MERA-Evaluation / MERALinks
MERA (Multimodal Evaluation for Russian-language Architectures) is a new open benchmark for the Russian language for evaluating SOTA models.
☆30Updated this week
Alternatives and similar repositories for MERA
Users that are interested in MERA are comparing it to the libraries listed below
Sorting:
- MERA (Multimodal Evaluation for Russian-language Architectures) is a new open benchmark for the Russian language for evaluating fundament…☆62Updated 10 months ago
- Effective LLM Alignment Toolkit☆140Updated 2 months ago
- Modified Arena-Hard-Auto LLM evaluation toolkit with an emphasis on Russian language☆43Updated 5 months ago
- Бенчмарк сравнивает русские аналоги ChatGPT: Saiga, YandexGPT, Gigachat☆60Updated last year
- Telegram bot for different language models. Supports system prompts and images☆59Updated 2 months ago
- SAGE: Spelling correction, corruption and evaluation for multiple languages☆158Updated 8 months ago
- Augmentex — a library for augmenting texts with errors☆65Updated last year
- AI-generated text boundary detection with RoFT☆24Updated 11 months ago
- Tools and agents for automated research.☆35Updated this week
- Top ML papers of the week.☆39Updated this week
- ☆48Updated last month
- Простой нормализатор текстов перед синтезом речи☆37Updated last year
- Репозиторий измеряет качество Yandexgpt, Gigachat, T-Pro, Saiga, Vikhr, Ruadapt на популярных англоязычных бенчмарках: MGSM, MATH, HumanE…☆24Updated 4 months ago
- RuBLiMP: Russian Benchmark of Linguistic Minimal Pairs☆17Updated 6 months ago
- Language modeling and instruction tuning for Russian☆467Updated last year
- LangChain-compatible integrations with YandexGPT and YandexGPT Embeddings☆43Updated 4 months ago
- The tiniest sentence encoder for Russian language☆233Updated last year
- ☆13Updated last year
- Library for industrial alignment.☆400Updated 3 weeks ago
- RuLeanALBERT is a pretrained masked language model for the Russian language that uses a memory-efficient architecture.☆93Updated 2 years ago
- This project is concerned with my participating in the RuNNE competition https://github.com/dialogue-evaluation/RuNNE☆12Updated 2 years ago
- GigaChain telegram bot example for technical support☆34Updated 8 months ago
- ☆31Updated 4 months ago
- Bunch of notebooks for pre-training custom Saiga-like LLM☆12Updated last year
- Repository for the paper: "Revisiting BPR: A Replicability Study of a Common Recommender System Baseline"☆51Updated 9 months ago
- A set of scripts and configurations for pretraining of Large Language Models (LLM)☆33Updated 5 months ago
- Библиотека для доступа к GigaChat☆119Updated this week
- ☆31Updated 11 months ago
- Russian SuperGLUE benchmark☆109Updated 2 years ago
- RAG pipeline implementation example for the Russian language☆21Updated 2 years ago