elephantmipt / compressorsLinks
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
Sorting:
- Distillation of BERT model with catalyst framework☆78Updated 2 years ago
- Pytorch library for end-to-end transformer models training, inference and serving☆70Updated 3 months ago
- Russian RoBERTa☆29Updated 5 years ago
- Probing suite for evaluation of Russian embedding and language models☆33Updated 10 months ago
- Models for automatic abstractive summarization☆171Updated 3 years ago
- Code and data of "Methods for Detoxification of Texts for the Russian Language" paper☆49Updated 4 months ago
- Accelerated NLP pipelines for fast inference on CPU and GPU. Built with Transformers, Optimum and ONNX Runtime.☆126Updated 3 years ago
- http://nlp.seas.harvard.edu/2018/04/03/attention.html☆62Updated 4 years ago
- "Rossiya Segodnya" news dataset☆45Updated 5 years ago
- Russian dialog datasets parsers and crawlers.☆16Updated 3 years ago
- ☆12Updated 3 years ago
- Russian paraphrasers. Generate paraphrases with mt5, gpt2, etc.☆54Updated 2 years ago
- BSNLP 2021☆33Updated 9 months ago
- A Russian data set for question answering over Wikidata☆47Updated 4 years ago
- RuTransform: python framework for adversarial attacks and text data augmentation for Russian☆19Updated 2 years ago
- ☆58Updated last year
- Pipeline for easy fine-tuning of BERT architecture for sequence classification☆23Updated 2 years ago
- Code for BERT classifier finetuning for multiclass text classification☆70Updated 2 months ago
- nlp workshop at datafest siberia 2019☆22Updated 2 years ago
- (re)Implementation of Learning Multi-level Dependencies for Robust Word Recognition☆17Updated last year
- RUSSE 2022: Russian Text Detoxification Based on Parallel Corpora☆21Updated 4 months ago
- Multilingual Generative Pretrained Model☆205Updated last year
- REST API for sentence tokenization and embedding using Multilingual Universal Sentence Encoder.☆51Updated 3 years ago
- MOdel ResOurCe COnsumption. Evaluate Russian SuperGLUE models performance: inference speed, RAM usage. Reproducible scores using Docker☆22Updated 2 years ago
- ☆30Updated 2 years ago
- Tools for shrinking fastText models (in gensim format)☆179Updated last year
- RuCLIP tiny (Russian Contrastive Language–Image Pretraining) is a neural network trained to work with different pairs (images, texts).☆34Updated 3 years ago
- RuSimpleSentEval (RSSE) shared task repo☆21Updated 4 years ago
- Russian SuperGLUE benchmark☆109Updated 2 years ago
- RuREBus shared task repo☆30Updated 4 years ago