GenAI and LLMs development, trends and implications (11. - 17.11.2024)

New models and functionality:

• Anthropic releases new Claude models and computer use feature
• Meta Releases NotebookLlama - Open-Source PDF to podcast toolkit

Building with LLMs:

• Leveraging various deployment options - Economics of hosting Open Source LLMs
• Efficient resource management with Small Language Models (SLMs) in Edge Computing
• A step-by-step guide - Building a reliable text classification pipeline with LLMs
• A local ChatGPT-like interface + Copilot in less than 10 minutes - using Ollama, Llama3, Continue, and Open WebUI
• Turn any document into a conversation-ready AI tool with open-source AnythingLLM
• AI image generation with OpenAI DALL·E 3 using Spring AI

Using models:

• Torch Compile - 2x faster Llama 3.2 with low effort
• Music transcription with multi-modal language models

RAG:

• How to implement a basic reranking system in RAG
• An introduction to Graph RAG
• Where does the magic of RAG go from?

LLMs generally:

• Can quantum computing help improve our ability to train large neural networks encoding LLMs?
• Inference with Gemma using Dataflow and vLLM