ai-forever / mgpt

Related projects ⓘ

Alternatives and complementary repositories for mgpt

• AlekseyKorshuk / optimum-transformers
  Accelerated NLP pipelines for fast inference on CPU and GPU. Built with Transformers, Optimum and ONNX Runtime.
  ☆126Updated 2 years ago
• s-nlp / inappropriate-sensitive-topics
  BSNLP 2021
  ☆32Updated last week
• ai-forever / ru-prompts
  ☆58Updated 9 months ago
• RussianNLP / RuCoLA
  Russian Corpus of Linguistic Acceptability
  ☆41Updated last month
• dialogue-evaluation / RuATD
  Russian Artificial Text Detection
  ☆17Updated 2 years ago
• RussianNLP / RuSentEval
  Probing suite for evaluation of Russian embedding and language models
  ☆32Updated last month
• tatiana-iazykova / bert-for-sequence-classification
  Pipeline for easy fine-tuning of BERT architecture for sequence classification
  ☆22Updated last year
• s-nlp / rudetoxifier
  Code and data of "Methods for Detoxification of Texts for the Russian Language" paper
  ☆46Updated 2 months ago
• RussianNLP / russian_paraphrasers
  Russian paraphrasers. Generate paraphrases with mt5, gpt2, etc.
  ☆52Updated last year
• dayyass / QaNER
  Unofficial implementation of QaNER: Prompting Question Answering Models for Few-shot Named Entity Recognition.
  ☆65Updated 2 years ago
• nerel-ds / NEREL
  NEREL: A Russian Dataset with Nested Named Entities, Relations and Events
  ☆25Updated last year
• vladislavneon / RuBQ
  A Russian data set for question answering over Wikidata
  ☆46Updated 3 years ago
• elephantmipt / compressors
  A small library with distillation, quantization and pruning pipelines
  ☆26Updated 3 years ago
• RussianNLP / RussianSuperGLUE
  Russian SuperGLUE benchmark
  ☆108Updated last year
• ai-forever / MERA
  MERA (Multimodal Evaluation for Russian-language Architectures) is a new open benchmark for the Russian language for evaluating fundament…
  ☆58Updated last month
• microsoft / xtreme-distil-transformers
  XtremeDistil framework for distilling/compressing massive multilingual neural network models to tiny and efficient models for AI at scale
  ☆153Updated 10 months ago
• ccdv-ai / convert_checkpoint_to_lsg
  Efficient Attention for Long Sequence Processing
  ☆87Updated 10 months ago
• averkij / multipunct
  Train punctuation and capitalization models for different languages
  ☆24Updated 2 years ago
• vetka925 / gpt-j-8bit-lightning-finetune
  ☆18Updated last year
• huggingface / olm-datasets
  Pipeline for pulling and processing online language model pretraining data from the web
  ☆174Updated last year
• sismetanin / rureviews
  An automatically annotated sentiment analysis dataset of product reviews in Russian.
  ☆15Updated 4 years ago
• davidalami / ConveRT
  Dual Encoders for State-of-the-art Natural Language Processing.
  ☆60Updated 2 years ago
• google-research / t5x_retrieval
  ☆95Updated last year
• ai-forever / sage
  SAGE: Spelling correction, corruption and evaluation for multiple languages
  ☆131Updated last month
• yandex-research / RuLeanALBERT
  RuLeanALBERT is a pretrained masked language model for the Russian language that uses a memory-efficient architecture.
  ☆92Updated last year
• Geotrend-research / smaller-transformers
  Load What You Need: Smaller Multilingual Transformers for Pytorch and TensorFlow 2.0.
  ☆101Updated 2 years ago
• facebookresearch / stopes
  A library for preparing data for machine translation research (monolingual preprocessing, bitext mining, etc.) built by the FAIR NLLB te…
  ☆250Updated last month
• s-nlp / mutual_implication_score
  ☆12Updated 2 years ago
• vdobrovolskii / rucoco
  ☆29Updated last year
• ai-forever / ru-dolph
  RUDOLPH: One Hyper-Tasking Transformer can be creative as DALL-E and GPT-3 and smart as CLIP
  ☆253Updated last year