正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Your LLM knows the answer before it writes a single token. So we stopped making it write. transformers serve now turns any LLM or VLM into a decision model with `/v1/systemone` endpoint. Decision model standardization coming soon in transformers by Arthur Zucker Demos below👇

Marc Sun

1,692 subscribers

13,808 次观看 • 17 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

10 条评论

Marc Sun 的头像

Marc Sun17 天前

Try it in two commands ! Ask typed questions about anything and get a probability for every answer. Docs:

Marc Sun 的头像

Marc Sun17 天前

Tetris

Marc Sun 的头像

Marc Sun17 天前

Snake

Marc Sun 的头像

Marc Sun17 天前

Geoguesser

Paul Michalik 的头像

Paul Michalik17 天前

@art_zucker That was just a question of time...

Timothy McKenzie 的头像

Timothy McKenzie16 天前

@art_zucker Does changing the order or wording of the options affect the scores much? I’m curious how stable they are for task routing.

CV.YH 的头像

CV.YH17 天前

@art_zucker take a look

PyLocket 的头像

PyLocket16 天前

@art_zucker Skipping token generation simplifies inference but loses token-level diagnostics

MrOzi 的头像

MrOzi17 天前

@art_zucker Interesting shift, but tokens are how we audit the machine’s reasoning.

Arvind 的头像

Arvind17 天前

@art_zucker nice

相关视频

Fun addition to transformers serve: you can now turn any of the 250 LLM & VLM model into a JEV-like decision model. /v1/systemone scores a set of decision with the model's logits. No need to generate text! Which one of them can get microducks across the finish line fast?

Fun addition to transformers serve: you can now turn any of the 250 LLM & VLM model into a JEV-like decision model. /v1/systemone scores a set of decision with the model's logits. No need to generate text! Which one of them can get microducks across the finish line fast?

Lysandre

16,060 次观看 • 17 天前

LET'S GO! Cursor using local 🤗 transformers models! You can now test ANY transformers-compatible LLM against your codebase. From hacking to production, it takes only a few minutes: anything `transformers` does, you can serve into your app 🔥 Here's a demo with Qwen3 4B:

LET'S GO! Cursor using local 🤗 transformers models! You can now test ANY transformers-compatible LLM against your codebase. From hacking to production, it takes only a few minutes: anything `transformers` does, you can serve into your app 🔥 Here's a demo with Qwen3 4B:

João Gante

33,536 次观看 • 1 年前

Learning to Decode Collaboratively with Multiple Language Models We propose a method to teach multiple large language models (LLM) to collaborate by interleaving their generations at the token level. We model the decision of which LLM generates the next token as a latent

Learning to Decode Collaboratively with Multiple Language Models We propose a method to teach multiple large language models (LLM) to collaborate by interleaving their generations at the token level. We model the decision of which LLM generates the next token as a latent

AK

52,644 次观看 • 2 年前

We turned Qwen3.8-27B into a multimodal decision model. It beat Pokémon FireRed’s elite four and champion with sub-100 ms decisions from live game state. With SGLang’s native /v1/decisions, you can now turn LLMs and VLMs into classification and scoring models. We also added /v1/systemone so Jev-like open models can work with the TypeSafe SDK.

We turned Qwen3.8-27B into a multimodal decision model. It beat Pokémon FireRed’s elite four and champion with sub-100 ms decisions from live game state. With SGLang’s native /v1/decisions, you can now turn LLMs and VLMs into classification and scoring models. We also added /v1/systemone so Jev-like open models can work with the TypeSafe SDK.

SGLang

253,209 次观看 • 29 天前

TypeSafe AI released Jev. I truly believe this is a game changing kind of AI model. No joke. It does NOT replace LLMs. But in tandem with LLMs it feels like a missing building block. It makes the kind of applications you can build now SO much better and more powerful. And cheaper! It's an AI model that's all about decision making. But not like old-school classifiers ("fraud or no fraud") but with flexibility you know from LLMs. Feed some input (eg customer email, any other text, structured data) into it, define your questions ("which team should answer this email?") and dimensions ("sales, technical, fraud") and get back a response within milliseconds. No long reasoning, no exploding token costs. Sure, that answer will still be generated by an LLM, complex questions may still require an (additional) LLM but this model is really mindblowing.

TypeSafe AI released Jev. I truly believe this is a game changing kind of AI model. No joke. It does NOT replace LLMs. But in tandem with LLMs it feels like a missing building block. It makes the kind of applications you can build now SO much better and more powerful. And cheaper! It's an AI model that's all about decision making. But not like old-school classifiers ("fraud or no fraud") but with flexibility you know from LLMs. Feed some input (eg customer email, any other text, structured data) into it, define your questions ("which team should answer this email?") and dimensions ("sales, technical, fraud") and get back a response within milliseconds. No long reasoning, no exploding token costs. Sure, that answer will still be generated by an LLM, complex questions may still require an (additional) LLM but this model is really mindblowing.

Maximilian

43,939 次观看 • 1 个月前

He is a 1st year AI engineering student at Stanford - and already launched an automated system making $2.1M a year: 00:20 - how Anthropic engineers make millions with LLM and Transformers 38:34 - In-Context Learning makes AI smarter for free 59:47 - 1st year student made $2.1M using LLM from scratch after watching I gave LLM the idea I had been holding in my head for 3 years - it built it in one evening. save & watch - the article below is a step by step guide to build your automated LLM system.

He is a 1st year AI engineering student at Stanford - and already launched an automated system making $2.1M a year: 00:20 - how Anthropic engineers make millions with LLM and Transformers 38:34 - In-Context Learning makes AI smarter for free 59:47 - 1st year student made $2.1M using LLM from scratch after watching I gave LLM the idea I had been holding in my head for 3 years - it built it in one evening. save & watch - the article below is a step by step guide to build your automated LLM system.

Noisy

43,713 次观看 • 2 个月前

Ollama now supports Jev-like decision models all locally. Use decision models like Nimble for tasks like ticket triaging, model routing, and content moderation. ollama pull nimble Here’s Nimble playing Ollama racer through the new local /v1/systemone API by making decisions in real-time. 🏎️

Ollama now supports Jev-like decision models all locally. Use decision models like Nimble for tasks like ticket triaging, model routing, and content moderation. ollama pull nimble Here’s Nimble playing Ollama racer through the new local /v1/systemone API by making decisions in real-time. 🏎️

ollama

667,164 次观看 • 29 天前

Project #2: LLM Visualization So I created a web-page to visualize a small LLM, of the sort that's behind ChatGPT. Rendered in 3D, it shows all the steps to run a single token inference. (link in bio)

Project #2: LLM Visualization So I created a web-page to visualize a small LLM, of the sort that's behind ChatGPT. Rendered in 3D, it shows all the steps to run a single token inference. (link in bio)

Brendan Bycroft

1,203,096 次观看 • 2 年前

Met a guy making $1.6 million/year as an LLM engineer. I asked him how he learned LLMs from scratch. He sent me the exact video that got him in. A 1 hour course on how LLMs actually work. He shows how transformers inside LLMs like ChatGPT & Claude are actually built. I watched it last night. Halfway through, I realized LLM architecture is way simpler than they make it look. Bookmark this and read the article below. • 00:00 - LLM foundations • 04:21 - LLM tokenization • 05:43 - LLMs vector embeddings • 22:16 - attention mechanism of LLM • 43:42 - LLM multi head attention

Met a guy making $1.6 million/year as an LLM engineer. I asked him how he learned LLMs from scratch. He sent me the exact video that got him in. A 1 hour course on how LLMs actually work. He shows how transformers inside LLMs like ChatGPT & Claude are actually built. I watched it last night. Halfway through, I realized LLM architecture is way simpler than they make it look. Bookmark this and read the article below. • 00:00 - LLM foundations • 04:21 - LLM tokenization • 05:43 - LLMs vector embeddings • 22:16 - attention mechanism of LLM • 43:42 - LLM multi head attention

Roan

81,846 次观看 • 3 个月前

BOOOM! transformers now has a baked-in http server w/ OpenAI spec compatible API Launch it with `transformers serve` and connect your favorite apps. Here I'm running 👋 Jan with local transformers and hot-swappable models. There is preliminary tool call support as well!

BOOOM! transformers now has a baked-in http server w/ OpenAI spec compatible API Launch it with `transformers serve` and connect your favorite apps. Here I'm running 👋 Jan with local transformers and hot-swappable models. There is preliminary tool call support as well!

Lysandre

24,806 次观看 • 1 年前

Texture any 3D model in seconds 😱 Yes your read it right, using MeshyAI and their generative AI tool. All you need is to import your model, write a prompt, Done. Try it out today, link below 👇

Texture any 3D model in seconds 😱 Yes your read it right, using MeshyAI and their generative AI tool. All you need is to import your model, write a prompt, Done. Try it out today, link below 👇

Linus ✦ Ekenstam

483,772 次观看 • 3 年前

Introducing `gpt-llm-trainer` ✍️ The world's simplest way to train a task-specific LLM. **Just write a sentence describing the model you want.** A chain of AI systems will generate a dataset and train a model for you. And it's open-source:

Introducing `gpt-llm-trainer` ✍️ The world's simplest way to train a task-specific LLM. Just write a sentence describing the model you want. A chain of AI systems will generate a dataset and train a model for you. And it's open-source:

Matt Shumer

337,464 次观看 • 3 年前

The biggest stars of #SXSW. Literally. Coming soon to a city near you. #Transformers #RiseOfTheBeasts

The biggest stars of #SXSW. Literally. Coming soon to a city near you. #Transformers #RiseOfTheBeasts

Transformers

187,530 次观看 • 3 年前

Introducing `claude-llm-trainer` ✍️ The world's simplest way to train a task-specific LLM. Just write a sentence describing the model you want. A chain of AI systems will generate a dataset and train a model for you. And it's open-source.

Introducing `claude-llm-trainer` ✍️ The world's simplest way to train a task-specific LLM. Just write a sentence describing the model you want. A chain of AI systems will generate a dataset and train a model for you. And it's open-source.

Matt Shumer

383,365 次观看 • 2 年前

Introducing llms.txt Generator ✨ You can now concatenate any website into a single text file that can be fed into any LLM. We crawl the whole website with and extract data with gpt-4o-mini. Create your own llms.txt at

Introducing llms.txt Generator ✨ You can now concatenate any website into a single text file that can be fed into any LLM. We crawl the whole website with and extract data with gpt-4o-mini. Create your own llms.txt at

Eric Ciarla (hiring)

230,151 次观看 • 1 年前

Run OpenClaw 2.0 through Atomic Chat local LLM server on a 16GB MacBook 💻🦞 We gave OpenClaw a task to edit a video using Gemma 4 E4B, it successfully created a welcome video in two minutes by writing custom React code Load the model in start the LLM server and OpenClaw 2.0 picks it right up

Run OpenClaw 2.0 through Atomic Chat local LLM server on a 16GB MacBook 💻🦞 We gave OpenClaw a task to edit a video using Gemma 4 E4B, it successfully created a welcome video in two minutes by writing custom React code Load the model in start the LLM server and OpenClaw 2.0 picks it right up

atomic.chat

44,775 次观看 • 1 个月前

I needed a quick tool to convert any sort of GitHub links into a format an LLM could read. So I built it. GitHub → LLM It's completely free and works with projects, folders, or files 🪄 Deployed on Replit ⠕

I needed a quick tool to convert any sort of GitHub links into a format an LLM could read. So I built it. GitHub → LLM It's completely free and works with projects, folders, or files 🪄 Deployed on Replit ⠕

Pietro Schirano

120,827 次观看 • 2 年前