P-Lambda

All

12 repositories

dsir
Public
DSIR large-scale data selection framework for language model training
data language-models large-scale data-filtering data-selection importance-resampling
Python
•
MIT License
•19•241•3•1•Updated Apr 7, 2024Apr 7, 2024
wilds
Public
A machine learning benchmark of in-the-wild distribution shifts, with data loaders, evaluators, and default models.
Python
•
MIT License
•130•558•11•2•Updated Jan 26, 2024Jan 26, 2024
incontext-learning
Public
Experiments and code to generate the GINC small-scale in-context learning dataset from "An Explanation for In-context Learning as Implicit Bayesian Inference"
language-modeling dataset few-shot-learning gpt-3 in-context-learning
Python
•13•103•1•0•Updated Nov 10, 2023Nov 10, 2023
jukemir
Public
Perform transfer learning for MIR using Jukebox!
Shell
•
MIT License
•23•177•3•0•Updated Oct 12, 2023Oct 12, 2023
verified_calibration
Public
Calibration library and code for the paper: Verified Uncertainty Calibration. Ananya Kumar, Percy Liang, Tengyu Ma. NeurIPS 2019 (Spotlight).
metrics toolbox calibration ece uncertainty-calibration calibration-library
Python
•
MIT License
•20•144•8•1•Updated Nov 10, 2022Nov 10, 2022
dragon
Public
[NeurIPS 2022] DRAGON 🐲: Deep Bidirectional Language-Knowledge Graph Pretraining
Python
•
Apache License 2.0
•45•0•0•0•Updated Oct 19, 2022Oct 19, 2022
LinkBERT
Public
[ACL 2022] LinkBERT: A Knowledgeable Language Model 😎 Pretrained with Document Links
Python
•
Apache License 2.0
•43•0•0•0•Updated Apr 5, 2022Apr 5, 2022
swords
Public
The Stanford Word Substitution (Swords) Benchmark
nlp lexical-substitution writing-assistant benchmark swords
Python
•6•31•2•1•Updated Mar 24, 2022Mar 24, 2022
composed_finetuning
Public
Code for the ICML 2021 paper "Composed Fine-Tuning: Freezing Pre-Trained Denoising Autoencoders for Improved Generalization" by Sang Michael Xie, Tengyu Ma, Percy Liang
translation semi-supervised-learning image-generation structured-prediction ood-generalization
Python
•
MIT License
•1•4•0•0•Updated Dec 28, 2021Dec 28, 2021
in-n-out
Public
Code for the ICLR 2021 Paper "In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness"
self-training robustness pre-training out-of-distribution
Python
•0•12•1•0•Updated Oct 23, 2021Oct 23, 2021
gradual_domain_adaptation
Public
Python
•12•36•0•0•Updated Apr 16, 2021Apr 16, 2021
robust_tradeoff
Public
Code for the ICML 2020 paper "Understanding and Mitigating the Tradeoff Between Robustness and Accuracy", Aditi Raghunathan, Sang Michael Xie, Fanny Yang, John Duchi, and Percy Liang. Paper available at https://arxiv.org/pdf/2002.10716.pdf.
robustness adversarial-examples tradeoff
Python
•
MIT License
•0•9•0•0•Updated Jan 4, 2021Jan 4, 2021