LLM News and Articles
Monday, 2024-08-12 | ||||
09:39 | Comprehensive Guide to GNN, GAT, and GCN: A Beginner’s Introduction to Graph Neural Networks After… https://medium.com/@pamperherself/comprehensive-guide-to-gnn-gat-and-gcn-a-beginners-introduction-to-graph-neural-networks-after-51d09ac043b5 | |||
09:17 | Advanced Prompt Learning : Prompt Techniques Mentioned in 4 Prompt Engineering Papers, Including… https://medium.com/@pamperherself/advanced-prompt-learning-prompt-techniques-mentioned-in-4-prompt-engineering-papers-including-66aabd67349b | |||
09:06 | Enhancing Code Generation with Advanced Reasoning and Planning Algorithms in LLMs https://emaddehnavi.medium.com/enhancing-code-generation-with-advanced-reasoning-and-planning-algorithms-in-llms-63edb4aa3501 | |||
08:45 | Deploying LLMs in AWS for job listing summarisation https://medium.com/stepstone-tech/deploying-llms-in-aws-for-job-listing-summarisation-8c009a9bed70 | |||
08:17 | AI Agents — From Concepts to Practical Implementation in Python https://towardsdatascience.com/ai-agents-from-concepts-to-practical-implementation-in-python-fb26789b1560 | |||
08:11 | OpenAI Enhanced Their API With Robust Structured Output Capabilities https://cobusgreyling.medium.com/openai-enhanced-their-api-with-robust-structured-output-capabilities-dd9f4777e069 | |||
07:56 | ReAct prompting in LLM : Redefining AI with Synergized Reasoning and Acting https://medium.com/@sahin.samia/react-prompting-in-llm-redefining-ai-with-synergized-reasoning-and-acting-c19640fa6b73 | |||
07:23 | Optimizing Docker Images for Large Language Models https://blog.stackademic.com/optimizing-docker-images-for-large-language-models-60bc1156802b | |||
07:16 | Segmentación Básica e Intermedia https://medium.com/@gshaxor/segmentaci%C3%B3n-b%C3%A1sica-e-intermedia-1459e406332e | |||
07:03 | RAG + LLama3.1 + Ollama+ Streamlit is a powerful Document Assistant https://medium.com/@christophe.atten/rag-llama3-1-ollama-streamlit-is-a-powerful-document-assistant-5514d9e8462a | |||
07:01 | Enhancing LLMs with Multi-Hop RAG: Building a Dataset to Improve Complex Query Handling and… https://readqvick.medium.com/enhancing-llms-with-multi-hop-rag-building-a-dataset-to-improve-complex-query-handling-and-5e06216eede7 | |||
06:14 | Persona Hub: The Methodology of Persona-Driven Data Synthesis https://medium.com/thedeephub/persona-hub-the-methodology-of-persona-driven-data-synthesis-c95f2bea8b74 | |||
05:58 | The Essential Guide to Text Preprocessing for Better RAG Results https://medium.com/@afolabi-lagunju/the-essential-guide-to-text-preprocessing-for-better-rag-results-c8f9f2ea557c | |||
05:29 | Retrieval Augmented Generation Frameworks: LangChain https://admantium.medium.com/retrieval-augmented-generation-frameworks-langchain-8e42a5186246 | |||
05:28 | The Transformers Arithmetic https://medium.com/@kailaspsudheer/the-transformers-arithmetic-527111099527 | |||
04:57 | Introduction to Llama2 : Part-2 Samplers https://medium.com/@utsavtiwari9936/introduction-to-llama2-part-2-samplers-bd1e637ca4b9 | |||
04:48 | Summary Blog: ReLU Strikes Back: Harnessing Activation Sparsity in Large Language Models https://blog.gopenai.com/summary-blog-relu-strikes-back-harnessing-activation-sparsity-in-large-language-models-c4480a7c0761 | |||
03:05 | Announcing My New Book: Building an LLMOps Pipeline Using Hugging Face https://devopslearning.medium.com/announcing-my-new-book-building-an-llmops-pipeline-using-hugging-face-f22d53bb8e72 | |||
02:57 | A Short Introduction to Generative AI — Part 3 of 3 https://jdejesus001.medium.com/a-short-introduction-to-generative-ai-part-3-of-3-fedca8bf9a16 | |||
02:54 | Introducing JSON Schemas for AI Data Integrity https://medium.com/thedeephub/introducing-json-schemas-for-ai-data-integrity-57c16c296266 | |||
02:54 | Order or Chaos: Why groups of intelligent agents may exhibit unexpected behaviour https://medium.com/@isaacdonnelly/order-or-chaos-why-groups-of-intelligent-agents-may-exhibit-unexpected-behaviour-2c8dc835a6f4 | |||
02:35 | Mastering PowerPoint Creation with RAG-Powered Automation in Google Colab https://abxda.medium.com/mastering-powerpoint-creation-with-rag-powered-automation-in-google-colab-e3499015d6d6 | |||
01:47 | La Fábrica de Inteligencia ¿Cómo se construye un ChatGPT? https://medium.com/@csantacruz_42638/la-f%C3%A1brica-de-inteligencia-c%C3%B3mo-se-construye-un-chatgpt-fdc0ef324acc | |||
01:36 | Correctyly Set up tp Unleash the Power Of OLLAMA both as a local service and Remote Service. https://kaustavmukherjee-66179.medium.com/correctyly-set-up-tp-unleash-the-power-of-ollama-both-as-a-local-service-and-remote-service-975948b06ae5 | |||
01:00 | We’re Not in a AI Bubble https://medium.com/@jaycruz/were-not-in-a-ai-bubble-06ea5c9fe00f | |||
00:00 | The Future is Structured: OpenAI’s Game-Changing Outputs https://hammadulhaq.medium.com/the-future-is-structured-openais-game-changing-outputs-e0203f5e5040 | |||
00:00 | The Future is Structured: OpenAI’s Game-Changing Outputs https://medium.com/geekculture/the-future-is-structured-openais-game-changing-outputs-e0203f5e5040 | |||
00:00 | Tool Use, Unified https://huggingface.co/blog/unified-tool-use | |||
00:00 | Welcome FalconMamba: The first strong attention-free 7B model https://huggingface.co/blog/falconmamba | |||
Sunday, 2024-08-11 | ||||
23:05 | AI: An overview of common LLM benchmarks https://miller-hodeem.medium.com/ai-an-overview-of-common-llm-benchmarks-be4e430c96b2 | |||
22:44 | Unveiling the Magic: Understanding Large Language Models (LLMs) and Getting Started with Open… https://medium.com/@DaveLumAI/unveiling-the-magic-understanding-large-language-models-llms-and-getting-started-with-open-fc2326094f0d | |||
22:16 | Transformers Like Informer ArRevolutionizing Time-Series Forecasting https://medium.com/@bijit211987/transformers-like-informer-arrevolutionizing-time-series-forecasting-f4e4ebd7db1b | |||
21:27 | Running an LLM Locally Using Ollama https://praveenng.medium.com/running-an-llm-locally-using-ollama-92186a9e5496 | |||
20:44 | An implementation of LLMs and Gen AI utilizing a Flask REST API https://medium.com/@anirudhsekar2008/an-implementation-of-llms-and-gen-ai-utilizing-a-flask-rest-api-677769db8224 | |||
20:37 | InsightCopilot — Email Interface https://verticalserve.medium.com/insightcopilot-email-interface-249c6e239dff | |||
20:01 | Understanding LLMs: Types, Versions, and Their Evolution https://medium.com/@devhuria60/understanding-llms-types-versions-and-their-evolution-d1c8606d2ff7 | |||
19:34 | An in-depth pipeline to help reduce air pollution using knowledge graphs, Llama 2 and Neo4j https://medium.com/@NainikaBaliga/an-in-depth-pipeline-to-help-reduce-air-pollution-using-knowledge-graphs-llama-2-and-neo4j-847ba0fd7e8c | |||
19:14 | An alternate to Transformers: Diving into the paradigm of State Space Models, from Structured SSMs… https://medium.com/@ashir.rahman25/an-alternate-to-transformers-diving-into-the-paradigm-of-state-space-models-from-structured-ssms-c1ba87ded44c | |||
19:05 | Responsible AI for Generative AI https://medium.com/@neeraj051098/responsible-ai-for-generative-ai-7dfa8db8e59c | |||
19:04 | Testing LLMs logic & reasoning through codes https://medium.com/@haidar.joumaa/testing-llms-logic-reasoning-through-codes-507492d4dc56 | |||
18:55 | LLMs Can Fake It, But They Can’t Make It: The Limits of Curve Fitting on the Road to AGI https://medium.com/@meirgotroot/llms-can-fake-it-but-they-cant-make-it-the-limits-of-curve-fitting-on-the-road-to-agi-2a5e3f78e2ba | |||
18:33 | Introducing the Hrida T2SQL 128k Model https://medium.com/@hrida.aiofficial/introducing-the-hrida-t2sql-128k-model-f146a83a8189 | |||
18:30 | Top Python Libraries for Machine Learning in 2024 https://medium.com/@awaleedpk/top-python-libraries-for-machine-learning-in-2024-07c7c88aee32 | |||
18:28 | AI Agents: Useful and Practical Proof of Concept Using Autogen https://postbio.medium.com/ai-agents-useful-and-practical-proof-of-concept-using-autogen-67d5d22a273f | |||
18:17 | Fine-Tuning Sentiment Analysis Model https://ai.plainenglish.io/fine-tuning-sentiment-analysis-model-db088da71879 | |||
17:25 | Embracing Generative AI in Agriculture https://graindatasolutions.medium.com/embracing-generative-ai-in-agriculture-eef8b1ef56b9 | |||
17:25 | Prompt Engineering 102 https://medium.com/@coyle_41098/prompt-engineering-102-c3df3f8ea7c0 | |||
17:11 | Quick and Easy: Sentiment Analysis with LLM https://medium.com/@beam_villa/quick-and-easy-sentiment-analysis-with-llm-c61c562d059c | |||
16:47 | Interview Questions on LLM’s, RAG , Embeddings , Prompting — Part 1 https://medium.com/@purnima.msb/interview-questions-on-llms-rag-embeddings-prompting-part-1-fe2b1168b0b2 | |||
16:44 | SLM in Action: Arcee Nova 72B local inference on math and code with Open WebUI and Ollama https://julsimon.medium.com/slm-in-action-arcee-nova-72b-local-inference-on-math-and-code-with-open-webui-and-ollama-cc9a11a58aba | |||
16:28 | ChatGPT unexpectedly began speaking in a user's cloned voice during testing https://arstechnica.com/information-technology/2024/08/chatgpt-unexpectedly-began-speaking-in-a-users-cloned-voice-during-testing/ | |||
16:08 | LLM Transformers : Part 1 https://medium.com/@nishi.paul.in/llm-transformers-part-1-5cf8438e6c12 | |||
16:06 | Entering the space of Generative AI: A Practical Approach https://kanishkamukherjee.medium.com/entering-the-space-of-generative-ai-a-practical-approach-a9b495304a1d | |||
16:06 | Part C of The Pictures That Bots Made: Renaissance and Pirate Ship https://medium.com/@aleksmilanov/part-c-of-the-pictures-that-bots-made-renaissance-and-pirate-ship-82c51b8520bb | |||
15:45 | RAG Evaluation Metrics Explained: A Complete Guide https://medium.com/@med.el.harchaoui/rag-evaluation-metrics-explained-a-complete-guide-dbd7a3b571a8 | |||
15:34 | Reasoning and Planning Algorithms with LLMs https://medium.com/@yugank.aman/reasoning-and-planning-algorithms-with-llms-804c5b16fe17 | |||
15:13 | Introducing Llama 3.1 by Meta: A New Era in LLM Innovation https://medium.com/@xanthophile10/introducing-llama-3-1-by-meta-a-new-era-in-llm-innovation-98d5e157c3d7 | |||
15:06 | Case Study: Leveraging LLMs with Semantic and Vector Search for a Legal Q&A System https://medium.com/@siladityaghosh/case-study-leveraging-llms-with-semantic-and-vector-search-for-a-legal-q-a-system-1daeb04a4e3e | |||
14:45 | Tell GPT It Can Scrape My https://permit.substack.com/p/tell-gpt-it-can-scrape-my | |||
14:38 | How to Use Hybrid Search for Better LLM RAG Retrieval https://towardsdatascience.com/how-to-use-hybrid-search-for-better-llm-rag-retrieval-032f66810ebe | |||
14:19 | Como a AI Generativa pode Transformar a Venda de Imóveis Através do WhatsApp https://medium.com/@matewz/como-a-ai-generativa-pode-transformar-a-venda-de-im%C3%B3veis-atrav%C3%A9s-do-whatsapp-c86942381563 | |||
13:46 | Using a small local LLM (llama 3.1 https://medium.com/@scmstorz/using-a-small-local-llm-llama-3-1-1d13223b2bbe | |||
13:40 | Corpus Linguistics: Overview https://medium.com/@riazleghari/corpus-linguistics-overview-c5cb3793b800 | |||
13:36 | GBNF Grammar: - Structure your LLM Outputs with GBNF https://medium.com/@sridevi17j/gbnf-grammar-structure-your-llm-outputs-with-gbnf-0e71965e76f9 | |||
13:28 | HyDE — Hypothetical Document Embeddings https://medium.com/@dineshkumarjaju/hyde-hypothetical-document-embeddings-9b3fbfca8d2d | |||
13:27 | Beyond ChatGPT: Pioneering the Future of Language Models with Emerging Innovations https://medium.com/@riazleghari/beyond-chatgpt-pioneering-the-future-of-language-models-with-emerging-innovations-29a83a8cdc5f | |||
13:25 | The Future of AI: Large Quantitative Models (LQMs) as the Next Frontier in Data-Driven Decision… https://medium.com/@riazleghari/the-future-of-ai-large-quantitative-models-lqms-as-the-next-frontier-in-data-driven-decision-89b9a9aad76f | |||
12:22 | Advanced RAG Retrieval Strategies: Query Routing https://ai.gopubby.com/advanced-rag-retrieval-strategies-query-routing-c7a56c6f68fa | |||
11:56 | Leveraging LLM Reasoning Enhances Personalized Recommender Systems https://arxiv.org/abs/2408.00802 | |||
09:52 | PocketPal AI: Tiny LLMs in the Pocket https://medium.com/@ghorbani59/pocketpal-ai-tiny-llms-in-the-pocket-6a65d0271a75 | |||
09:09 | Fine-Tuning LLMs with Reinforcement Learning (PPO) and PEFT: Automating RLHF https://bobrupakroy.medium.com/fine-tuning-llms-with-reinforcement-learning-ppo-and-peft-automating-rlhf-2d736695d2ab | |||
08:57 | Startup Playbook by Sam Altman https://playbook.samaltman.com/ | |||
08:11 | Llama3.1 70B Kullanmak mı? Hem de Hızlı, Ücretsiz ve Zahmetsiz mi??? https://medium.com/@cakirduygu/llama3-1-70b-kullanmak-m%C4%B1-hem-de-h%C4%B1zl%C4%B1-%C3%BCcretsiz-ve-zahmetsiz-mi-be407df0c685 | |||
08:06 | Creating a LLM based Chat Bot with RAG support for custom/own data using Azure OpenAI https://medium.com/@hamusingh/creating-a-llm-based-chat-bot-with-rag-support-for-custom-own-data-using-azure-openai-508f5cc43af8 | |||
08:00 | BiomedGPT: A Versatile Transformer-Based Foundation Model for Biomedical AI with Enhanced Multimodal Capabilities and Performance https://www.marktechpost.com/2024/08/11/biomedgpt-a-versatile-transformer-based-foundation-model-for-biomedical-ai-with-enhanced-multimodal-capabilities-and-performance/ | |||
07:29 | Intro to LLMs: Naruto’s Ninja Way https://mukulpatech.medium.com/intro-to-llms-narutos-ninja-way-4890b589c77d | |||
07:16 | LLM Deployment with vLLM https://medium.com/@naman1011/llm-deployment-with-vllm-62e9d912a638 | |||
06:55 | Leveraging LangChain MapReduce: Summarize Large Texts and Translate into Any Language https://medium.com/@gaurav4ever98/leveraging-langchain-mapreduce-summarize-large-texts-and-translate-into-any-language-c71777385169 | |||
06:49 | How Your Kids Compete with ChatGPT https://medium.com/@penny.tse/how-your-kids-compete-with-chatgpt-9df27cc72dc8 | |||
06:00 | Where have OpenAI's founders gone? https://www.ft.com/content/638f67f7-5375-47fc-b3a7-af7c9e05b9e0 | |||
05:54 | Dequantization in Large Language Models: Enhancing Accuracy Without Compromising Efficiency https://medium.com/@amresh.kumar11/dequantization-in-large-language-models-enhancing-accuracy-without-compromising-efficiency-5e84b6149181 | |||
05:46 | A Short Introduction to Generative AI https://jdejesus001.medium.com/a-short-introduction-to-generative-ai-697b2e293cc9 | |||
05:31 | Auto-Analyst 2.0 — The AI data analytics system https://medium.com/firebird-technologies/auto-analyst-2-0-the-ai-data-analytics-system-26aec602928e | |||
05:27 | Beyond the Hype: Effective Implementation of Retrieval-Augmented Generation (RAG) https://medium.com/@dinabavli/beyond-the-hype-effective-implementation-of-retrieval-augmented-generation-rag-49b2ce3c9b23 | |||
02:43 | Transformer Architecture Explained https://medium.com/@ashwin.saraswatula/transformer-architecture-explained-ba017573b99a | |||
02:38 | Turn Any webpage and PDF into knowledge instantaneously https://medium.com/@pkang_91584/turn-any-webpage-and-pdf-into-knowledge-instantaneously-e26fcc8a71d8 | |||
02:00 | Hitting Pause on “AI” https://rom.feria.name/hitting-pause-on-ai-7212c0361daf | |||
01:39 | OpenAI’s Project Strawberry — A Wish Upon a GPT STaR? https://generativeai.pub/openais-project-strawberry-a-wish-upon-a-gpt-star-88dc978be8c2 | |||
01:38 | Will This New AI Tool Kill ChatGPT? https://generativeai.pub/will-this-new-ai-tool-kill-chatgpt-8c41b22fe5dd | |||
00:40 | LangChain4j — Inteligência Artificial com Java (Spring Boot) https://medium.com/@pedro.inacio11/langchain4j-intelig%C3%AAncia-artificial-com-java-spring-boot-0ff91b3fafb4 | |||
Saturday, 2024-08-10 | ||||
23:57 | Recursive Introspection: LLM finetuning approach to teach models how to self-improve https://medium.com/@techsachin/recursive-introspection-llm-finetuning-approach-to-teach-models-how-to-self-improve-77176f825204 | |||
22:25 | What Is the Technical Debt of Large Language Models (LLMs) and How Does It Affect Us? https://sandar-ali.medium.com/what-is-the-technical-debt-of-large-language-models-llms-and-how-does-it-affect-us-484efe4d9552 | |||
22:21 | ChatGPT Prompting: Avoiding the Wall of Text https://immodalbard.medium.com/chatgpt-prompting-avoiding-the-wall-of-text-c7549449b512 | |||
22:00 | Build a Knowledge Graph-Based Agent with Llama 3.1, Nvidia Nim, and LangChain https://neo4j.com/developer-blog/knowledge-graph-llama-nvidia-langchain/ | |||
21:25 | Hybrid search in Retrieval-augmented generation https://blog.gopenai.com/hybrid-search-in-retrieval-augmented-generation-e50b7eaa1a7a | |||
21:13 | Introduction to Ollama + Run LLM Locally + Data Privacy + Why On Google Collab? https://medium.com/@sridevi.gogusetty/introduction-to-ollama-run-llm-locally-data-privacy-f7e4e58b37a0 | |||
21:12 | Linear quantization with Hugging Face Quanto https://blog.gopenai.com/linear-quantization-with-hugging-face-quanto-222a1d29721f | |||
21:01 | Building OpenAI-Compatible API https://blog.gopenai.com/building-openai-compatible-api-1f15494a2dda | |||
20:20 | WhyHow.AI Platform Beta Update — SDK for programmatic flows https://medium.com/enterprise-rag/whyhow-ai-platform-beta-update-sdk-for-programmatic-flows-a0e33921416a | |||
20:07 | Under the Hood of RAG: A Step-by-Step Tutorial for Beginners https://medium.com/@SaphE/under-the-hood-of-rag-a-step-by-step-tutorial-for-beginners-50574b4be75c |
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803