EvilFreelancer / saiga-custom
Bunch of notebooks for pre-training custom Saiga-like LLM
☆13Updated last year
Alternatives and similar repositories for saiga-custom:
Users that are interested in saiga-custom are comparing it to the libraries listed below
- MERA (Multimodal Evaluation for Russian-language Architectures) is a new open benchmark for the Russian language for evaluating fundament…☆62Updated 4 months ago
- Modified Arena-Hard-Auto LLM evaluation toolkit with an emphasis on Russian language☆38Updated 2 months ago
- Framework for processing and filtering datasets☆27Updated 6 months ago
- Простой нормализатор текстов перед синтезом речи☆25Updated 9 months ago
- Бенчмарк сравнивает русские аналоги ChatGPT: Saiga, YandexGPT, Gigachat☆60Updated last year
- Effective LLM Alignment Toolkit☆115Updated this week
- Telegram bot for different language models. Supports system prompts and images☆45Updated 2 months ago
- Augmentex — a library for augmenting texts with errors☆61Updated 7 months ago
- ☆25Updated 3 months ago
- T5-based (russian) text normalization☆20Updated last year
- RuTransform: python framework for adversarial attacks and text data augmentation for Russian☆19Updated last year
- ☆31Updated 4 months ago
- "Руформеры" - список популярных базовых моделей на основе трансформеров для решения задач по автоматической обработке русского языка☆36Updated last year
- ☆15Updated last year
- SAGE: Spelling correction, corruption and evaluation for multiple languages☆147Updated 2 months ago
- Russian open TTS dataset☆12Updated 5 years ago
- ☆21Updated last year
- RuBLiMP: Russian Benchmark of Linguistic Minimal Pairs☆17Updated last week
- ☆57Updated last year
- Train punctuation and capitalization models for different languages☆24Updated 2 years ago
- Top ML papers of the week.☆25Updated this week
- Gazeta: Dataset for automatic summarization of Russian news / Газета: набор данных для автоматического реферирования на русском языке☆34Updated 3 years ago
- A new second practical assignment for Huawei's NLP course☆16Updated 11 months ago
- MERA (Multimodal Evaluation for Russian-language Architectures) is a new open benchmark for the Russian language for evaluating SOTA mode…☆20Updated 3 months ago
- Efficient DL/ML Models Seminars☆27Updated last month
- RAG pipeline implementation example for the Russian language☆19Updated last year
- Проект языковой модели для проведения морфемного анализа, сегментации и токенизации слов русского языка.☆14Updated last month
- This project is concerned with my participating in the RuNNE competition https://github.com/dialogue-evaluation/RuNNE☆11Updated last year
- Using transformers to generate Russian poetry☆35Updated last year