Author(s): Barhoumi Mosbeh Originally published on Towards AI. Ollama multi-modal Ollama has just announced its official support for the Llama 3.2 Vision models. The Llama 3.2 Vision models come in two sizes: 11 billion and 90 billion parameters. In this article, I …

Author(s): Barhoumi Mosbeh Originally published on Towards AI. source In a previous article, we looked at contextual retrieval from Anthropic, which is their context enhancement technique for improving RAG systems. But there’s another technique called late chunking in long-context embedding models, which …

Author(s): Barhoumi Mosbeh Originally published on Towards AI. Microsoft has silently released OmniParser, an open-source tool designed to convert screenshots into structured, easy-to-interpret elements for Vision Agents. The goal of this tool is to advance the emerging field of enabling large language …

Author(s): Barhoumi Mosbeh Originally published on Towards AI. unsloth Why Fine-Tune When We Have RAG? It’s a question I see a lot — with RAG (Retrieval-Augmented Generation) becoming increasingly popular, why bother with fine-tuning at all? While RAG is fantastic for many …

Author(s): Barhoumi Mosbeh Originally published on Towards AI. I’m working as a machine learning engineer, and I frequently use Claude or ChatGPT to help me write code. However, in some cases, the model starts to repeat itself or hallucinate, especially during complex …

Author(s): Barhoumi Mosbeh Originally published on Towards AI. The Rise of LLMs LLMs are super-powerful tools. I remembered the first time ChatGPT was released, I was saying hell no, I will lose my job (before even getting one), but… then I saw …