MERA-Evaluation / MERALinks
MERA (Multimodal Evaluation for Russian-language Architectures) is a new open benchmark for the Russian language for evaluating SOTA models.
☆33Updated 3 weeks ago
Alternatives and similar repositories for MERA
Users that are interested in MERA are comparing it to the libraries listed below
Sorting:
- Effective LLM Alignment Toolkit☆145Updated 4 months ago
- MERA (Multimodal Evaluation for Russian-language Architectures) is a new open benchmark for the Russian language for evaluating fundament…☆62Updated last year
- Бенчмарк сравнивает русские аналоги ChatGPT: Saiga, YandexGPT, Gigachat☆60Updated 2 years ago
- Modified Arena-Hard-Auto LLM evaluation toolkit with an emphasis on Russian language☆45Updated 7 months ago
- Telegram bot for different language models. Supports system prompts and images☆62Updated 4 months ago
- Augmentex — a library for augmenting texts with errors☆67Updated last year
- SAGE: Spelling correction, corruption and evaluation for multiple languages☆160Updated 10 months ago
- Top ML papers of the week.☆41Updated last week
- Репозиторий измеряет качество Yandexgpt, Gigachat, T-Pro, Saiga, Vikhr, Ruadapt на популярных англоязычных бенчмарках: MGSM, MATH, HumanE…☆24Updated 6 months ago
- Tools and agents for automated research.☆41Updated last week
- LangChain-compatible integrations with YandexGPT and YandexGPT Embeddings☆44Updated 6 months ago
- MMLU eval for RU/EN☆15Updated 2 years ago
- The tiniest sentence encoder for Russian language