:mag: AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.
Distilling BERT-Large. The published TinyBERT is based on BERT-Base. It would be interesting to see if using a better teacher would result in performance improvements. In case it does, we should consider using large models as teachers in later distillations #2023
Closing this issue as its an accidentally created duplicate with #2019.