g0t4 / llm-colosseum
Benchmark LLMs by fighting in Street Fighter 3! The new way to evaluate the quality of an LLM
☆18Updated 3 months ago
Related projects ⓘ
Alternatives and complementary repositories for llm-colosseum
- Telegram bot for different language models. Supports system prompts and images☆37Updated 2 weeks ago
- Modified Arena-Hard-Auto LLM evaluation toolkit with an emphasis on Russian language☆24Updated 2 weeks ago
- MERA (Multimodal Evaluation for Russian-language Architectures) is a new open benchmark for the Russian language for evaluating fundament…☆58Updated last month
- Effective LLM Alignment Toolkit☆85Updated 2 weeks ago
- Foundational Model for Speech Recognition Tasks☆113Updated 5 months ago
- CLIP implementation for Russian language☆137Updated last year
- T5-based (russian) text normalization☆19Updated 9 months ago
- ☆21Updated last year
- Framework for processing and filtering datasets☆25Updated 3 months ago
- best llms in russian☆39Updated 5 months ago
- Бенчмарк сравнивает русские аналоги ChatGPT: Saiga, YandexGPT, Gigachat☆57Updated last year
- EasyPortrait - Face Parsing and Portrait Segmentation Dataset☆28Updated 2 months ago
- Fine tuning of the base model from OpenAI Whisper in Russian language on the dataset Sber-golos☆36Updated 2 years ago
- ☆53Updated last month
- Thin wrapper around OpenAI Whisper API with streaming support☆87Updated 3 weeks ago
- Bunch of notebooks for pre-training custom Saiga-like LLM☆13Updated 9 months ago
- Repository for the paper: "Revisiting BPR: A Replicability Study of a Common Recommender System Baseline"☆44Updated this week
- 2D Positional Embeddings for Webpage Structural Understanding 🦙👀☆93Updated 2 months ago
- ☆18Updated 2 years ago
- ☆26Updated last month
- LangChain-compatible integrations with YandexGPT and YandexGPT Embeddings☆35Updated 2 weeks ago
- RuLeanALBERT is a pretrained masked language model for the Russian language that uses a memory-efficient architecture.☆92Updated last year
- Enterprise RAG Challenge to test accuracy of different LLM-driven assistants