Ruoyu Li

Unlock the potential of Meta’s Llama3 for biotech applications with torchtune, a PyTorch-native library that simplifies fine-tuning of large language models. Whether you're looking to enhance drug discovery, genetic analysis, or scientific writing, our latest blog provides a guide to leverage this powerful tool effectively. 🔗 Learn more here: https://lnkd.in/g9WnrNSN #Biotechnology #Llama3 #torchtune #AI #MachineLearning

6

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

We are excited to announce our newest study that focuses on addressing the challenges inherent to treatments of active inference (AIF) in the context of pixel-level, sparse-reward partially observable Markov decision processes! Our proposed generalization of AIF, which we call robust active inference (R-AIF), is used to construct and train a reinforcement learning agents capable of scoring higher that SOTA, model-based RL and active inference models that must operate with sparse reward, image-based observation, and continuous-action robotic control tasks. 🤖💻🧠 *The preprint can be found here:* https://lnkd.in/e8u3BNQz *Brief video walk-through of the work can be found here:* https://lnkd.in/eP2ae5rb *Official Github Implementation:* https://lnkd.in/e9sDV4XV #ActiveInference #ReinforcementLearning, #DeepLearning, #Robotics, #WorldModels, #SparseRewards, #Pomdps

18

2 Comments

📖 "Efficient Multimodal Large Language Models: A Survey" - a comprehensive review of recent progress in efficient MLLMs. Key advances include:   💡 Architecture: optimizations in vision encoder, vision-language projector, language model, vision token compression, and using efficient structures like MoE and Mamba. 💡 Training: pre-training, instruction-tuning, and fine tuning 💡 Data: pre-training data, instruction data and benchmarks   Efficient MLLM efforts aim to make the powerful models more accessible - reducing cost and latency, and enabling deployments on device for privacy protection.   Read the full paper: https://lnkd.in/gFEw_XQ8   #generativeai #MLLM #largelanguagemodels

21

🚀 Looking to streamline fine-tuning for models like Llama 3, Mistral, and Mixtral? Our latest blog shows how Anyscale simplifies LLMs fine-tuning with Ray: 🔑 Key takeaways: • Scalable fine-tuning with LLM-Forge • Model Deployment with RayLLM Read more: https://lnkd.in/gQwD4A2U

34

Only ✨15 DAYS✨ until PyTorch Conference! Join us in San Francisco, Sept 18-19, to help shape the future of PyTorch, engage in technical sessions, explore collaborative opportunities, and connect with a global network of developers. Check out the schedule: https://hubs.la/Q02NwT3D0 Grab your ticket today: https://hubs.la/Q02NwL-m0 #PyTorchConf #PyTorch #PyTorchFoundation #AI #MachineLearning #ML #DeepLearning #OpenSource #OpenSourceSoftware #OpenSourceDevelopment #OpenSourceCommunity #OSS #LinuxFoundation #events #LLM #NLP

12

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

Can you use #llms for every machine learning task? Members of MIT Data-to-AI Lab Kalyan Veeramachaneni and Sarah Alnegheimish tried #llms for a well known task of unsupervised time series anomaly detection in their paper. In an article in VentureBeat they explore the affordances that #llms provide and how to make most of them. Article: https://lnkd.in/emvEDDkg Research paper: https://lnkd.in/ezNzHkBj

3

vGPU, MIG, & Time-Slicing! 3 ways to optimize the #GPU resources to meet the dynamic demands of computational tasks💻 Sameer Kulkarni explains & compares these methods in the blog post to help you select the right GPU optimization for your models👇 https://lnkd.in/gFQPX4b4

7

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

🚀 See how Handshake cut their LLM GPU costs by 50% with Anyscale. Discover how they: 💰 Reduced LLM GPU costs by 50% or more. 📈 Seamlessly scaled large language models (LLMs) without compromising performance. ⏱ Enhanced operational efficiency, enabling faster development cycles. Check out the full story here: https://lnkd.in/gSiKJDaY

37

2 Comments

We can't wait to see Jerry Liu of LlamaIndex on stage at PyTorch Conference 2024! Explore the list of keynote speakers: https://hubs.la/Q02KmnXz0. Register & join us September 18-19 in San Francisco! https://hubs.la/Q02KmbPJ0 #PyTorchConf #PyTorch #PyTorchFoundation #AI #MachineLearning #ML #DeepLearning #OpenSource #OpenSourceSoftware #OpenSourceDevelopment #OpenSourceCommunity #OSS #LinuxFoundation #events #linux #SoftwareSupplyChainNews

29

We’ve recently contributed FP8 support to vLLM in collaboration with Neural Magic -- with this feature, you can see up to a 1.8x reduction in inter-token latency, with >99% accuracy preservation! A common concern with FP8 is whether users will experience accuracy degradation. To address this, Neural Magic has produced many checkpoints for key models with >99% accuracy preservation across a wide range of benchmarks (https://lnkd.in/gTimN5dZ), including: - Llama3-70b - Mixtral 8x7b - Llama3-8b You can easily try this out on vLLM, and read more about the feature here -- https://lnkd.in/gzKJqerB

146

3 Comments

FP8 quantization is now available in vLLM - check it out! Quantized inference is one of the best ways to reduce the costs of LLM deployments.

5