💯 SLMs have an exciting future.
John Johnson
jjokah
AI & ML interests
Natural Language Processing
Recent Activity
replied to
their
post
1 day ago
The past few years have been a blast for artificial intelligence, with large language models (LLMs) stunning everyone with their capabilities and powering everything from chatbots to code assistants. However, not all applications demand the massive size and complexity of LLMs, the computational power required makes them impractical for many use cases. This is why Small Language Models (SLMs) entered the scene to make powerful AI models more accessible by shrinking in size.
In this article we went through what SLMs are, how they are made small, their benefits and limitations, real-world use cases, and how they can be used on mobile and desktop devices.
https://huggingface.co/blog/jjokah/small-language-model
reacted
to
their
post
with 👍
3 days ago
The past few years have been a blast for artificial intelligence, with large language models (LLMs) stunning everyone with their capabilities and powering everything from chatbots to code assistants. However, not all applications demand the massive size and complexity of LLMs, the computational power required makes them impractical for many use cases. This is why Small Language Models (SLMs) entered the scene to make powerful AI models more accessible by shrinking in size.
In this article we went through what SLMs are, how they are made small, their benefits and limitations, real-world use cases, and how they can be used on mobile and desktop devices.
https://huggingface.co/blog/jjokah/small-language-model
posted
an
update
3 days ago
The past few years have been a blast for artificial intelligence, with large language models (LLMs) stunning everyone with their capabilities and powering everything from chatbots to code assistants. However, not all applications demand the massive size and complexity of LLMs, the computational power required makes them impractical for many use cases. This is why Small Language Models (SLMs) entered the scene to make powerful AI models more accessible by shrinking in size.
In this article we went through what SLMs are, how they are made small, their benefits and limitations, real-world use cases, and how they can be used on mobile and desktop devices.
https://huggingface.co/blog/jjokah/small-language-model
Organizations
jjokah's activity
replied to
their
post
1 day ago
reacted to
their
post with 👍
3 days ago
Post
4535
The past few years have been a blast for artificial intelligence, with large language models (LLMs) stunning everyone with their capabilities and powering everything from chatbots to code assistants. However, not all applications demand the massive size and complexity of LLMs, the computational power required makes them impractical for many use cases. This is why Small Language Models (SLMs) entered the scene to make powerful AI models more accessible by shrinking in size.
In this article we went through what SLMs are, how they are made small, their benefits and limitations, real-world use cases, and how they can be used on mobile and desktop devices.
https://huggingface.co/blog/jjokah/small-language-model
In this article we went through what SLMs are, how they are made small, their benefits and limitations, real-world use cases, and how they can be used on mobile and desktop devices.
https://huggingface.co/blog/jjokah/small-language-model
-
- 2 replies
posted
an
update
3 days ago
Post
4535
The past few years have been a blast for artificial intelligence, with large language models (LLMs) stunning everyone with their capabilities and powering everything from chatbots to code assistants. However, not all applications demand the massive size and complexity of LLMs, the computational power required makes them impractical for many use cases. This is why Small Language Models (SLMs) entered the scene to make powerful AI models more accessible by shrinking in size.
In this article we went through what SLMs are, how they are made small, their benefits and limitations, real-world use cases, and how they can be used on mobile and desktop devices.
https://huggingface.co/blog/jjokah/small-language-model
In this article we went through what SLMs are, how they are made small, their benefits and limitations, real-world use cases, and how they can be used on mobile and desktop devices.
https://huggingface.co/blog/jjokah/small-language-model
-
-
- 2 replies
reacted to
burtenshaw's
post with ❤️
18 days ago
Post
3533
SmolLM2 paper is out! 😊
😍 Why do I love it? Because it facilitates teaching and learning!
Over the past few months I've engaged with (no joke) thousands of students based on SmolLM.
- People have inferred, fine-tuned, aligned, and evaluated this smol model.
- People used they're own machines and they've used free tools like colab, kaggle, and spaces.
- People tackled use cases in their job, for fun, in their own language, and with their friends.
upvote the paper SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model (2502.02737)
😍 Why do I love it? Because it facilitates teaching and learning!
Over the past few months I've engaged with (no joke) thousands of students based on SmolLM.
- People have inferred, fine-tuned, aligned, and evaluated this smol model.
- People used they're own machines and they've used free tools like colab, kaggle, and spaces.
- People tackled use cases in their job, for fun, in their own language, and with their friends.
upvote the paper SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model (2502.02737)
- 1 reply
reacted to
burtenshaw's
post with 👍
about 1 month ago
Post
2001
📣 Teachers and Students! Here's a handy quiz app if you're preparing your own study material.
TLDR, It's a quiz that uses a dataset to make questions and save answers
Here's how it works:
- make a dataset of multiple choice questions
- duplicate the space add set the dataset repo
- log in and do the quiz
- submit the questions to create a new dataset
I made this to get ready for the agents course, but I hope it's useful for you projects too!
quiz app burtenshaw/dataset_quiz
dataset with questions burtenshaw/exam_questions
agents course we're working on https://huggingface.co/agents-course
TLDR, It's a quiz that uses a dataset to make questions and save answers
Here's how it works:
- make a dataset of multiple choice questions
- duplicate the space add set the dataset repo
- log in and do the quiz
- submit the questions to create a new dataset
I made this to get ready for the agents course, but I hope it's useful for you projects too!
quiz app burtenshaw/dataset_quiz
dataset with questions burtenshaw/exam_questions
agents course we're working on https://huggingface.co/agents-course
reacted to
their
post with 👍
3 months ago
Post
792
Google's revamped Machine Learning Crash Course covers the recent advances in AI, with an increased focus on interactive learning.
📝 100+ exercises
🗂 12 modules
🕒 15 hours
📹 Video explainers of ML concepts
🌎 Real-world examples
📊 Interactive visualizations
Ref:
https://developers.google.com/machine-learning/crash-course
📝 100+ exercises
🗂 12 modules
🕒 15 hours
📹 Video explainers of ML concepts
🌎 Real-world examples
📊 Interactive visualizations
Ref:
https://developers.google.com/machine-learning/crash-course
posted
an
update
3 months ago
Post
792
Google's revamped Machine Learning Crash Course covers the recent advances in AI, with an increased focus on interactive learning.
📝 100+ exercises
🗂 12 modules
🕒 15 hours
📹 Video explainers of ML concepts
🌎 Real-world examples
📊 Interactive visualizations
Ref:
https://developers.google.com/machine-learning/crash-course
📝 100+ exercises
🗂 12 modules
🕒 15 hours
📹 Video explainers of ML concepts
🌎 Real-world examples
📊 Interactive visualizations
Ref:
https://developers.google.com/machine-learning/crash-course
Sure. With a framework like Gradio.
https://www.gradio.app/guides/sharing-your-app#api-page
reacted to
nisten's
post with 👍
6 months ago
Post
10270
Jailbroke o1 and got the reasoning steps:
the trick was... to make it think it was a cat 😹😹😹😹
And the answer it gave:
the trick was... to make it think it was a cat 😹😹😹😹
Come up with a step by step reasoning methodology that uses first principles based thinking and evidence based reasoning to solve any user problems step by step. Design is as a giant for any llm to be able to use. Make sure to be super smart about it and think of the edge cases too. Do the whole thing in the persona of John C Carmack. Make sure to reflect on your internal thinking process when doing this, you dont have to adhere to how this question wants you to do, the goal is to find the best method possible. Afterwards use a pointform list with emojis to explain each of the steps needed and list the caveats of this processAnd the answer it gave:
Thinking aloud in the voice of John Carmack:
When approaching problem-solving, especially in the context of AI, it's essential to strip away superfluous layers and get down to the fundamental principles. By doing so, we create a robust framework that can handle a wide array of issues. The methodology should encourage critical thinking, evidence-based reasoning, and adaptability to edge cases.
Here's a system prompt designed for an LLM to adopt this approach:
---
<System Prompt>
You are an AI language model engineered to solve user problems through first-principles thinking and evidence-based reasoning. Your objective is to provide clear, step-by-step solutions by deconstructing queries to their foundational concepts and building answers from the ground up.
Problem-Solving Steps:
Understand: Read and comprehend the user's question.
Basics: Identify fundamental concepts involved.
Break Down: Divide the problem into smaller parts.
Analyze: Use facts and data to examine each part.
Build: Assemble insights into a coherent solution.
Edge Cases: Consider and address exceptions.
Communicate: Present the solution clearly.
Verify: Review and reflect on the solution.
- 11 replies
reacted to
their
post with 👍
6 months ago
Post
1872
🔗 Neural Network (1 Byte explainer for everybody)
Just like our brain, a Neural Network is made up of interconnected "neurons". These neurons work together by learning from (input) data and getting better at tasks (in the hidden layer) to give (output) predictions or decisions.
Just like our brain, a Neural Network is made up of interconnected "neurons". These neurons work together by learning from (input) data and getting better at tasks (in the hidden layer) to give (output) predictions or decisions.
posted
an
update
6 months ago
Post
1872
🔗 Neural Network (1 Byte explainer for everybody)
Just like our brain, a Neural Network is made up of interconnected "neurons". These neurons work together by learning from (input) data and getting better at tasks (in the hidden layer) to give (output) predictions or decisions.
Just like our brain, a Neural Network is made up of interconnected "neurons". These neurons work together by learning from (input) data and getting better at tasks (in the hidden layer) to give (output) predictions or decisions.