Stars
Stanford NLP Python library for Representation Finetuning (ReFT)
Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
DSPy: The framework for programming—not prompting—language models
🚀 A very efficient Texas Holdem GTO solver
Evaluate interpretability methods on localizing and disentangling concepts in LLMs.
Stanford NLP Python library for understanding and improving PyTorch models via interventions
Function Vectors in Large Language Models (ICLR 2024)
Universal Adversarial Triggers for Attacking and Analyzing NLP (EMNLP 2019)
The codebase for our ACL2023 paper: Did You Read the Instructions? Rethinking the Effectiveness of Task Definitions in Instruction Learning
The repository of the preprint paper "Evaluating the Zero-shot Robustness of Instruction-tuned Language Models"
A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)
Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities o 765E f language models
Task-based datasets, preprocessing, and evaluation for sequence models.
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Reproduce results and replicate training fo T0 (Multitask Prompted Training Enables Zero-Shot Task Generalization)
Toolkit for creating, sharing and using natural language prompts.
Faithfulness and factuality annotations of XSum summaries from our paper "On Faithfulness and Factuality in Abstractive Summarization" (https://www.aclweb.org/anthology/2020.acl-main.173.pdf).
An inductive logic programming system
A beautiful, simple, clean, and responsive Jekyll theme for academics