Titus Winters

#DYK While pre-trained large language models (LLMs) excel at factual tasks after fine-tuning, their ability to access and update knowledge remains limited. Enter Retrieval-Augmented Generation (RAG), which overcomes these limitations by combining LLMs with a retrieval component. 💥 Interested in learning more? Check out this blog to see how you can have a basic RAG solution up and running for your documents with minimal clicks and code copy-pasting: https://dell.to/4c438Ds #AI #Dell #DellTechnologies #HuggingFace #AImadeeasy #iwork4dell #iwork4dell

10

Instead of scaling AI training to produce more accurate answers, chain-of-thought reasoning explore different avenues and provide better answers. This "think before answering" approach provides dramatically better performance on demanding tasks like math, science, and code generation, fundamentally boosting the intelligence of AI models without requiring additional training. By running over 70x faster than other solutions, Cerebras Inference allows AI models to "think" far longer and return more accurate results. As agentic AI becomes available and eventually widespread, the demands in ifnerencing hardware will increase by another 10-fold.

7

The 7th workshop on Neural Scaling Laws is about to start: https://lnkd.in/gQSB5k8v Scaling laws, emergency, alignment, transfer learning, with a focused track on multilingual models. Looking forward to kick it off with Irina Rish and discuss all these topics with Yuhai Tu, Paul Bogdan, Hailey Schoelkopf, Darshil Doshi, Rio Yokota, Neha Sengupta, Preslav Nakov, Tatiana Shavrina, PhD, Yishi Xu. Join in person or virtually! #icml2024 #ai

37

⭐ I’m excited to announce our new blog post⭐ Intel Labs and Hugging Face introduce dynamic speculative decoding to 🤗 Transformers: a new trick that accelerate text generation by up to 2.7x It is so consistent that it is now the default in 🤗 Transformers when you trigger assisted generation/speculative decoding. Read the blogpost here: https://lnkd.in/d262VJbu How does it work? With speculative decoding, we split the generative process into two stages: 1️⃣ A small, but less accurate draft / assistant model generates a sequence of tokens 2️⃣ The target model applies parallelised verification over the tokens from the draft model This allows the target model to produce multiple tokens in a single forward pass and thus accelerate decoding. The approach relies on a concept known as speculation lookahead (SL), which is essentially the number of tokens generated by the draft model during each iteration. Now, SL is usually a static value or determined based on heuristics - in both cases this leaves a lot of performance on the table The trick behind dynamic speculative decoding is to dynamically adjust the number of draft tokens generated *per iteration*. This strikes a balance between generating too few draft tokens (which would forgo potential speed gains) and too many (which would result in tokens being discarded by the target model and reducing the speedup gain)." Happy decoding! Thanks to the awesome collaborators: Jonathan Mamou, João Gante, Lewis Tunstall, Daniel Korat, Nadav Timor, Moshe Wasserblat

68

4 Comments

Good listen: Mark Suster, the guest host, is joined by Dan Senor to discuss the remarkable growth of NVIDIA in #Israel, which now boasts over 4,000 employees and a global CTO who is Israeli. The conversation shifts to Israel’s startup ecosystem, highlighting its impressive statistics: 500 venture capital firms, 120 accelerators, 35 incubators, 400 multinationals with major R&D operations, and 7,000 startups. These figures underscore Israel’s position as having the highest density of startups globally, attracting significant global venture capital, leading in R&D spending relative to GDP, and ranking fourth in NASDAQ-listed public companies. Regardless - I'll recommend following This Week in Startups podcasts which brings interesting conversations with leaders from the startup community... https://lnkd.in/eGv3fr-H #iwork4dell

7

1 Comment

Large Language Models (LLMs) are absolute powerhouses when it comes to generating top-notch #GenAI responses. Yet, #LLMs lack that in-depth, domain-specific knowledge that can make all the difference in certain use cases. Additionally, let's not forget the hefty computing resources and expertise required to develop and deploy them. In my latest article, I delve into why Small Language Models (SLMs) are becoming the go-to choice for specific tasks. With their more focused approach, #SLMs are more efficient than LLMs, and have a smaller compute footprint. Thus, they are more suitable to run locally on workstations or on-prem servers. Check out my article 👇 and ‘d love to hear your thoughts about it https://lnkd.in/diRYaNXF #DellTechEMEA #iWork4Dell #AMD, #Intel, #NVIDIA 

143

7 Comments

Learn why the NVIDIA Jetson AGX Orin is the leading platform for running transformer models like GPT-J, vision transformers, and stable diffusion at the edge.

8

1 Comment

FlashInfer v0.2 is here, a lot of technical upgrades, great news for anyone are doing custom attention improvement or just benefit it implicitly from integration of LLM frameworks

39

Discover how Perplexity AI built AI architecture to scale its Llama 3 #LLM deployment to serve millions of inference requests. Key takeaways: ✅ 435M queries/month ✅ 20+ AI models, including Llama 3 (8B, 70B, 405B) ✅ 3x cost reduction

7

Meet AGUVIS: A pure vision-based framework for autonomous Computer/Mobile-use GUI agents, operating seamlessly across web, desktop, and mobile platforms without UI code. Key Features & Contributions - Pure Vision Framework: First fully autonomous pure vision GUI agent capable of performing tasks independently without relying on closed-source models - Cross-Platform Unification: Unified action space and plugin system that works consistently across different GUI environments - Comprehensive Dataset: Large-scale dataset of GUI agent trajectories with multimodal grounding and reasoning - Two-Stage Training: Novel training pipeline focusing on GUI grounding followed by planning and reasoning - Inner Monologue: Explicit planning and reasoning capabilities integrated into the model training - Generalization to OOD (Out-of-Distribution): AGUVIS demonstrates impressive generalization on OSWorld benchmark even without desktop trajectory data during training. Project Page: https://lnkd.in/guzkwpbB Paper: https://lnkd.in/gs7wXyJS GitHub: https://lnkd.in/gWeSkFmK Collaboratiion among Yiheng Xu Zekun Wang Junli Wang Dunjie Lu Tianbao Xie Amrita Saha Doyen Sahoo Tao Yu Caiming Xiong

155

6 Comments

Check out how the world’s first #generativeAI models for #OpenUSD development will be available as NVIDIA NIM microservices.

9

Chapter 4 of my book "Quantum Programming in Depth: Solving problems with Q# and Qiskit" is now available via Manning Early Access Program (MEAP)! Chapters 2 and 3 dealt with quantum state preparation and unitary implementation - things you can do using just quantum gates. Chapter 4 adds quantum measurements to the toolbox, covering several different tasks on extracting information from quantum states. Today's update also includes small edits to the first chapters to fix errata reported by eagle-eyed readers. Huge thanks to everybody who reported an issue, and keep them coming! https://lnkd.in/gwnke93p

69

1 Comment

EWE: arxiv.org/pdf/2412.18069 Ewe (Explicit Working Memory), enhances factuality in long-form text generation by integrating a working memory that receives real-time feedback from external resources. The working memory consists of k memory units, each unit stores the representations of each feedback message of M tokens.The memory is refreshed based on online fact-checking and retrieval feedback, allowing Ewe to rectify false claims. Ewe outperforms strong baselines on four fact-seeking long-form generation datasets, increasing the factuality metric, VeriScore, by 2 to 10 points absolute without sacrificing the helpfulness of the responses. Ewe can be easily adapted to various large language models.

18