "Methods for Detoxification of Texts for the Russian Language" paper☆47Updated last month
- RuREBus shared task repo☆30Updated 4 years ago
- RUSSE 2022: Russian Text Detoxification Based on Parallel Corpora☆20Updated last month
- "Rossiya Segodnya" news dataset☆45Updated 5 years ago
- Train punctuation and capitalization models for different languages☆24Updated 3 years ago
- Pipeline for easy fine-tuning of BERT architecture for sequence classification☆23Updated last year
- RuTransform: python framework for adversarial attacks and text data augmentation for Russian☆19Updated last year
- Source code for the ACL workshop paper and Kaggle competition by Google AI team☆40Updated 3 years ago
- RuCLIP tiny (Russian Contrastive Language–Image Pretraining) is a neural network trained to work with different pairs (images, texts).☆34Updated 2 years ago
- Infrastructure for starting TG bot project. Postgres, Minio, Grafana, Alembic☆21Updated 2 years ago
- BSNLP 2021☆33Updated 6 months ago
- Accelerated NLP pipelines for fast inference on CPU and GPU. Built with Transformers, Optimum and ONNX Runtime.☆125Updated 3 years ago
- Code for AINL2018 paper Deep Convolutional Networks for Supervised Morpheme Segmentation of Russian Language☆22Updated 5 years ago
- ☆23Updated 4 years ago
- Simple library to work with pre-trained ELMo models in TensorFlow☆52Updated last year