Loading video...

Video Failed to Load

Go Home

๐Ÿš€ Today, we are introducing SmolTools! ๐Ÿš€ Last week, at Hugging Face we made a significant leap forward with the release of SmolLM2, a compact 1.7B language model that sets a new benchmark for performance among models of its size. But beyond the impressive stats, SmolLM2 truly shines in...

100,813 views โ€ข 1 year ago โ€ขvia X (Twitter)

11 Comments

Daniel Nakov's profile picture
Daniel Nakov1 year ago

@andi_marafioti great stuff! i've been finetuning SmolLM2-135M recently and really liking the results and speed of iteration it allows for

Tom Bielecki's profile picture
Tom Bielecki1 year ago

@andi_marafioti @simonw check out SmolAgent for local tool calling

ASSEM's profile picture
ASSEM1 year ago

@andi_marafioti Great Job, congrats to @LoubnaBenAllal1 Team.

Thorsten Linz's profile picture
Thorsten Linz1 year ago

@andi_marafioti @Thom_Wolf @Thom_Wolf, what are your thoughts on SmolTools' efficiency? Do you foresee widespread adoption in the AI community?

Reza Sayar's profile picture
Reza Sayar1 year ago

@andi_marafioti ๐Ÿ”ฅ๐Ÿ”ฅy este temazo!! ๐ŸŽถ๐Ÿ‡ฆ๐Ÿ‡ท

Andi Marafioti's profile picture
Andi Marafioti1 year ago

Subliminal ๐Ÿ˜‚

Nemesis Alm's profile picture
Nemesis Alm1 year ago

@andi_marafioti Looking forward to trying it! Thanks for sharing

Uri Gil's profile picture
Uri Gil1 year ago

@andi_marafioti Nice

ASSEM's profile picture
ASSEM1 year ago

@andi_marafioti @LoubnaBenAllal1 Very interesting and great work to be honest, can't wait to try it.

Laurent Denoue's profile picture
Laurent Denoue1 year ago

@andi_marafioti What is the doc for the max output tokens? Is it limited to 8.192 like the other models or is it longer? I ask because my task is to punctuate longer texts and itโ€™s cumbersome to chunk apriori

Andi Marafioti's profile picture
Andi Marafioti1 year ago

This is using the same smollm2 instruct 1.7B model that was released last week, so the context size is still 8k. Honestly, I find the performance for rewriting is best for shorter texts.

Related Videos

New short course: Collaborative Writing and Coding with OpenAI Canvas! Explore new ways to write and code with OpenAI Canvas, a user-friendly interface that allows you to brainstorm, draft, and refine text and code in collaboration with ChatGPT. In the short course, created with OpenAI, and taught by , a research lead at OpenAI, youโ€™ll learn to use Canvas to enhance your workflows. Canvas lets you go beyond simple chat interactions. It provides a side-by-side workspace where you and ChatGPT can edit and refine text or code collaboratively. This makes brainstorming, drafting, and iterating as you write feel more natural and effective. As the first major update to ChatGPTโ€™s visual interface since its launch in 2022, Canvas gives a new, innovative approach to collaboration with AI. For instance, after writing the first version of your code, Canvas can review it and give suggestions for improvement. It can also help with debugging by adding logging, identifying problems to fix, and writing comments. In addition, you'll also learn what it takes to train the model for an interface like Canvas. In this video-only short course, youโ€™ll: - Learn how to ask for in-line feedback and control the iteration of your work by directly editing selected areas of your text or code from the modelโ€™s output. - Learn how to access quick automation tools in a shortcut menu that allows you to modify your writing tone and length, enhance your code, and restore previous versions of your work. - Learn how to use Canvas as a research assistant tool with an example of asking the model to reason through the screenshot of a plot to write a research report, in which you can ask questions within the created report. - Ask the model to write Python code to replicate the graph seen on a screenshot image. - Go behind the scenes of how you can create a video game, such as Space Battleship, from scratch, edit it, and display it in one self-contained HTML file. - Get a real-world application example of creating a SQL database from the image of its architecture. - Understand the model training and design processes that power Canvas! Please sign up here:

Andrew Ng

128,180 views โ€ข 1 year ago

Culture is genetic because behavior is genetic. This beaver never saw a dam in its life. No beavers or anything else ever taught it to build a dam. It wants to build a dam because it is a beaver. Many beavers together build a big dam. That is beaver culture. Humans are not different. Nothing is different. This is what life is. This is how life works. Your body is your mind. A caterpillar wants to build a chrysalis. A bee wants to build a hive. A lion wants to build a pride. You are not special. You are not above your nature. you are INSIDE of it. The thoughts that we think are genetic thoughts. The crimes we commit are genetic crimes. The art we create is genetic art. Just like this beaver, you can give the animal different sticks and it will build a different dam, but it will always build a dam. And you can give humans different "education," but the human will always use it to do what its genes tell it to do. This is the first big answer that you need. This is the biggest piece of the puzzle. This is how to understand people 90% of the way. You just... notice what they do, and get out of the way, and watch them do it. And if they need sticks, you give them sticks. And if you don't like what they do, you have to get away from them. You cannot train dam-building into them or out of them any more than you can with a beaver. A beaver wants to build a dam because it is a beaver. Whatever you see people build, that's what they wanted to build from the sticks they got in the river they were in. Stop pretending you can change it.

hoe_math = PsychoMath

1,189,824 views โ€ข 11 months ago

99% of AI applications are cool-looking demos. Impressive, but don't get fooled by the hype. It takes a lot to build enterprise-grade products that deliver real value. I have at least three weekly conversations with companies that want to use a Large Language Model with their data. The demand is huge! Here is one idea about what you can do to help. The use cases that most of these companies want to solve are similar: They have an extensive knowledge base and want to build a simple application that uses that information to answer questions. In other words, they need help building Retrieval Augmented Generation (RAG) applications they can use in many different scenarios: 1. To train new employees 2. To help their support team 3. To search old meetings and documents 4. To help with their research However, building these systems is not straightforward. Yes, there's a lot of information online, but there aren't enough people who know how to create solutions that work. Here is the idea: Today, you can build an enterprise-grade RAG application without writing code. A couple of MIT PhDs with 10+ years of experience building AI applications created . It's a no-code platform for building applications using Large Language Models. They are partnering with me on this post. You can use Stack AI to create, test, and deploy an end-to-end production-ready AI system. It's SOC-2, HIPAA, and GDPR compliant and offers SSO, role management, access control, and on-premise deployments. Of course, you can use the platform with any LLM on the market now. It's the whole nine yards for building AI applications. Check them out here: 2023 was about models. 2024 is about the tools using these models to build production-ready applications. That's where I'd start.

Santiago

197,702 views โ€ข 2 years ago

We are not okay, and thatโ€™s okay to say. I wish I could tell you that we are standing here and that the rest of the world is standing with us. With you. Sadly I canโ€™t say that. There is a loud and aggressive minority around the world who doesnโ€™t get, that being murdered at a peace festival does not equal resistance. I do however, know that we are standing here on behalf of all those people in the world, with moral clarity. And there are a lot of them. And there are many who want to be here with you. And they are here with you at heart. On October 7th, your loved ones went to Nova. We call it a peace music festival because thatโ€™s what it wasโ€”a place to make new friends, to let loos explore and celebrate life. And this juxtaposition hurts the most โ€”because on that day, the light your loved ones were, was met with the most unimaginable darkness. Our lives will never be the same. But today, as we remember them, we also make a promise: to honor their memory by living as they would have. As we stand here in grief, we have a message to the world: we will not be defeated. Israel was attacked on October 7th and every day since, for the crime of existing. For the audacity of just being here. But we are here, and we are here to stay. And despite the trauma weโ€™ve faced, we are in Israel, standing strong together, committed to the memories of those we lost and to the return of our hostages. We, despite the pain and alongside it, are going to build a brighter future. Together. We will dance again. Am Yisrael Chai Forever

Noa Tishby

32,742 views โ€ข 10 months ago