Video yükleniyor...

Video Yüklenemedi

Bu video yüklenirken bir sorun oluştu. Bu geçici bir ağ sorunundan kaynaklanıyor olabilir veya video kullanılamıyor olabilir.

Ana Sayfaya Dön

Ralf #Rangnick - Training Methods Explaining his training methods and use of exaggeration & provocational rules ” We want to train in a way that makes the training even harder than the actual game by limiting time, space and learn under pressure ”

Albin Sheqiri

32,122 subscribers

68,370 görüntüleme • 3 yıl önce •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

In case you missed it, we recently launched "Post-training of LLMs," a short course where you'll: ✅ Understand when and why to use post-training methods like Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Online Reinforcement Learning. ✅ Learn the concepts underlying the three post-training methods of SFT, DPO, and Online RL, their common use-cases, and how to curate high-quality data to effectively train a model using each method. ✅ Download a pre-trained model and implement post-training pipelines to turn a base model into an instruct model, change the identity of a chat assistant, and improve a model’s math capabilities. Learn more and enroll for free:

In case you missed it, we recently launched "Post-training of LLMs," a short course where you'll: ✅ Understand when and why to use post-training methods like Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Online Reinforcement Learning. ✅ Learn the concepts underlying the three post-training methods of SFT, DPO, and Online RL, their common use-cases, and how to curate high-quality data to effectively train a model using each method. ✅ Download a pre-trained model and implement post-training pipelines to turn a base model into an instruct model, change the identity of a chat assistant, and improve a model’s math capabilities. Learn more and enroll for free:

DeepLearning.AI

16,779 görüntüleme • 1 yıl önce

"It's a bit of a juxtaposition..." 🤔 On the new reports that Jadon Sancho was one of the top players in training under Ralf Rangnick, Mordzs discusses if this looks bad on Erik ten Hag. #mufc Who do you think is in the right in training-gate? 👇

"It's a bit of a juxtaposition..." 🤔 On the new reports that Jadon Sancho was one of the top players in training under Ralf Rangnick, Mordzs discusses if this looks bad on Erik ten Hag. #mufc Who do you think is in the right in training-gate? 👇

The United Stand

120,412 görüntüleme • 2 yıl önce

New Course: Post-training of LLMs Learn to post-train and customize an LLM in this short course, taught by Banghua Zhu, Assistant Professor at the University of Washington University of Washington, and co-founder of @NexusflowX. Training an LLM to follow instructions or answer questions has two key stages: pre-training and post-training. In pre-training, it learns to predict the next word or token from large amounts of unlabeled text. In post-training, it learns useful behaviors such as following instructions, tool use, and reasoning. Post-training transforms a general-purpose token predictor—trained on trillions of unlabeled text tokens—into an assistant that follows instructions and performs specific tasks. Because it is much cheaper than pre-training, it is practical for many more teams to incorporate post-training methods into their workflows than pre-training. In this course, you’ll learn three common post-training methods—Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Online Reinforcement Learning (RL)—and how to use each one effectively. With SFT, you train the model on pairs of input and ideal output responses. With DPO, you provide both a preferred (chosen) and a less preferred (rejected) response and train the model to favor the preferred output. With RL, the model generates an output, receives a reward score based on human or automated feedback, and updates the model to improve performance. You’ll learn the basic concepts, common use cases, and principles for curating high-quality data for effective training. Through hands-on labs, you’ll download a pre-trained model from Hugging Face and post-train it using SFT, DPO, and RL to see how each technique shapes model behavior. In detail, you’ll: - Understand what post-training is, when to use it, and how it differs from pre-training. - Build an SFT pipeline to turn a base model into an instruct model. - Explore how DPO reshapes behavior by minimizing contrastive loss—penalizing poor responses and reinforcing preferred ones. - Implement a DPO pipeline to change the identity of a chat assistant. - Learn online RL methods such as Proximal Policy Optimization (PPO) and Group Relative Policy Optimization (GRPO), and how to design reward functions. - Train a model with GRPO to improve its math capabilities using a verifiable reward. Post-training is one of the most rapidly developing areas of LLM training. Whether you’re building a high-accuracy context-specific assistant, fine-tuning a model's tone, or improving task-specific accuracy, this course will give you experience with the most important techniques shaping how LLMs are post-trained today. Please sign up here:

New Course: Post-training of LLMs Learn to post-train and customize an LLM in this short course, taught by Banghua Zhu, Assistant Professor at the University of Washington University of Washington, and co-founder of @NexusflowX. Training an LLM to follow instructions or answer questions has two key stages: pre-training and post-training. In pre-training, it learns to predict the next word or token from large amounts of unlabeled text. In post-training, it learns useful behaviors such as following instructions, tool use, and reasoning. Post-training transforms a general-purpose token predictor—trained on trillions of unlabeled text tokens—into an assistant that follows instructions and performs specific tasks. Because it is much cheaper than pre-training, it is practical for many more teams to incorporate post-training methods into their workflows than pre-training. In this course, you’ll learn three common post-training methods—Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and Online Reinforcement Learning (RL)—and how to use each one effectively. With SFT, you train the model on pairs of input and ideal output responses. With DPO, you provide both a preferred (chosen) and a less preferred (rejected) response and train the model to favor the preferred output. With RL, the model generates an output, receives a reward score based on human or automated feedback, and updates the model to improve performance. You’ll learn the basic concepts, common use cases, and principles for curating high-quality data for effective training. Through hands-on labs, you’ll download a pre-trained model from Hugging Face and post-train it using SFT, DPO, and RL to see how each technique shapes model behavior. In detail, you’ll: - Understand what post-training is, when to use it, and how it differs from pre-training. - Build an SFT pipeline to turn a base model into an instruct model. - Explore how DPO reshapes behavior by minimizing contrastive loss—penalizing poor responses and reinforcing preferred ones. - Implement a DPO pipeline to change the identity of a chat assistant. - Learn online RL methods such as Proximal Policy Optimization (PPO) and Group Relative Policy Optimization (GRPO), and how to design reward functions. - Train a model with GRPO to improve its math capabilities using a verifiable reward. Post-training is one of the most rapidly developing areas of LLM training. Whether you’re building a high-accuracy context-specific assistant, fine-tuning a model's tone, or improving task-specific accuracy, this course will give you experience with the most important techniques shaping how LLMs are post-trained today. Please sign up here:

Andrew Ng

125,146 görüntüleme • 1 yıl önce

I have never seen a harder-working athlete than Yomif Kejelcha. Most of the time, he trains three times a day. He does his main training in the morning, hits the gym before lunch, and then heads out for afternoon training after his nap.

I have never seen a harder-working athlete than Yomif Kejelcha. Most of the time, he trains three times a day. He does his main training in the morning, hits the gym before lunch, and then heads out for afternoon training after his nap.

Aman

48,314 görüntüleme • 4 ay önce

An exciting new course: Fine-tuning and Reinforcement Learning for LLMs: Intro to Post-training, taught by Sharon Zhou, VP of AI at AMD. Available now at Post-training is the key technique used by frontier labs to turn a base LLM--a model trained on massive unlabeled text to predict the next word/token--into a helpful, reliable assistant that can follow instructions. I've also seen many applications where post-training is what turns a demo application that works only 80% of the time into a reliable system that consistently performs. This course will teach you the most important post-training techniques! In this 5 module course, Sharon walks you through the complete post-training pipeline: supervised fine-tuning, reward modeling, RLHF, and techniques like PPO and GRPO. You'll also learn to use LoRA for efficient training, and to design evals that catch problems before and after deployment. Skills you'll gain: - Apply supervised fine-tuning and reinforcement learning (RLHF, PPO, GRPO) to align models to desired behaviors - Use LoRA for efficient fine-tuning without retraining entire models - Prepare datasets and generate synthetic data for post-training - Understand how to operate LLM production pipelines, with go/no-go decision points and feedback loops These advanced methods aren’t limited to frontier AI labs anymore, and you can now use them in your own applications. Learn here:

An exciting new course: Fine-tuning and Reinforcement Learning for LLMs: Intro to Post-training, taught by Sharon Zhou, VP of AI at AMD. Available now at Post-training is the key technique used by frontier labs to turn a base LLM--a model trained on massive unlabeled text to predict the next word/token--into a helpful, reliable assistant that can follow instructions. I've also seen many applications where post-training is what turns a demo application that works only 80% of the time into a reliable system that consistently performs. This course will teach you the most important post-training techniques! In this 5 module course, Sharon walks you through the complete post-training pipeline: supervised fine-tuning, reward modeling, RLHF, and techniques like PPO and GRPO. You'll also learn to use LoRA for efficient training, and to design evals that catch problems before and after deployment. Skills you'll gain: - Apply supervised fine-tuning and reinforcement learning (RLHF, PPO, GRPO) to align models to desired behaviors - Use LoRA for efficient fine-tuning without retraining entire models - Prepare datasets and generate synthetic data for post-training - Understand how to operate LLM production pipelines, with go/no-go decision points and feedback loops These advanced methods aren’t limited to frontier AI labs anymore, and you can now use them in your own applications. Learn here:

Andrew Ng

132,304 görüntüleme • 10 ay önce

De Zerbi explaining that when opponent press more, we can be more 'vertical' and without pressure we can play more 'slow & dribble' Brilliant 2 hours long webinar of De Zerbi's game model with training and game examples Complete webinar below👇

De Zerbi explaining that when opponent press more, we can be more 'vertical' and without pressure we can play more 'slow & dribble' Brilliant 2 hours long webinar of De Zerbi's game model with training and game examples Complete webinar below👇

Gaurav

28,357 görüntüleme • 1 yıl önce

Diving into the “why” behind some of the training methods I choose A few reasons 1. I enjoy high volume = adherence 2. Efficiency when training before work 3. I prefer machines when training to failure on lower body 4. I’m 39 and probably already set any PR I’m gonna set so who cares if the the training progression is perfect 🤷‍♂️

Diving into the “why” behind some of the training methods I choose A few reasons 1. I enjoy high volume = adherence 2. Efficiency when training before work 3. I prefer machines when training to failure on lower body 4. I’m 39 and probably already set any PR I’m gonna set so who cares if the the training progression is perfect 🤷‍♂️

Alan Bishop

23,724 görüntüleme • 10 ay önce

Want the game to slow down? Train faster than the game. Training at or above game speed forces you to process information, move your feet and execute your actions under pressure. That doesn’t mean every rep has to feel this way. Controlled reps are important too. But the game shouldn’t be the first time you’re put in these situations or asked to execute at this speed. When you consistently train at that speed, game speed starts to feel normal. You’ve already been there. Push the pace in practice so the game doesn’t speed up internally.

Want the game to slow down? Train faster than the game. Training at or above game speed forces you to process information, move your feet and execute your actions under pressure. That doesn’t mean every rep has to feel this way. Controlled reps are important too. But the game shouldn’t be the first time you’re put in these situations or asked to execute at this speed. When you consistently train at that speed, game speed starts to feel normal. You’ve already been there. Push the pace in practice so the game doesn’t speed up internally.

Dirt Bro Diamond Training

11,070 görüntüleme • 27 gün önce

Limited time: FREE Redshift Training! For the next 30 days, we’re giving away our complete up-to-date Greyscalegorilla Plus Redshift Training Course! Learn the ins-and-outs of redshift3d in Maxon C4D with over 16 hours of training. Get the details

Limited time: FREE Redshift Training! For the next 30 days, we’re giving away our complete up-to-date Greyscalegorilla Plus Redshift Training Course! Learn the ins-and-outs of redshift3d in Maxon C4D with over 16 hours of training. Get the details

Greyscalegorilla

43,902 görüntüleme • 3 yıl önce

Hōjutsu training. In traditional Japanese gunnery, gunners use equipment from the age of the samurai - meaning that practitioners have a genuine and tangible link to Japan’s history, every time they train or take part in demonstrations.

Hōjutsu training. In traditional Japanese gunnery, gunners use equipment from the age of the samurai - meaning that practitioners have a genuine and tangible link to Japan’s history, every time they train or take part in demonstrations.

Gun Samurai

21,069 görüntüleme • 7 ay önce

"We normally issue instructions to all training institutions and formations that only the minimum necessary force should be used in riot control. That is a basic principle of all riot control duties. The use of pellet guns was definitely not required because there are other methods as well," says M.P.NATHANAEL #NewsToday #PelletGuns #Police #Protests Rajdeep Sardesai

"We normally issue instructions to all training institutions and formations that only the minimum necessary force should be used in riot control. That is a basic principle of all riot control duties. The use of pellet guns was definitely not required because there are other methods as well," says M.P.NATHANAEL #NewsToday #PelletGuns #Police #Protests Rajdeep Sardesai

IndiaToday

54,686 görüntüleme • 1 ay önce

This is the kind of training that builds elite reflexes, balance, and composure under pressure. How do you explain a training that requires that you box through a hard rolling rope and was doing effortlessly without a single contact with the rope 🤯🔥🥊👑

This is the kind of training that builds elite reflexes, balance, and composure under pressure. How do you explain a training that requires that you box through a hard rolling rope and was doing effortlessly without a single contact with the rope 🤯🔥🥊👑

FURY FURY

42,993 görüntüleme • 3 ay önce

Shedeur Sanders has been working HARDER than almost every QB in the NFL. On his off days, Sanders reportedly “never” takes the day off and is always training. Sanders has reportedly been spending his free time training at Baldwin Wallace University. A D3 university that’s roughly five minutes from the Browns training complex. Sanders has been seen there training with BW players and his own personal coach. The Browns rookie QB wants to be a successful SO BAD 😳

Shedeur Sanders has been working HARDER than almost every QB in the NFL. On his off days, Sanders reportedly “never” takes the day off and is always training. Sanders has reportedly been spending his free time training at Baldwin Wallace University. A D3 university that’s roughly five minutes from the Browns training complex. Sanders has been seen there training with BW players and his own personal coach. The Browns rookie QB wants to be a successful SO BAD 😳

Rookie Watch

2,004,787 görüntüleme • 11 ay önce

Djed Spence and Van de Ven intentionally ignoring their manager Thomas Frank. Still waiting for the media to flood news of Frank losing the dressing room and players complaining about his training methods. We all know the outrage if it was Amorim/United.

Djed Spence and Van de Ven intentionally ignoring their manager Thomas Frank. Still waiting for the media to flood news of Frank losing the dressing room and players complaining about his training methods. We all know the outrage if it was Amorim/United.

UF

2,876,305 görüntüleme • 10 ay önce