Amir Ziaimlbench — ML benchmarking utilsSimple utilities and visualizations to help with doing the right thing when you’re running ML experiments.Aug 19, 2024Aug 19, 2024
Amir Ziaimlbench — ML benchmarking utilsSimple utilities and visualizations to help with doing the right thing when you’re running ML experiments.Aug 19, 2024Aug 19, 2024
InTDS ArchivebyBhavin JawadeTuning-Free Longer Context Lengths For LLMs — A Review of Self-Extend (LLM Maybe LongLM)A simple strategy to enable LLMs to consume longer context length inputs during inference without the need for finetuning.Jan 4, 20241Jan 4, 20241
InTDS ArchivebyShenyang(Andy) HuangTemporal Graph Learning in 2024Continue the journey for evolving networksJan 18, 20241Jan 18, 20241
InTDS ArchivebyCameron R. Wolfe, Ph.D.Supervised Fine-Tuning (SFT) with Large Language ModelsUnderstanding how SFT works from idea to a working implementation…Jan 16, 20243Jan 16, 20243
InTDS ArchivebyNikita KiselovBuilding, Evaluating and Tracking a Local Advanced RAG System | Mistral 7b + LlamaIndex + W&BLearn how to build, evaluate and track advanced RAG system using local Mistral-7b, LlamaIndex, and W&B. Step-by-step guide with code.Jan 19, 20243Jan 19, 20243
InGenerative AIbyFabio ChiusanoWeekly AI and NLP News — January 15th 2024OpenAI releases the GPT Store, OpenAI vs The New York Times, and the Mixtral-of-Experts paperJan 15, 2024Jan 15, 2024
InTDS ArchivebyWenqi GlantzDemocratizing LLMs: 4-bit Quantization for Optimal LLM InferenceA deep dive into model quantization with GGUF and llama.cpp and model evaluation with LlamaIndexJan 15, 20243Jan 15, 20243
InTDS ArchivebyBenjamin MarieRun Mixtral-8x7B on Consumer Hardware with Expert OffloadingFinding the right trade-off between memory usage and inference speedJan 11, 20243Jan 11, 20243
InTowards AIbyFlorian JuneA Detailed Explanation of Mixtral 8x7B ModelIncluding principles, diagrams, and code analysis.Jan 9, 20241Jan 9, 20241
InAIGuysbyVishal RajputMamba: Can it replace Transformers?Solving the quadratic scaling problem of Self-Attention.Jan 8, 20249Jan 8, 20249
InStackademicbyFabio MatricardiTiny-Vicuna-1B is the lightweight champion of the Tiny ModelsCommand and Conquer: the smallest Vicuna flavor is the Tiny Master of Instruction, answers your every call (Flawlessly!)Jan 11, 20244Jan 11, 20244
Fireworks.aiFireAttention — Serving Open Source Models 4x faster than vLLM by quantizing with ~no tradeoffsServing Open Source Models 4x faster than vLLM by quantizing with ~no tradeoffsJan 8, 20241Jan 8, 20241
InData Science at MicrosoftbyAndreas StöffelbauerHow Large Language Models WorkFrom zero to ChatGPTOct 24, 202351Oct 24, 202351
InLevel Up CodingbySalvatore RaieliTabula rasa: Could We Have a Transformer for Tabular DataWe are using large language models for everything, so why not for tabular data?Jan 9, 20242Jan 9, 20242
InTDS ArchivebyMariya MansurovaCan LLMs Replace Data Analysts? Learning to CollaboratePart 3: Teaching the LLM agent to pose and address clarifying questionsJan 9, 20246Jan 9, 20246
Mastering LLM (Large Language Model)LLM Training: A Simple 3-Step Guide You Won’t Find Anywhere Else!Discover How Language Models are Trained in 3 Easy StepsOct 1, 20234Oct 1, 20234
InTDS ArchivebyMaxime LabonneExLlamaV2: The Fastest Library to Run LLMsQuantize and run EXL2 modelsNov 20, 20236Nov 20, 20236
InTDS ArchivebyMaxime LabonneExLlamaV2: The Fastest Library to Run LLMsQuantize and run EXL2 modelsNov 20, 20236Nov 20, 20236
InTDS ArchivebyMaxime LabonneFine-tune a Mistral-7b model with Direct Preference OptimizationBoost the performance of your supervised fine-tuned modelsJan 1, 20249Jan 1, 20249
