Loading video...

Video Failed to Load

Go Home

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 ”

albinsheqiri's profile picture

Albin Sheqiri

31,932 subscribers

68,074 views • 2 years ago •via X (Twitter)

#Rangnick
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

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:
1:31

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

16,746 views • 11 months ago

"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? 👇
1:40

"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

120,405 views • 2 years ago

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:
2:52

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 views • 11 months ago

Training camp rules: Train hard, trade harder 🎲 Head to our YouTube channel to watch the full video from Carlos' pre-season training camp 📺
0:31

Training camp rules: Train hard, trade harder 🎲 Head to our YouTube channel to watch the full video from Carlos' pre-season training camp 📺

Atlassian Williams F1 Team

31,754 views • 4 months ago

ELON: OPTIMUS NEEDS 10X MORE TRAINING COMPUTE THAN THE CAR “The training needs for the Optimus humanoid robot are probably at least 10x what's needed for the car to get to the full range of useful roles. The humanoid robot has probably a thousand times more uses and can do more complex things than a car. That doesn't mean the training scales by a thousand, but it's probably 10x. You can do this progressively. It doesn't mean Tesla is going to spend $500 billion on training compute. We obviously want to train Optimus to do enough tasks to match the output of Optimus robots. And obviously, the cost of training is dropping dramatically with time. I think long-term Optimus the potential to be north of $10 trillion in revenue. It's really bananas. You can obviously afford a lot of training compute in that situation. In fact, even $500 billion in training compute in that situation would be quite a good deal.” Source: Tesla Q4 and full year 2024 Financial Results Webcast, January 29, 2025
1:14

ELON: OPTIMUS NEEDS 10X MORE TRAINING COMPUTE THAN THE CAR “The training needs for the Optimus humanoid robot are probably at least 10x what's needed for the car to get to the full range of useful roles. The humanoid robot has probably a thousand times more uses and can do more complex things than a car. That doesn't mean the training scales by a thousand, but it's probably 10x. You can do this progressively. It doesn't mean Tesla is going to spend $500 billion on training compute. We obviously want to train Optimus to do enough tasks to match the output of Optimus robots. And obviously, the cost of training is dropping dramatically with time. I think long-term Optimus the potential to be north of $10 trillion in revenue. It's really bananas. You can obviously afford a lot of training compute in that situation. In fact, even $500 billion in training compute in that situation would be quite a good deal.” Source: Tesla Q4 and full year 2024 Financial Results Webcast, January 29, 2025

Mario Nawfal

83,001 views • 1 year ago

Is modern athletic training losing its way? Some argue velocity-based training misses the mark, calling for a return to foundational capacity-based methods. What's the real secret to building lasting strength? #AthleticTraining #Strength
0:26

Is modern athletic training losing its way? Some argue velocity-based training misses the mark, calling for a return to foundational capacity-based methods. What's the real secret to building lasting strength? #AthleticTraining #Strength

Joe Kenn

15,448 views • 1 month ago

🚨 Exclusive 🇵🇰👺: An old, undated video attributed to LeT shows terrorists training in camps in PoJK and Pak. The training includes border infiltration techniques, use and construction of hideouts, live-fire drills at shooting ranges, and methods to rescue cadres after being captured by Indian forces. For more such updates please subscribe to our TG channel Pls Ignore The BGM
3:37

🚨 Exclusive 🇵🇰👺: An old, undated video attributed to LeT shows terrorists training in camps in PoJK and Pak. The training includes border infiltration techniques, use and construction of hideouts, live-fire drills at shooting ranges, and methods to rescue cadres after being captured by Indian forces. For more such updates please subscribe to our TG channel Pls Ignore The BGM

OsintTV 📺

13,623 views • 9 months ago

The one time Nate Diaz left Conor McGregor without a comeback after bringing up his training methods at the UFC 196 press conference 🎤
0:43

The one time Nate Diaz left Conor McGregor without a comeback after bringing up his training methods at the UFC 196 press conference 🎤

FULL SEND MMA

259,178 views • 6 months ago

Training the SGA way means learning to compete under pressure, adapt quickly, and perform when it counts most. #BlnPlayersTrainedbySGA
0:40

Training the SGA way means learning to compete under pressure, adapt quickly, and perform when it counts most. #BlnPlayersTrainedbySGA

Miss Mughal

40,449 views • 4 months ago

Eden Hazard was not a fan of Conte’s training methods 😂😂😂
0:35

Eden Hazard was not a fan of Conte’s training methods 😂😂😂

🎬N

44,305 views • 9 days ago

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👇
2:19

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

27,505 views • 1 year ago

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:
2:27

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 views • 7 months ago

Marcelo Bielsa explains the fundamentals of his team's setup in 3-3-1-3 formation 📈 Amazing masterclass from Bielsa this year about his game ideas and training methods💡 Complete masterclass available in the link below with ENGLISH subtitles👇
2:33

Marcelo Bielsa explains the fundamentals of his team's setup in 3-3-1-3 formation 📈 Amazing masterclass from Bielsa this year about his game ideas and training methods💡 Complete masterclass available in the link below with ENGLISH subtitles👇

Gaurav

23,929 views • 7 months ago

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 🤷‍♂️
0:40

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

23,617 views • 6 months ago

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
0:32

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

43,880 views • 3 years ago

Jiri Prochazka explains his unique training methods 👀 #UFC #MMA 🚨 FULL EPISODE LIVE
0:55

Jiri Prochazka explains his unique training methods 👀 #UFC #MMA 🚨 FULL EPISODE LIVE

Pound 4 Pound

11,701 views • 7 months ago