Clara GadelhoMar 2610 minRAG vs Large Context Models: How Gemini 1.5 changes the worldShould you use GPT4 or other models with RAG or just send everything in the context to Gemini 1.5?
Miguel Carreira NevesJan 297 minLLM Mixture of Experts ExplainedExplaining Mixture of Experts (MoE): GPT4 is just 8 smaller Expert models; Mixtral is just 8 Mistral models. Advantages and disadvantages.
Miguel Carreira NevesDec 8, 202313 minAdvanced Prompt Engineering - Practical ExamplesThis blog post will cover more complex state-of-the-art methods in prompt engineering including Chains, Agents, and more.
Miguel Carreira NevesSep 19, 202310 minWhat are Quantized LLMs?Quantization is a technique used to compact LLMs. What methods exist and how to quickly start using them?