Adrián Bazaga

Proprietary datasets and the combination of AI and experimental data are the key to build successful companies.

1

Fine-tuning LLMs with Reinforcement Learning from Human Feedback This blog post explores how Reinforcement Learning from Human Feedback (RLHF) can be used to fine-tune Large Language Models (LLMs) to align with human preferences. It delves into the concept of Proximal Policy Optimization (PPO) and how it is used in this context. The key takeaway is that RLHF offers a powerful framework to train LLMs that can produce human-aligned text, while still maintaining creativity. This paves the way for more natural and nuanced language generation in the future of AI and natural language understanding. Read the article: https://lnkd.in/d9EGf579 #AI #machinelearning #goML

8

🔍 Fascinating insights from @He Chao on ByteDance approach to topology-aware scheduling for LLM workloads! #KubeConNA 🎯 Key Challenges: • Network bottlenecks over compute • Die-level affinity requirements • RDMA congestion at ToR level • Insufficient K8s topology management • Pod-level scheduling limitations 💡 Notable Solutions: • Modified K8s scheduler • Catalist Agent for resource management • Enhanced NUMA awareness • CCX-level workload alignment • GPU co-location strategies 🛠️ Perfect for: • ML Infrastructure Teams • Platform Engineers • Performance Engineers • Cloud Architects • SRE Teams ⚡️ Impact: • Improved inference performance • Better resource efficiency • Enhanced RDMA communication • Optimized cache management • Reduced network congestion 🎥 Watch the full presentation: https://lnkd.in/gNCaQ28F #MLOps #Kubernetes #CloudNative #AI #CNCF

2

Mixture-of-Agents as an Event-Driven System 🤖☎️ This paper by Wang et al. shows you how to ensemble smaller LLMs to create a system that can outperform state-of-the-art larger models. We’ve implemented this paper in a fully async, event-driven workflow system thanks to Ravi Theja Desetty - treat each “small LLM” as an event-driven step that can process incoming events and respond to it, independently and in parallel. ✅ Take full advantage of processing an entire batch of requests  ✅ Cleaner, readable code LlamaPack: https://lnkd.in/gRuqQGk2 Learn more about workflows: https://lnkd.in/gqWwz7Xs

311

9 Comments

🚀 While many studies highlight LLMs' success in answering medical questions, research from Yanjun Gao, PhD, and colleagues takes it a step further. They evaluated LLMs on real-world EHR datasets for clinical prediction, comparing them directly against classical machine learning models—widely regarded as state-of-the-art in this field. By examining tasks like mortality prediction and hospital length-of-stay prediction, which greatly influence clinical workflows, the findings demonstrate that LLMs have significant potential to advance clinical predictive modeling.

7

Are you facing difficulties in deploying LLMs? Garvan D., a Technical Staff Member at Anthropic, has crafted an insightful guide on deploying Large Language Models (LLMs). This guide addresses the challenges and solutions in LLM deployment. In this walkthrough he builds a simple classifier and shares prompt engineering techniques to improve the model's accuracy.

1

Microsoft researchers developed Orca 2, using a technique that allows small language models to achieve performance nearly on par with larger models by following more cautious reasoning strategies. Read our summary of the paper in #TheBatch: https://hubs.ly/Q02BpKy90

430

4 Comments

Introducing ActPC-Geom, a novel, speculative approach for accelerating Active Predictive Coding (ActPC) based learning in artificial neural networks through the integration of information geometry: https://lnkd.in/e5PRvhBz

22

Will you be at NeurIPS this year? 📍Exciting news from Structured! Our very own CTO, Shivam Singhal, will be speaking at NeurIPS 2024 as part of the Table Representation Learning Workshop. Shivam will dive into how TRL is transforming structured data—covering everything from text-to-SQL, semantic parsing, and how we're integrating tables with LLMs to push the limits of what’s possible in structured data understanding. If you're around, come join the conversation! #NeurIPS2024 #TRL #RepresentationLearning #Structured #AI

10

Don't miss Kartikay Khandelwal of Meta on stage at PyTorch Conference 2024, September 18-19 in San Francisco! Explore the list of keynote speakers: https://hubs.la/Q02NfBKt0. Register & join us next week in San Francisco! https://hubs.la/Q02NfwBx0 #PyTorchConf #PyTorch #PyTorchFoundation #AI #MachineLearning #ML #DeepLearning #OpenSource #OpenSourceSoftware #OpenSourceDevelopment #OpenSourceCommunity #OSS #LinuxFoundation #events #linux #SoftwareSupplyChainNews

21

Learn how Reinforcement Learning from Human Feedback (RLHF) is transforming the landscape of large language models (LLMs) like GPT-3. From feedback loops to best practices, Michał Oleszak's article dives deep into this technique. #AI #LLM

19

1 Comment

Are you interested in vector search, indexing, or database efficiency? Then you won't want to miss this talk by Etienne Dilocker from Weaviate at Carnegie Mellon University's Database Group with Andy Pavlo! Etienne breaks down key challenges and innovations that are powering the future of search: ✨ Bit-Sliced Indexing - tackling complex range queries like price filters with innovative indexing. ✨ BM25 Hybrid Search - combining keyword and vector search to handle nuanced queries. ✨ Graph-Based Indexing (HNSW) - optimizing for high update rates and recalls without latency drops. ✨ Overcoming the Minority Filter Problem - enhancing search relevance through in-place filtering, based on the ACORN paper. ✨ Weaviate's Roadmap - performance, enterprise readiness, and pioneering "Recommendations as a Service." Check out the full talk for an in-depth look at how Weaviate is setting new standards in search technology: https://lnkd.in/gavAZRrn

33

2 Comments

📢 Original article Sharing-Vol. 23 No. 7 💕 Title: Exploring Implicit Biological Heterogeneity in ASD Diagnosis Using a Multi-Head Attention Graph Neural Network 🤵 Authors: Hyung-Jun Moon, Sung-Bae Cho,* 🔔 Full Text: https://lnkd.in/gtMHteqU 😎Welcome to your reading! #Parkinsons #ParkinsonsDisease #Neurology #BrainHealth #MovementDisorders #Dopamine #NeurodegenerativeDiseases #Healthcare #Research #Awareness #Treatment #SupportGroups #PatientCare #Therapeutics #MentalHealth #Neuroscience #CureParkinsons #BrainMapping #Neurobiology #BrainInjury #NeuroscienceNews #NeuroImaging

3

Learn how you can convert a PyTorch model, trained on the web, to a mobile-optimized format. Madhur Zanwar describes the process using a few lines of code. He also discusses his journey and how one approach didn't yield satisfactory results while trying to run it in a React Native app. #machinelearning #pytorch #computervision #edgeml #reactnative #objectdetection #yolov5

14

For his debut TDS article, Jeremi Nuer presents a thoughtful walkthrough of a recent paper on model interpretability: "We want to have finer-tuned control over LLMs. Being able to detect when certain features are active, and tune how active they are in the middle of generating output, is an amazing tool to have in our toolbox."

19

An Open-Source Language Model for Evaluating LLMs Researchers have introduced Prometheus 2, a powerful open-source language model specifically designed to evaluate the quality of responses from other language models. This addresses the limitations of proprietary evaluator LMs like GPT-4, offering a transparent, controllable, and affordable alternative. Prometheus 2 surpasses existing open evaluator LMs by: - Achieving high correlation with human judgments and proprietary LMs: Scores closely mirror human evaluations and those of models like GPT-4 and Claude. - Handling both direct assessment and pairwise ranking: Offers flexibility for different evaluation schemes. - Evaluating based on custom criteria: Goes beyond general qualities like helpfulness and harmlessness, allowing for fine-grained assessment tailored to specific needs. Key advancements in Prometheus 2: - Preference Collection: A new dataset with pairwise ranking feedback and 1,000 custom evaluation criteria. - Weight merging: Combines models trained on direct assessment and pairwise ranking data, resulting in a unified evaluator LM that excels in both formats. Prometheus 2 represents a significant step towards a more reliable and accessible evaluation of LLMs, paving the way for further advancements in the field. Read the full paper: https://lnkd.in/dU7sit-Y #Prometheus2 #LLMs #Evaluation #OpenSource #AI ✔️ Click "Follow" on the Cohorte page for daily AI engineering news. Credits: Seungone Kim, Juyoung Suk, Shayne Longpre, Bill Yuchen Lin, Jamin Shin, Sean Welleck, Graham Neubig, Moontae Lee, Kyungjae Lee, Minjoon Seo

8

1 Comment

🚀 Want to employ the power of #PyTorch for your scientific models without a steep learning curve? 👀 Check out our latest blog, where Travis Oliphant discusses how PyTorch's integration with the Array API makes it easy to use with familiar libraries like NumPy and scikit-learn.🔥 https://lnkd.in/dDRkEY3v #Innovation

10