ai-forever / mgpt
Multilingual Generative Pretrained Model
☆202Updated 5 months ago
Related projects ⓘ
Alternatives and complementary repositories for mgpt
- Accelerated NLP pipelines for fast inference on CPU and GPU. Built with Transformers, Optimum and ONNX Runtime.☆126Updated 2 years ago
- BSNLP 2021☆32Updated last week
- ☆58Updated 9 months ago
- Russian Corpus of Linguistic Acceptability☆41Updated last month
- Russian Artificial Text Detection☆17Updated 2 years ago
- Probing suite for evaluation of Russian embedding and language models☆32Updated last month
- Pipeline for easy fine-tuning of BERT architecture for sequence classification☆22Updated last year
- Code and data of "Methods for Detoxification of Texts for the Russian Language" paper☆46Updated 2 months ago
- Russian paraphrasers. Generate paraphrases with mt5, gpt2, etc.☆52Updated last year
- Unofficial implementation of QaNER: Prompting Question Answering Models for Few-shot Named Entity Recognition.☆65Updated 2 years ago
- NEREL: A Russian Dataset with Nested Named Entities, Relations and Events☆25Updated last year
- A Russian data set for question answering over Wikidata☆46Updated 3 years ago
- A small library with distillation, quantization and pruning pipelines☆26Updated 3 years ago
- Russian SuperGLUE benchmark☆108Updated last year
- MERA (Multimodal Evaluation for Russian-language Architectures) is a new open benchmark for the Russian language for evaluating fundament…☆58Updated last month
- XtremeDistil framework for distilling/compressing massive multilingual neural network models to tiny and efficient models for AI at scale☆153Updated 10 months ago
- Efficient Attention for Long Sequence Processing☆87Updated 10 months ago
- Train punctuation and capitalization models for different languages☆24Updated 2 years ago
- ☆18Updated last year
- Pipeline for pulling and processing online language model pretraining data from the web☆174Updated last year
- An automatically annotated sentiment analysis dataset of product reviews in Russian.☆15Updated 4 years ago
- Dual Encoders for State-of-the-art Natural Language Processing.☆60Updated 2 years ago
- ☆95Updated last year
- SAGE: Spelling correction, corruption and evaluation for multiple languages☆131Updated last month
- RuLeanALBERT is a pretrained masked language model for the Russian language that uses a memory-efficient architecture.☆92Updated last year
- Load What You Need: Smaller Multilingual Transformers for Pytorch and TensorFlow 2.0.☆101Updated 2 years ago
- A library for preparing data for machine translation research (monolingual preprocessing, bitext mining, etc.) built by the FAIR NLLB te…☆250Updated last month
- ☆12Updated 2 years ago
- ☆29Updated last year
- RUDOLPH: One Hyper-Tasking Transformer can be creative as DALL-E and GPT-3 and smart as CLIP☆253Updated last year