InTDS ArchivebyMantek SinghLLM for Synthetic Time Series Data GenerationWe recently participated and won the grand prize of $10,000 in the Brembo hackathon, where the task was to use Generative AI to create new…Oct 26, 20236Oct 26, 20236
Cobus GreylingA New Prompting Approach From DeepMind Called Analogical PromptingModern LLMs acquire vast knowledge ranging over various problems during training. Via Analogical Prompting, explicitly prompting an LLM to…Oct 25, 20235Oct 25, 20235
InTDS ArchivebyMarco PeixeiroTimeGPT: The First Foundation Model for Time Series ForecastingExplore the first generative pre-trained forecasting model and apply it in a project with PythonOct 24, 202323Oct 24, 202323
Saurav JoshiRetrieval Augmented Generation for Medical Question-Answering with Llama-2–7bExploring the Capabilities of Llama-2–7b for Retrieval Augmented Generation in the Medical Domain using AWSOct 6, 20233Oct 6, 20233
InLlamaIndex BlogbyRavi ThejaNVIDIA Research: RAG with Long Context LLMsThis blog post dives into NVIDIA’s recent study comparing retrieval-augmentation with and without long-context LLMs.Oct 22, 20231Oct 22, 20231
InLlamaIndex BlogbyKiran Neelakanda PanickerMastering PDFs: Extracting Sections, Headings, Paragraphs, and Tables with Cutting-Edge ParserDespite recent motivation to utilize NLP for wider range of real world applications, most NLP papers, tasks and pipelines assume raw, clean…Oct 18, 202314Oct 18, 202314
InDev GeniusbyMilind DeoreTranspose HuggingFace Models to GGUF FormatLlama.cpp provides an efficient method for running LLMs on both CPUs and GPUs. However, these two frameworks utilize different file formats…Sep 23, 20235Sep 23, 20235
RubentakGive OpenAI models internet access using LangChain🦜🔗Taking AI to the next levelMay 8, 20231May 8, 20231
InBetter ProgrammingbyWenqi GlantzFine-Tuning GPT-3.5 RAG Pipeline with GPT-4 Training DataNVIDIA SEC 10-K filing analysis before and after fine-tuningSep 4, 20232Sep 4, 20232
InTDS ArchivebyVyacheslav EfimovLarge Language Models: TinyBERT — Distilling BERT for NLPUnlocking the power of Transformer distillation in LLMsOct 21, 2023Oct 21, 2023
InNeo4j Developer BlogbyTomaz BratanicUsing a Knowledge Graph to Implement a DevOps RAG ApplicationLeveraging knowledge graphs to power LangChain ApplicationsOct 18, 20232Oct 18, 20232
InLevel Up CodingbyRyan ShrottIntegrate AutoGen into your Chatbot: Code Interpreter CloneDiscover how to harness the power of AutoGen to develop an advanced code interpreter chatbot using Chainlit.Oct 10, 20239Oct 10, 20239
InTDS ArchivebyDonato RiccioExtending Context Length in Large Language ModelsHow to turn your Llama into a GiraffeOct 15, 20235Oct 15, 20235
Qendel AIThe Easiest and Cheapest Way to Deploy Finetuned Mistral 7B Instruct Model (or Any Model)An Easy and Cheap Way to Deploy a Finetuned Mistral 7B Instruct Model (or any model) on HuggingFace Inference EndpointsOct 12, 20233Oct 12, 20233
Venelin ValkovAutoGen — Build Powerful AI Agents with ChatGPT/GPT-4Explore AutoGen, a Microsoft library that lets you create LLM applications with agents. These agents can communicate and help you solve…Oct 17, 20233Oct 17, 20233
Cobus GreylingLarge Language Model (LLM) Stack Version 5In my attempt to interpret what is taking place and where the market is moving, I created a product taxonomy defining the various LLM…Oct 19, 20231Oct 19, 20231
InTDS ArchivebyBenjamin MarieQA-LoRA: Fine-Tune a Quantized Large Language Model on Your GPUQuantization-aware fine-tuningOct 14, 20231Oct 14, 20231
InGoPenAIbyQendel AIRAG Pipeline With Mistral 7B Instruct Model: A step-by-step guideBuilding RAG pipeline with Mistral 7B Instruct Model: A beginner’s guideOct 5, 20234Oct 5, 20234
Akriti UpadhyayEfficient Information Retrieval with RAG WorkflowImproving Search and Summarization using Retrieval Augmented GenerationOct 9, 20235Oct 9, 20235
InTowards AIbyRyan NguyenRAG Pipeline Pitfalls: The Untold Challenges of Embedding TableA typical journey of building the RAG pipeline from Zero to Something and a guide on handling tables of RAG with LlamaIndexOct 8, 20233Oct 8, 20233
