Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Training cue for lats Keep your shoulders down Very common mistake when training, you’ll see this everyday at the gym Jeremy Buendia Mr. Olympia Men’s Physique 2014, 2015, 2016, 2017

272,167 Aufrufe • vor 6 Monaten •via X (Twitter)

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

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 Aufrufe • vor 1 Jahr

The most underrated exercise on the planet is the Bar Hang. But 99% of people don't even do them. Here are 4 powerful reasons to do bar hangs every day: 1. They improve your posture Don't want to look like a croissant? Bar hangs help strengthen & mobilize your upper body. They also provide a constant stretch on the shoulders, back arms & lats. This helps reverse upper body posture defects that come from sitting for too long. 2. They improve your strength Your weight is supported first by the grip of your hand. A good grip improves your performance across all exercises like the pull-up, rows, deadlifts...pretty much any activity requiring a grip. 3. They build stronger shoulders Bar hangs can improve mobility, and strengthen the shoulders & lats while reducing shoulder pain. They stretch the brachial muscles while strengthening the supraspinatus tendon, which is responsible for shoulder strength & endurance. 4. They may help you live longer Grip strength can be a biomarker for your inner age & determines your mobility & strength as you get older. In some studies, decreased grip strength is associated with accelerated biological age. There are 2 ways to do bar hangs: The first is a passive hang (video) Take an overhand grip. Let shoulders & lats relax. Your body should sink with your shoulders touching your ears. Hang there with feet slightly forward, core braced & let your weight passively stretch your shoulders, lats, & back. The second is an active hang. Start in a passive hang. Retract your shoulder blades down and away from your ears. Stop retracting when your ears reach your elbows. Hold for as long as you can. This puts more emphasis on the muscles in your shoulders and back. If you're a beginner aim for 10 seconds to start. Work your way up to one minute and eventually 2 minutes at a time. As long as you're not sore you can do these daily. If you can't hang from a bar you can step on a box at first to help support your weight. Another way is to attach a resistance band to the bar putting while putting your feet on it. Bar hangs are one of the most underrated exercises on the planet especially if you work at a desk. Add these to your daily workouts and experience the benefits.

Dan Go

1,340,822 Aufrufe • vor 2 Jahren