whisper.cpp HTTP transcription server with OAI-like API in Docker

Few methods of splitting text to chunks

Простой пример того, как при помощи сплиттеров и эмбеддеров доступных через LangChain можно построить граф знаний

Bunch of notebooks for pre-training custom Saiga-like LLM

Collection of scripts for training bert-based embedder for Russian<>English embeddings extraction

Is a framework designed to enhance the performance and flexibility of large language models by dynamically selecting and integrating specialized LoRA adapters based on the input query.