LLM News and Articles
Tuesday, 2024-07-23 | ||||
22:55 | PEQUENOS MODELOS DE LINGUAGEM
Ricardo Murer
Julho 2024 https://medium.com/@rdmurer64/pequenos-modelos-de-linguagem-ricardo-murer-julho-2024-6a1e55a18f19 | |||
22:41 | Meet Llama 3.1, Meta new Open Source LLM with High Performance and Cost Efficiency https://medium.com/@AhmedF/meet-llama-3-1-meta-new-open-source-llm-with-high-performance-and-cost-efficiency-d37174b1f967 | |||
22:19 | Iterating on an HTML resume with GPT-4o via cURL https://www.johncs.com/posts/gpt-assisted-html-resume | |||
21:55 | How Document Chunk Overlap Affects a RAG Pipeline https://ai.gopubby.com/how-document-chunk-overlap-affects-a-rag-pipeline-9b8931845c20 | |||
21:39 | Framing Truth in the Age of Generative AI https://medium.com/@benji_ai/framing-truth-in-the-age-of-generative-ai-73f7c2672e54 | |||
21:35 | AI Agentic Frameworks https://medium.com/@ga3435/ai-agentic-frameworks-2022fe43e78a | |||
21:23 | Can TOP 13 LLM Explain Fractals? https://medium.com/@cristian.nedelcu/can-top-13-llm-explain-fractals-e7fdc2f5e910 | |||
21:00 | Llama 3.1 — 405b, 70B & 8B: The new Open Source LLM https://medium.com/@ninapepite/llama-3-1-405b-70b-8b-the-new-open-source-llm-2420082b4632 | |||
21:00 | Progressive Learning Framework for Enhancing AI Reasoning through Weak-to-Strong Supervision https://www.marktechpost.com/2024/07/23/progressive-learning-framework-for-enhancing-ai-reasoning-through-weak-to-strong-supervision/ | |||
20:55 | Development of AI-Powered Remittance Chatbot https://medium.com/@adetunjijeremiah1/development-of-ai-powered-remittance-chatbot-63cc29fddd32 | |||
20:46 | OpenAI removes AI safety leader Mądry, a onetime ally of CEO Altman https://www.theinformation.com/articles/openai-removes-ai-safety-leader-m-dry-a-onetime-ally-of-ceo-altman | |||
20:45 | The Open-Source AI Revolution by Meta with Llama 3.1 https://generativeai.pub/the-open-source-ai-revolution-by-meta-with-llama-3-1-f105366b3c8f | |||
20:42 | Why Llama 3.1 is Important https://timkellogg.me/blog/2024/07/23/llama-3.1 | |||
20:31 | AI Race Heats Up: xAI’s Supercluster and Meta’s Llama 3.1 Shake Up the Industry https://vidrihmarko.medium.com/ai-race-heats-up-xais-supercluster-and-meta-s-llama-3-1-shake-up-the-industry-751a2cdfc7c8 | |||
20:31 | AI Race Heats Up: xAI’s Supercluster and Meta’s Llama 3.1 Shake Up the Industry https://blog.gopenai.com/ai-race-heats-up-xais-supercluster-and-meta-s-llama-3-1-shake-up-the-industry-751a2cdfc7c8 | |||
20:30 | Show HN: Finetune Llama-3.1 2x faster in a Colab https://colab.research.google.com/drive/1Ys44kVvmeZtnICzWz0xgpRnrIOjZAuxp | |||
20:16 | Meta Releases Llama 3.1 AI Model for Free, Sparking Debate on Open Source AI https://medium.com/nomadmedia/meta-releases-llama-3-1-ai-model-for-free-sparking-debate-on-open-source-ai-acfe4a2f3896 | |||
20:13 | Meta releases an open-weights GPT-4-level AI model, Llama 3.1 405B https://arstechnica.com/information-technology/2024/07/the-first-gpt-4-class-ai-model-anyone-can-download-has-arrived-llama-405b/ | |||
20:11 | Identifying Intents Efficiently with Serverless Fine-tuning https://medium.com/snowflake/identifying-intents-efficiently-with-serverless-fine-tuning-1d3d11b0802f | |||
20:10 | QuickRead: Llama 3.1: Scaling New Heights in Multilingual AI and Beyond https://readquick.medium.com/quickread-llama-3-1-scaling-new-heights-in-multilingual-ai-and-beyond-4d1cb16f6ccc | |||
20:01 | Low-cost, Low-latency, Customizable Chatbots for Your Websites and Web Apps Using GPT-4o mini https://pub.towardsai.net/low-cost-low-latency-customizable-chatbots-for-your-websites-and-web-apps-using-gpt-4o-mini-5089e6776702 | |||
19:59 | Uncensored AI just added Llama 405B - (use toggle) (free access) https://www.aiuncensored.info/About%20Us | |||
19:51 | How can your LLM explain an image to users? (Not just another OCR solution) https://medium.com/@tselvaraj/how-can-your-llm-explain-an-image-to-users-not-just-another-ocr-solution-128a669c956f | |||
19:50 | GPT-4o Mini Fine-tuning https://platform.openai.com/docs/guides/fine-tuning | |||
19:27 | Estimating the Audience Segments of a Website Using Artificial Intelligence https://medium.com/@mauriciotorob/estimating-the-audience-segments-of-a-website-using-artificial-intelligence-f1ead9e9355e | |||
19:16 | Part A of Pictures That Bots Made: Astronomy, Science and History https://medium.com/@aleksmilanov/part-a-of-pictures-that-bots-made-astronomy-science-and-history-e068b629e4c3 | |||
19:13 | Llama 3.1, the most advanced AI model from Meta https://deasadiqbal.medium.com/llama-3-1-the-most-advanced-ai-model-from-meta-b2eded886ebe | |||
19:06 | Sam Altman's House Sucks, Lawsuit Says https://gizmodo.com/openai-ceo-sam-altmans-house-sucks-lawsuit-says-2000475933 | |||
18:47 | Quest for Proof Automation: What can ChatGPT4 do? simple multiplication (part 1/N) https://medium.com/@uwyang/quest-for-proof-automation-what-can-chatgpt4-do-simple-multiplication-part-1-n-9b4d673fb55d | |||
18:10 | How to Download Llama 3.1 405B https://wpchen-roc.medium.com/how-to-download-llama-3-1-405b-82c6ad1b891d | |||
18:09 | Prompt Engineering To Enhance LLM Responses https://medium.com/@perepc/prompt-engineering-to-enhance-llm-responses-986d5fa741e8 | |||
17:50 | Generative AI Fundamentals: Deploying LLMs with OpenVINO™ https://medium.com/openvino-toolkit/generative-ai-fundamentals-deploying-llms-with-openvino-3057861f6feb | |||
17:49 | Trust at scale: Auto-evaluation for high-stakes LLM accuracy https://blog.elicit.com/auto-evaluation/ | |||
17:48 | Introduction to the Open Artificial Knowledge Dataset https://medium.com/@elmo92/introduction-to-the-open-artificial-knowledge-dataset-6ad78bf458ee | |||
17:44 | What is Meta Llama 3.1 405B? https://wpchen-roc.medium.com/what-is-meta-llama-3-1-405b-276058fedf09 | |||
17:18 | Transformer Architecture Metrics Cheat Sheet: GPT-3 as Reference https://medium.com/@jeremywang_83970/transformer-architecture-metrics-cheat-sheet-gpt-3-as-reference-1e633bd3ef6f | |||
16:57 | Llama as a System https://github.com/meta-llama/llama-agentic-system | |||
16:50 | AI’s WYSIWYG Moment: Charting AI’s Next Interface Revolution https://ai.plainenglish.io/ais-wysiwyg-moment-charting-ai-s-next-interface-revolution-7774fcb17517 | |||
16:50 | Small Language Models are the Future https://medium.com/thoughts-on-machine-learning/small-language-models-are-the-future-6e8909567198 | |||
16:46 | Meta Llama 3.1 405B https://openrouter.ai/models/meta-llama/llama-3.1-405b-instruct | |||
16:44 | Introducing Llama 3.1: Meta’s Game-Changing AI Model Transforming the Business Landscape https://medium.com/ai-news-nuggets/introducing-llama-3-1-metas-game-changing-ai-model-transforming-the-business-landscape-58f3ad00d75e | |||
16:41 | Chat with Meta Llama 3.1 405B https://llama3.replicate.dev/ | |||
16:28 | Meta AI released their latest open-source AI model Llama 3.1 https://medium.com/@piotrmacai0/meta-ai-released-their-latest-open-source-ai-model-llama-3-1-3a7393f2de4e | |||
16:22 | Breaking Down and Analyzing the Official MultiVector Retriever Sample Code https://medium.com/llm-study-diary-a-beginners-path-through-ai/breaking-down-and-analyzing-the-official-multivector-retriever-sample-code-e6d8360d10e0 | |||
16:14 | AI & the Trolley Problem https://augmentedstartups.medium.com/ai-the-trolley-problem-bd77033c7da0 | |||
16:14 | ICML 2024 Orals (top 10%): Summaries of interesting papers https://prakashkagitha.medium.com/icml-2024-orals-top-10-summaries-of-interesting-papers-53c415a891de | |||
16:14 | N&L’dan Temmuz Ayı Yapay Zeka ve NLP Bülteni — Temmuz 2024 https://medium.com/nane-limon/n-ldan-temmuz-ay%C4%B1-yapay-zeka-ve-nlp-b%C3%BClteni-temmuz-2024-edb5b5af19c3 | |||
16:06 | Llama 3.1: 405B, the largest openly available model released https://github.com/meta-llama/llama-models/blob/main/models/llama3_1/MODEL_CARD.md | |||
16:02 | LangGraph: The Future of Production-Ready AI Agents https://odsc.medium.com/langgraph-the-future-of-production-ready-ai-agents-56e44180a76a | |||
15:59 | Small Language Models: The New Superheroes of AI https://blog.cuminai.com/small-language-models-the-new-superheroes-of-ai-c3c02b523590 | |||
15:57 | A Contemplation: Orwell in the ChatGPT Universe https://historicaorg.medium.com/a-contemplation-orwell-in-the-chatgpt-universe-f6febf99c4dc | |||
15:52 | Meta Llama 3.1 now available on Cloudflare Workers AI https://blog.cloudflare.com/meta-llama-3-1-available-on-workers-ai | |||
15:51 | Zuck pod interview: Llama 3.1 405B, Meta's open-source AI beats GPT-4 https://twitter.com/rowancheung/status/1815763595197616155 | |||
15:46 | Become an LLM Expert: 10 NLP Prompts Every Beginner Should Know https://levelup.gitconnected.com/become-an-llm-expert-10-nlp-prompts-every-beginner-should-know-e4e276856860 | |||
15:40 | Groq Supercharges Fast AI Inference for Meta Llama 3.1 https://wow.groq.com/news_press/groq-supercharges-fast-ai-inference-for-llama-3-1/ | |||
15:32 | Meta unleashes Llama 3.1 https://medium.com/@simeon.emanuilov/meta-unleashes-llama-3-1-f0064e4f86c0 | |||
15:30 | Implementing Map-Reduce with LangGraph: Creating Flexible Branches for Parallel Execution https://medium.com/@astropomeai/implementing-map-reduce-with-langgraph-creating-flexible-branches-for-parallel-execution-b6dc44327c0e | |||
15:28 | Llama 3.1 405B on Groq https://wow.groq.com/now-available-on-groq-the-largest-and-most-capable-openly-available-foundation-model-to-date-llama-3-1-405b/ | |||
15:26 | From Sentiment to Empathy: Enhancing Customer Experiences with AI https://medium.com/@ibbyrahmani/from-sentiment-to-empathy-enhancing-customer-experiences-with-ai-a1855fc693aa | |||
15:24 | Understanding Large Language Models (LLM): The Power Behind Modern AI https://medium.com/@hasfatauil12/understanding-large-language-models-llm-the-power-behind-modern-ai-7f742de953b6 | |||
15:14 | How to Use Llama 3.1 405B in Germany https://towards-agi.medium.com/how-to-use-llama-3-1-405b-in-germany-3696c52b5524 | |||
15:14 | Meta releases Llama 3.1 open-source AI model to take on OpenAI https://www.theverge.com/2024/7/23/24204055/meta-ai-llama-3-1-open-source-assistant-openai-chatgpt | |||
15:13 | Llama 3.1: Our most capable models to date https://ai.meta.com/blog/meta-llama-3-1/ | |||
15:11 | How to Use Llama 3.1 405B in Europe: Best Alternatives without https://towards-agi.medium.com/how-to-use-llama-3-1-405b-in-europe-best-alternatives-without-de8d6bdd31c6 | |||
15:02 | TAI #109: Cost and Capability Leaders Switching Places With GPT-4o Mini and LLama 3.1? https://pub.towardsai.net/tai-109-cost-and-capability-leaders-switching-places-with-gpt-4o-mini-and-llama-3-1-b957648b6b70 | |||
15:02 | Generative semantic fabric // GSF https://sbagency.medium.com/generative-semantic-fabric-gsf-6befe144c9f3 | |||
14:57 | Build Knowledge Graph RAG with LlamaIndex from PDF Documents https://pengwanghello.medium.com/build-knowledge-graph-rag-with-llamaindex-from-pdf-documents-99ccef833840 | |||
14:57 | The Llama 3 Herd of Models https://ai.meta.com/research/publications/the-llama-3-herd-of-models/ | |||
14:47 | Llama 3.1 https://llama.meta.com/ | |||
14:40 | Understanding the Ways for Text-to-SQL with LLMs https://generativeai.pub/understanding-the-ways-for-text-to-sql-with-llms-df2b47c01715 | |||
14:07 | Fine-tuning a pre-trained model https://medium.com/@fahamin5149/fine-tuning-a-pre-trained-model-5c0551d035e2 | |||
12:25 | Supercharging Vector Search : The HNSW Advantage https://medium.com/@tripathinaman.1014/supercharging-vector-search-the-hnsw-advantage-533aacdd163c | |||
12:09 | How to make a moslem bot? https://medium.com/@bofandra/how-to-make-a-moslem-bot-72f2d350fec2 | |||
12:09 | Ploting the unique values in a Pandas dataframe (LLM assisted) https://medium.com/@sorin.tudor/ploting-the-unique-values-in-a-pandas-dataframe-llm-assisted-bb209851bf8b | |||
11:45 | WTU-Eval: A New Standard Benchmark Tool for Evaluating Large Language Models LLMs Usage Capabilities https://www.marktechpost.com/2024/07/23/wtu-eval-a-new-standard-benchmark-tool-for-evaluating-large-language-models-llms-usage-capabilities/ | |||
11:41 | Understanding Model Quantization for LLMs https://medium.com/@edmond.po/understanding-model-quantization-for-llms-1573490d44ad | |||
11:25 | Using LLM Inference, Apple’s Generative AI Improvements https://medium.com/@agarapuramesh/using-llm-inference-apples-generative-ai-improvements-85697e97f777 | |||
11:11 | المناهج الاستراتيجية للبحث العلمي باستخدام الذكاء الاصطناعي والنماذج اللغوية الكبيرة https://medium.com/@mashaii/%D8%A7%D9%84%D9%85%D9%86%D8%A7%D9%87%D8%AC-%D8%A7%D9%84%D8%A7%D8%B3%D8%AA%D8%B1%D8%A7%D8%AA%D9%8A%D8%AC%D9%8A%D8%A9-%D9%84%D9%84%D8%A8%D8%AD%D8%AB-%D8%A7%D9%84%D8%B9%D9%84%D9%85%D9%8A-%D8%A8%D8%A7%D8%B3%D8%AA%D8%AE%D8%AF%D8%A7%D9%85-%D8%A7%D9%84%D8%B0%D9%83%D8%A7%D8%A1-%D8%A7%D9%84%D8%A7%D8%B5%D8%B7%D9%86%D8%A7%D8%B9%D9%8A-%D9%88%D8%A7%D9%84%D9%86%D9%85%D8%A7%D8%B0%D8%AC-%D8%A7%D9%84%D9%84%D8%BA%D9%88%D9%8A%D8%A9-%D8%A7%D9%84%D9%83%D8%A8%D9%8A%D8%B1%D8%A9-79f3463504c6 | |||
10:19 | Generative AI ve Büyük Dil Modelleri: Karşılaştırma https://medium.com/@yo632228/%C3%BCretken-yapay-zeka-ve-b%C3%BCy%C3%BCk-dil-modelleri-kar%C5%9F%C4%B1la%C5%9Ft%C4%B1rma-fafbf466be99 | |||
10:15 | Stanford STORM: Revolutionizing AI-Powered Knowledge Curation https://medium.com/@cognidownunder/stanford-storm-revolutionizing-ai-powered-knowledge-curation-35ce51996c19 | |||
09:51 | Optimizing Our LLMs: Exploring Down-Scaling and Depth Up-Scaling Techniques https://medium.com/@ayoubkirouane3/optimizing-our-llms-exploring-down-scaling-and-depth-up-scaling-techniques-2434d81bc433 | |||
09:51 | Optimizing Our LLMs: Exploring Down-Scaling and Depth Up-Scaling Techniques https://blog.gopenai.com/optimizing-our-llms-exploring-down-scaling-and-depth-up-scaling-techniques-2434d81bc433 | |||
09:45 | Enterprise Use Case-Based Evaluation of LLMs https://towardsdatascience.com/enterprise-use-case-based-evaluation-of-llms-abcf8292889f | |||
09:24 | Llama3 405B: The Most Advanced Openly Available LLM to Release https://medium.com/@marketing_novita.ai/llama3-405b-the-most-advanced-openly-available-llm-to-release-702da74e81ae | |||
09:18 | Building a Chatbot with LangChain and Pinecone: A Simple Guide https://pulithar.medium.com/building-a-chatbot-with-langchain-and-pinecone-a-simple-guide-f2a9faa46d29 | |||
08:57 | Line By Line, Let’s Reproduce GPT-2: Section 1 https://towardsdatascience.com/line-by-line-lets-reproduce-gpt-2-section-1-b26684f98492 | |||
08:53 | Counterfactuals in Language AI https://towardsdatascience.com/counterfactuals-in-language-ai-956673049b64 | |||
08:46 | LLMs reasoning // knowledge representation https://sbagency.medium.com/llms-reasoning-knowledge-representation-aec5916695c2 | |||
08:13 | Understanding Transformers: The Role of Attention Mechanisms in Modern NLP https://medium.com/@romybuch22/understanding-transformers-the-role-of-attention-mechanisms-in-modern-nlp-ba2895f3377b | |||
07:18 | Natural Language to SQL with LLMs https://rojojojo.medium.com/natural-language-to-sql-with-llms-823325f3adf0 | |||
07:17 | T5 Model: Fine-Tuning on a Single GPU in a Docker Container https://medium.com/@sulaiman.shamasna/t5-model-fine-tuning-on-a-single-gpu-in-a-docker-container-68beea101996 | |||
07:03 | PromptTemplate and ChatPromptTemplate Explained https://medium.com/@ypredofficial/prompttemplate-and-chatprompttemplate-explained-87291576c6de | |||
06:53 | Simplifying Data Extraction with OpenAI JSON Mode and JSON Schemas https://medium.com/@patc888/simplifying-data-extraction-with-openai-json-mode-and-json-schemas-a65545d29e07 | |||
06:42 | Building a Retrieval-Augmented Generation (RAG) Service on Compute Nest with Alibaba Cloud Model… https://k-farruh.medium.com/building-a-retrieval-augmented-generation-rag-service-on-compute-nest-with-alibaba-cloud-model-6013cb1b98c3 | |||
06:29 | Or maybe finally harness AI to productive action? https://n-biedrzycki.medium.com/or-maybe-finally-harness-ai-to-productive-action-ff888f41a498 | |||
06:29 | Multi-Modal Generation Market Growth [2032] https://medium.com/@InnoTechGuru/multi-modal-generation-market-growth-2032-a287d29b92a9 | |||
06:14 | Microsoft Research Introduces E5-V: A Universal AI Framework for Multimodal Embeddings with Single-Modality Training on Text Pairs https://www.marktechpost.com/2024/07/22/microsoft-research-introduces-e5-v-a-universal-ai-framework-for-multimodal-embeddings-with-single-modality-training-on-text-pairs/ | |||
06:05 | Multimodal Retrieval-augmented generation (MMRAG) https://medium.com/@mayankchugh.jobathk/multimodal-retrieval-augmented-generation-rag-09918c6c1fb7 | |||
06:02 | Evaluating LLM-Powered Applications : Concept and Examples (using promptfoo) https://medium.com/@pallavisinha12/evaluating-llm-powered-applications-concept-and-examples-using-promptfoo-d652ba53a728 | |||
05:37 | Gemini API: Revolutionizing Content Generation with Direct PDF Input https://medium.com/google-cloud/gemini-api-revolutionizing-content-generation-with-direct-pdf-input-105493780fa4 |
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803