elephantmipt / compressors

Related projects ⓘ

Alternatives and complementary repositories for compressors

• elephantmipt / bert-distillation
  Distillation of BERT model with catalyst framework
  ☆75Updated last year
• vlarine / ruberta
  Russian RoBERTa
  ☆29Updated 4 years ago
• RussianNLP / RuSentEval
  Probing suite for evaluation of Russian embedding and language models
  ☆32Updated last month
• dialogue-evaluation / RuATD
  Russian Artificial Text Detection
  ☆17Updated 2 years ago
• dialogue-evaluation / RuSimpleSentEval
  RuSimpleSentEval (RSSE) shared task repo
  ☆21Updated 3 years ago
• alexeykarnachev / dialogs_data_parsers
  Russian dialog datasets parsers and crawlers.
  ☆16Updated 3 years ago
• alexeykarnachev / full_stack_transformer
  Pytorch library for end-to-end transformer models training, inference and serving
  ☆70Updated 2 years ago
• RossiyaSegodnya / ria_news_dataset
  "Rossiya Segodnya" news dataset
  ☆45Updated 5 years ago
• s-nlp / rudetoxifier
  Code and data of "Methods for Detoxification of Texts for the Russian Language" paper
  ☆46Updated 2 months ago
• s-nlp / annotated-transformer
  http://nlp.seas.harvard.edu/2018/04/03/attention.html
  ☆63Updated 3 years ago
• averkij / multipunct
  Train punctuation and capitalization models for different languages
  ☆24Updated 2 years ago
• AlekseyKorshuk / optimum-transformers
  Accelerated NLP pipelines for fast inference on CPU and GPU. Built with Transformers, Optimum and ONNX Runtime.
  ☆126Updated 2 years ago
• tatiana-iazykova / bert-for-sequence-classification
  Pipeline for easy fine-tuning of BERT architecture for sequence classification
  ☆22Updated last year
• RussianNLP / MOROCCO
  MOdel ResOurCe COnsumption. Evaluate Russian SuperGLUE models performance: inference speed, RAM usage. Reproducible scores using Docker
  ☆21Updated 2 years ago
• eatsleepraverepeat / reMUDE
  (re)Implementation of Learning Multi-level Dependencies for Robust Word Recognition
  ☆17Updated 3 months ago
• yandex / mlcup
  Official baseline solutions to Yandex Cup ML challenge
  ☆31Updated 3 years ago
• s-nlp / mutual_implication_score
  ☆12Updated 2 years ago
• Yorko / gender-unbiased_BERT-based_pronoun_resolution
  Source code for the ACL workshop paper and Kaggle competition by Google AI team
  ☆40Updated 2 years ago
• esceptico / squeezer
  Lightweight knowledge distillation pipeline
  ☆28Updated 2 years ago
• ispras-texterra / derek
  DEREK (Domain Entities and Relations Extraction Kit)
  ☆10Updated last year
• buriy / nlp_workshop
  nlp workshop at datafest siberia 2019
  ☆22Updated last year
• s-nlp / russe_detox_2022
  RUSSE 2022: Russian Text Detoxification Based on Parallel Corpora
  ☆20Updated 2 years ago
• dayyass / text-classification-baseline
  Pipeline for fast building text classification TF-IDF + LogReg baselines.
  ☆63Updated 3 years ago
• PragmaticsLab / NLP-course-AMI
  NLP course @ CS Faculty, HSE
  ☆15Updated 4 years ago
• dialogue-evaluation / RuREBus
  RuREBus shared task repo
  ☆30Updated 3 years ago
• vdobrovolskii / rucoco
  ☆29Updated last year
• dialogue-evaluation / GramEval2020
  ☆21Updated 3 years ago
• AlexeySorokin / NeuralMorphemeSegmentation
  Code for AINL2018 paper Deep Convolutional Networks for Supervised Morpheme Segmentation of Russian Language
  ☆19Updated 5 years ago
• BobaZooba / DeepNLP
  Курс по глубокому обучению в обработке естественных языков для магистров компьютерной лингвистики Высшей Школы Экономики
  ☆47Updated 2 years ago
• catalyst-team / bert
  A barebones (Distil)BERT pipeline for token classification tasks driven by catalyst
  ☆13Updated 5 years ago