SebastianRetrieval Augmented Generation Frameworks: AutoGenWith an Retrieval Augmented Generation (RAG) framework, documents relevant for a given user query can be extracted from a database and used…5d ago5d ago
SebastianRetrieval Augmented Generation Frameworks: HayStackLarge Language Models need accurate and up-to-date information when generating text for specific domains or with content from private data…Aug 26Aug 26
SebastianRetrieval Augmented Generation Frameworks: LangChainLarge Language Models have one crucial limitation: They can only generate text determined by the training material that they consumed. To…Aug 12Aug 12
SebastianQA System Design with LLMs: Prompt EngineeringLarge Language Models are vast neural networks trained on billions of text token. They can work with natural language in a…Jul 29Jul 29
SebastianQA System Design with LLMs: Practical Instruction Fine-Tuning Gen3 and Gen4 modelsLarge Language Models are vast neural networks trained on billions of text token. They can work with natural language in a…Jul 15Jul 15
SebastianInstruction Fine-Tuning: Dataset and Library LandscapeLarge Language Models have fascinating abilities to understand and output natural language texts. From knowledge databases to assistants…Jul 11Jul 11
SebastianLLM Fine-Tuning: Domain Embeddings with GPT-3Starting in 2023, Large Language Models evolved to form or be a component of information retrieval systems. In such a system, domain…Jun 17Jun 17
SebastianLLM Fine-Tuning Workshop: Improve Question-Answering SkillsLarge Language Models are a fascinating technology that becomes embedded into several applications and products. In my blog series about…Jun 3Jun 3
SebastianLLM Fine-Tuning Workshop: Improve Linguistic SkillsLarge Language Models are a fascinating technology capable of many classic and advanced NLP tasks, from text-classification and sentiment…May 20May 20
SebastianFine-Tuning LLMs: Technical OverviewLLMs are ubiquitous tools used for the processing and producing of natural language texts. Since its inception in 2018, several generations…May 6May 6