playground
dspy
Our great sponsors
playground | dspy | |
---|---|---|
16 | 20 | |
11,674 | 10,471 | |
1.1% | 31.0% | |
0.0 | 9.9 | |
3 months ago | 1 day ago | |
TypeScript | Python | |
Apache License 2.0 | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
playground
-
Why do tree-based models still outperform deep learning on tabular data? (2022)
Not the parent, but NNs typically work better when you can't linearize your data. For classification, that means a space in which hyperplanes separate classes, and for regression a space in which a linear approximation is good.
For example, take the circle dataset here: https://playground.tensorflow.org
That doesn't look immediately linearly separable, but since it is 2D we have the insight that parameterizing by radius would do the trick. Now try doing that in 1000 dimensions. Sometimes you can, sometimes you can't or do want to bother.
-
Introduction to TensorFlow for Deep Learning
For visualisation and some fun: http://playground.tensorflow.org/
- TensorFlow Playground – Tinker with a NN in the Browser
-
Visualization of Common Algorithms
https://seeing-theory.brown.edu/
https://www.3blue1brown.com/
https://playground.tensorflow.org/
-
Stanford A.I. Courses
There’s an interactive neural network you can train here, which can give some intuition on wider vs larger networks:
https://mlu-explain.github.io/neural-networks/
See also here:
http://playground.tensorflow.org/
-
Let's revolutionize the CPU together!
This site is worth playing around with to get a feel for neural networks, and somewhat about ML in general. There are lots of strategies for statistical learning, and neural nets are only one of them, but they essentially always boil down into figuring out how to build a “classifier”, to try to classify data points into whatever category they best belong in.
-
Curious about Inputs for neural network
I don’t know much experimenting you’ve done, but many repeated small scale experiments might give you a better intuition at least. I highly recommend this online tool for playing with different environmental variables, even if you’re comfortable coding up your own experiments: http://playground.tensorflow.org
-
Intel Announces Aurora genAI, Generative AI Model With 1 Trillion Parameters
Even if you can’t code, play around with this tool: https://playground.tensorflow.org — you can adjust the shape of the NN and watch how well it classifies the data. Model size obviously matters.
-
Where have all the hackers gone?
I don't think so. You can easily play around in the browser, using Javascript, or on https://processing.org/, https://playground.tensorflow.org/, https://scratch.mit.edu/, etc.
If anything the problem is that today's kids have too many options. And sure, some are commercial.
-
[Discussion] Questions about linear regression, polynomial features and multilayer NN.
Well there is no point of using a multilayer linear neural network, because a cascade of linear transformations can be reduced to a single linear transformation. So you can only approximate linear functions. However if you have prior knowledge about the non linearity of your data lets say you know that it is a linear combination of polynomials up to certain degree, you can expand your input space by explicitly making non linear transformation. For instance a 1D linear regression can be modeled by 2 input neurons and 1 output neuron where the activation of the output is the identity. The input neuron x0 will take a constant input namely 1 and the second input neuron x1 will takes your data x. The output neuron will be y=w_0 * 1+w_1 *x which is equal to y=w_0 +w_1 * x. Let us say that your data follows a polynomial form, the idea is to add input neurons and expand your input to for instance X=[1 x x2] in this case you have 3 input neurons where the third is an explict non linear form of the input so y=w_0 + w_1 x +w_2 x2. The general idea is to find a space where the problem becomes linear. In real life example these spaces are non trivial the power of neural network is that they can find by optimization such space without explicitly encoding these non linearities. Try playing around with https://playground.tensorflow.org/ you can get an intuition about your question.
dspy
- Ask HN: Most efficient way to fine-tune an LLM in 2024?
-
Princeton group open sources "SWE-agent", with 12.3% fix rate for GitHub issues
DSPy is the best tool for optimizing prompts [0]: https://github.com/stanfordnlp/dspy
Think of it as a meta-prompt optimizer, it uses a LLM to optimize your prompts, to optimize your LLM.
-
Winner of the SF Mistral AI Hackathon: Automated Test Driven Prompting
Isn’t this just a very naive implementation of what DsPY does?
https://github.com/stanfordnlp/dspy
I don’t understand what is exceptional here.
-
Show HN: Fructose, LLM calls as strongly typed functions
Have you done any comparison with DSPy ? (https://github.com/stanfordnlp/dspy)
Feels very similiar to DSPy except you dont have optimizations yet. But I like your API and the programming model your are enforcing through this.
-
AI Prompt Engineering Is Dead
I'm interested in hearing if anyone has used DSPy (https://github.com/stanfordnlp/dspy) just for prompt optimization for GPT-3.5 or GPT-4. Was it worth the effort and much better than manual prompt iteration? Was the optimized prompt some weird incantation? Any other insights?
-
Ask HN: Are you using a GPT to prompt-engineer another GPT?
You should check out x.com/lateinteraction's DSPy — which is like an optimizer for prompts — https://github.com/stanfordnlp/dspy
- SuperDuperDB - how to use it to talk to your documents locally using llama 7B or Mistral 7B?
- FLaNK Stack Weekly for 12 September 2023
- Stanford DSPy: The framework for programming with foundation models
What are some alternatives?
clip-interrogator - Image to prompt with BLIP and CLIP
semantic-kernel - Integrate cutting-edge LLM technology quickly and easily into your apps
nvim-treesitter - Nvim Treesitter configurations and abstraction layer
open-interpreter - A natural language interface for computers
pyllama - LLaMA: Open and Efficient Foundation Language Models
FastMJPG - FastMJPG is a command line tool for capturing, sending, receiving, rendering, piping, and recording MJPG video with extremely low latency. It is optimized for running on constrained hardware and battery powered devices.
lake.nvim - A simplified ocean color scheme with treesitter support
prompt-engine-py - A utility library for creating and maintaining prompts for Large Language Models
developer - the first library to let you embed a developer agent in your own app!
machine-learning-specialization-andrew-ng - A collection of notes and implementations of machine learning algorithms from Andrew Ng's machine learning specialization.
AgentOoba - An autonomous AI agent extension for Oobabooga's web ui