Загрузка видео...

Не удалось загрузить видео

На главную

“There aren’t many high-quality, high-performance Layer 1s — but one in particular stood out once we dug into the details,” says Richard G Brown, reflecting on why the team selected Solana. A parallelised execution model, a safer programming language, and an architectural approach built to remove familiar bottlenecks shifted...

22,570 просмотров • 7 месяцев назад •via X (Twitter)

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

Saint Louis’s Dion Brown is one of the best glue guy’s in this year’s NBA Draft. For the season Brown averaged 11/5/2 on 62/40/75 splits in only 24 MPG. While also playing a major role in Saint Louis’s 29-6 record. When it comes to role versatility and impacting the game without the ball in his hands Brown is one of the best in this year’s class. At just 6’4 Brown has the ability to play the 2-4 at a high level with his motor, strength, and instincts. Brown was one of the best finishers in the country this season where he shot 75% at the rim on 170 attempts and was the only non big to do that. Brown is an elite cutter with great instincts to get to his spots, while also being a high level slasher in the half court and he also has the ability to push in transition with and without the ball. Brown is also a strong shooter from three who shot 40% from three. Brown’s mix of shooting and finishing efficiency makes him an extremely valuable player. Brown is also a skilled passer as a connector and creator who uses his ability to get to the rim to find cutting teammates, or uses his passing vision. On the defensive end Brown was one of the best defenders in the A10 with his motor and instincts. Brown is also an elite rebounder for his height who is always attacking the glass. Browns mix of finishing, shooting, versatility, passing, rebounding, off ball scoring and defensive impact makes him one of the most valuable glue guys on any team he plays for.

KJ

51,234 просмотров • 4 месяцев назад

How can you solve complex tasks using a Large Language Model? Here is a 2-minute introduction to everything you need to know to 10x the quality of your results. Let's talk about three techniques, in order of complexity, starting with the easiest one: • In-Context Learning • Indexing + In-Context Learning • Fine-tuning In-Context Learning The team that trained GPT-3 found something they couldn't explain: You can condition a model using examples of how you want it to behave. I included an example prompt in the attached video. You can "teach" the model how you want it to interpret questions, select the correct answers, and format the results by giving a few examples. You can also give specific knowledge to the model that will be helpful when formulating answers. We call this approach "grounding the model." There's another example in the video. Indexing + In-Context Learning Unfortunately, there is a limit to how much data you can include in a prompt. We call this the "context size." One version of GPT-4 supports a context of approximately 6,000 words, while the other supports 25,000 words. Although this sounds like a lot, many applications need more than that. Imagine you wrote a book and want to build an application to answer any questions about your story. What happens if your book is longer than the context? That's where Indexing comes in. Using a model, you can turn every book passage into an embedding. These are vectors, numbers that "encode" the passage's text. You can then store these embeddings in a particular database that supports fast retrieval of these vectors. You can then turn any question into an embedding and search the database for the list of passages that are similar to that query. Instead of using the entire book to ask the model, you can now use the relevant passages as in-context information, effectively working around the context size limitation. Fine-tuning Fine-tuning can give you an extra boost to get reliable outputs from your LLM. It is, however, the most complex approach on the list. There are different approaches to fine-tuning a model with your data. A popular technique is to process your data with your LLM and use the outputs to train a new classifier that solves your specific task. Notice that here you aren't modifying the LLM. Instead, you are chaining it with your trained classifier. Another approach is to modify the parameters of the LLM using your data. Think of this as "rewiring" the model in a way that solves your particular task. The results and costs will vary depending on how many layers you want to fine-tune from the original model. Many companies think that fine-tuning is the solution to their problems. In my experience, many will benefit from exploring the other two approaches. I love explaining Machine Learning and Artificial Intelligence ideas. If you enjoy in-depth content like this, follow me Santiago so you don't miss what comes next.

Santiago

384,510 просмотров • 3 лет назад