M K Pavan KumarBuilding Robust LLM Applications for Production grade scale using LiteLLM.LiteLLM is an innovative proxy that simplifies the integration of various large language models (LLMs) into applications by providing a…Jul 12Jul 12
Gabriel BotsieinGenerative AIChain of Density Prompting: A New Way to Generate Better Summaries with Generative AISummarising content is a difficult task. The post explores the:Oct 1, 2023Oct 1, 2023
Fareed KhaninLevel Up CodingBuilding a Million-Parameter LLM from Scratch Using PythonA Step-by-Step Guide to Replicating LLaMA ArchitectureDec 7, 202332Dec 7, 202332
Fareed KhaninLevel Up CodingBuilding LLaMA 3 From Scratch with PythonCode Your Own Billion Parameter LLMMay 2813May 2813
Vishal RajputinAIGuysPrompt Engineering Is Dead: DSPy Is New Paradigm For PromptingDSPy Paradigm: Let’s program — not prompt — LLMsMay 2940May 2940
DatadriftersLlama 3 Powered Voice Assistant: Integrating Local RAG with Qdrant, Whisper, and LangChainVoice-enabled AI applications will forever change how we interact with technology.May 174May 174
Pavan BelagattiinLevel Up CodingEvaluating Large Language Models: A Developer’s Guide!Large Language Models (LLMs) like GPT-4, Claude, LLama and Gemini have contributed a lot to the AI community, helping organizations build…May 14May 14
Michael PhiinTowards Data ScienceIllustrated Guide to LSTM’s and GRU’s: A step by step explanationHi and welcome to an Illustrated Guide to Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRU). I’m Michael, and I’m a Machine…Sep 24, 2018116Sep 24, 2018116
Srijanie Dey, PhDinTowards Data ScienceDeep Dive into Self-Attention by Hand✍︎Explore the intricacies of the attention mechanism responsible for fueling the transformersApr 226Apr 226
Ankur ManikandaninTowards Data ScienceHow does temperature impact next token prediction in LLMs?Exploration vs. ExploitationMay 61May 61
Robert A. GonsalvesinTowards Data ScienceFanFabler: Fine-Tuning Llama 3 to Be a Multilingual Fanfic Writing AssistantHow I used a custom training dataset and information retrieval for global storytelling. 好样的! Bravo! वाह! ¡Guau! 브라보!May 71May 71
Srijanie Dey, PhDinTowards Data ScienceDeep Dive into LlaMA 3 by Hand ✍️Explore the nuances of the transformer architecture behind Llama 3 and its prospects for the GenAI ecosystemMay 317May 317
Yujian TanginPlain Simple SoftwareThe LLM App Stack — 2024The tools you need to know, what they do, and how they’re differentMay 1511May 1511
Mandar Karhade, MD. PhD.inTowards AIRun Local LLM Inference10x Faster (244 TOK/s): PyTorch IIThere are many ways to run, here is a quick overviewDec 2, 20234Dec 2, 20234
ByteferLocally Running Embedding Services That Surpasses OpenAI Text-Embedding-Ada-002 and…Revolutionize Your Data Security Game: Quick and Seamless Deployment of Local Models for Unparalleled Privacy!Apr 14Apr 14
Ömer KARABACAKinITNEXTStep-by-Step Guide to Running Latest LLM Model Meta Llama 3 on Apple Silicon Macs (M1, M2 or M3)Are you looking for an easiest way to run latest Meta Llama 3 on your Apple Silicon based Mac? Then you are at the right place! In this…Apr 19Apr 19
Júlio AlmeidainPython in Plain EnglishClaude 3: The king of data extractionUnleashing the Future of Data Extraction: Inside Claude 3’s Revolutionary LeapMar 276Mar 276
Dr James RavenscroftSelf-hosting Llama 3 on a home serverSelf-hosting Llama 3 as your own ChatGPT replacement service using a 10 year old graphics card and open source components.Apr 206Apr 206
Pavan BelagattiinLevel Up CodingA Comprehensive Guide to Reducing LLM Hallucinations!Large language models (LLMs) have gained great momentum due to their inherent advantages for organizations building gen AI applications…Apr 30Apr 30
Faire Data TeaminThe CraftFine-tuning Llama3 to measure semantic relevance in searchWritten by: Quentin Hsu, Wayne ZhangApr 292Apr 292