PinnedPublished inGenerative AIBuild Your Own RLHF LLM — Forget Human Labelers!You know, that thing OpenAI used to make GPT3.5 into ChatGPT? You can do the same without asking strangers to rank statements.Feb 19, 20246544Feb 19, 20246544
Published inGenerative AIVideoChat AI : Talk to Any YT VideoAny YT Video. Any question. 10x your learning.Jan 755Jan 755
Published inAI AdvancesLightEval — Test any LLM against any Benchmark with 1 CLI CommandThe HuggingFace native framework for benchmarking LLMs en masseMay 18, 2024127May 18, 2024127
Published inAI AdvancesMultimodality Explained. Part II: CoordinationOn Dec 6, 2023, Google’s Gemini had been released.May 10, 2024109May 10, 2024109
Published inAI AdvancesMultimodality Explained. Part I. Fusion.How do MultiModal ML Models Really Come to Its Output?May 1, 2024105May 1, 2024105
Published inGenerative AIAI Engineer’s Guide To Building Autonomous AI Agents in 2 MinsI would have needed this when I started building agents.Apr 27, 20241981Apr 27, 20241981
Published inTowards AITurn any YT Video into a Content-Making Machine with Claude-3 and Lightning AICreate any Video-to-Text LLM Product. Literally.Apr 19, 202460211Apr 19, 202460211
Published inTowards AIBuild a Personal ML Model Registry with Replicate in 5 minsDeveloper’s Guide to Hosting any ML Model and Charging for ItApr 16, 2024108Apr 16, 2024108
Published inAI AdvancesBuild Your Own Liquid Neural Network with PyTorchWhy LNNs are so Fascinating — 2024 OverviewApr 9, 20241.4K15Apr 9, 20241.4K15
Published inTowards AI8-Bit LLM Quantization with Lightning Fabric2024 — Easiest Way to any LLM Int-8 Quantization with Lightning FabricMar 30, 2024Mar 30, 2024
Published inGenerative AILitGPT — Fastest Way To FineTune Llama-2 with LoRaBest Developer-Friendly Library to Train, Fine-Tune & Chat with any LLMMar 30, 2024Mar 30, 2024
Published inGenerative AI4-Bit VS 8-Bit Quantization Performance Comparison on Llama-2 and Falcon-7B4 or 8 Bits? That is the question!Mar 30, 2024Mar 30, 2024
Published inGenerative AIBiology Foundation Models, Explained Intuitively2024 is the Breakthrough Year for Foundation AI Biology ModelsMar 30, 2024Mar 30, 2024
Published inGenerative AIRAG Evaluation with LLM-as-a-Judge + Synthetic Dataset CreationForget Custom Human QA PairsMar 11, 20242Mar 11, 20242
Published inGenerative AIHow VCs Technically Evaluate AI StartupsWhy Mistral AI Raised €113M with a Google Doc, but you can’t raise sh**?!?Mar 4, 2024Mar 4, 2024
Published inGenerative AIThe History, Past, and Future of Large Language ModelsHow Did We Get to GPT-4?Feb 23, 20241Feb 23, 20241
Published inGenerative AII Compared PEFT-Lora vs Full Fine-Tune on Open AI’s WhisperAn experiment on OpenAI’s Whisper adjourning effectiveness of LoRA vs Full Fine-TuningFeb 10, 2024Feb 10, 2024
Published inTowards AIDirect Preference Optimization, Intuitively ExplainedThe Top Secret Behind Effective LLM Training in 2024Jan 30, 2024Jan 30, 2024