Large-Language-Models on Noureddine RAMDIhttps://ramdi.fr/tags/large-language-models/Recent content in Large-Language-Models on Noureddine RAMDIHugoenSat, 23 May 2026 20:41:27 +0000Graph-R1: Reinforcement learning to train LLMs for reasoning over knowledge graphshttps://ramdi.fr/github-stars/graph-r1-reinforcement-learning-to-train-llms-for-reasoning-over-knowledge-graphs/Sat, 23 May 2026 20:41:14 +0000https://ramdi.fr/github-stars/graph-r1-reinforcement-learning-to-train-llms-for-reasoning-over-knowledge-graphs/Graph-R1 trains large language models with reinforcement learning to reason over knowledge graphs, cycling through think-query-retrieve-rethink steps for complex knowledge tasks.Hands-On Large Language Models: A practical, visual journey through LLM engineeringhttps://ramdi.fr/github-stars/hands-on-large-language-models-a-practical-visual-journey-through-llm-engineering/Mon, 04 May 2026 10:23:02 +0000https://ramdi.fr/github-stars/hands-on-large-language-models-a-practical-visual-journey-through-llm-engineering/Explore the Hands-On Large Language Models repo, a Jupyter notebook-based practical guide from fundamentals to fine-tuning, designed for hands-on LLM learning on free Colab GPUs.MegaTrain: RAM-centric training architecture for 100B+ parameter LLMs on a single GPUhttps://ramdi.fr/github-stars/megatrain-ram-centric-training-architecture-for-100b-parameter-llms-on-a-single-gpu/Mon, 04 May 2026 10:23:01 +0000https://ramdi.fr/github-stars/megatrain-ram-centric-training-architecture-for-100b-parameter-llms-on-a-single-gpu/MegaTrain enables training 100B+ parameter LLMs on a single GPU by offloading all parameters to CPU RAM and streaming layers to GPU. Supports HuggingFace models and multi-GPU data parallelism without NCCL.