textgrad
Gradient calculator
An autograd engine for textual gradients using large language models to backpropagate gradients.
TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients.
2k stars
19 watching
164 forks
Language: Python
last commit: 3 months ago
Linked from 1 awesome list
ai-optimizationcompound-systemslarge-language-modelsprompt-optimizationtextual-gradients
Related projects:
Repository | Description | Stars |
---|---|---|
| PyTorch implementation of a technique to improve the interpretability of deep learning models by adding noise to the gradients | 168 |
| A library that provides reusable, customizable gradient components and utilities for generating gradients. | 229 |
| A high-performance tool for computing derivatives of complex functions used in various scientific and engineering applications. | 337 |
| A Swift library for creating gradient layers, colors, and images with customizable directions and corner radii. | 267 |
| Provides automatic differentiation capabilities for numerical computations in Python | 12 |
| A PyTorch implementation of attributing the impact of inputs on deep neural network outputs | 182 |
| A TensorFlow implementation of generating images from text descriptions using a Generative Adversarial Network (GAN) architecture | 602 |
| A tool to generate linear web gradients with a user interface. | 1,992 |
| A collection of curated gradients made in Swift for use in iOS and other platforms | 803 |
| An optimized distributed gradient boosting library for machine learning | 572 |
| A differentiable rendering library that computes accurate gradients without approximation and can simulate realistic lighting phenomena. | 1,396 |
| A tool to demonstrate and analyze attacks on private data in machine learning models using gradients | 34 |
| A customizable Core Graphics based gradient view for iOS development | 175 |
| A Rust library for creating customizable color gradients with various input formats and flexible domain settings | 290 |
| Automates model building and deployment process by optimizing hyperparameters and compressing models for edge computing. | 200 |