wpeebles/G.pt
Official PyTorch Implementation of "Learning to Learn with Generative Models of Neural Network Checkpoints"
This project helps machine learning researchers efficiently explore and optimize neural network architectures. By inputting an existing neural network's parameters and a target performance (like a desired loss or error rate), it outputs an updated set of parameters that should achieve that target, often in a single step. It's designed for researchers working on model development and optimization tasks, offering a novel way to 'learn to learn' for various neural network types.
345 stars. No commits in the last 6 months.
Use this if you are a machine learning researcher looking for a new method to quickly generate optimized neural network parameters or explore the parameter space of different models.
Not ideal if you are an application developer seeking a ready-to-use library for standard model training or fine-tuning, as this is a research-focused tool for meta-learning.
Stars
345
Forks
24
Language
Python
License
BSD-2-Clause
Category
Last pushed
Oct 03, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/wpeebles/G.pt"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
tabularis-ai/be_great
A novel approach for synthesizing tabular data using pretrained large language models
EleutherAI/gpt-neox
An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron...
shibing624/textgen
TextGen: Implementation of Text Generation models, include LLaMA, BLOOM, GPT2, BART, T5, SongNet...
ai-forever/ru-gpts
Russian GPT3 models.
AdityaNG/kan-gpt
The PyTorch implementation of Generative Pre-trained Transformers (GPTs) using Kolmogorov-Arnold...