InstructCoder: Instruction Tuning Large Language Models for Code Editing | Oral ACL-2024 srw

A Mutation Testing Framework of In-Context Learning Systems

Code and example data for the paper: Rule Based Rewards for Language Model Safety

Code release for "Improved baselines for vision-language pre-training"

Schedule-Free Optimization in PyTorch

🚀 Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton

Utilities intended for use with Llama models.

Official code for NeurIPS 2023 paper "Laplacian Canonization: A Minimalist Approach to Sign and Basis Invariant Spectral Embedding".

Evaluate interpretability methods on localizing and disentangling concepts in LLMs.

Transformers are Sample-Efficient World Models. ICLR 2023, notable top 5%.

A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.

The nnsight package enables interpreting and manipulating the internals of deep learned models.

AmpleGCG: Learning a Universal and Transferable Generator of Adversarial Attacks on Both Open and Closed LLM

A library for mechanistic interpretability of GPT-style language models

Diffusion on syntax trees for program synthesis

[ICLR'24] RAIN: Your Language Models Can Align Themselves without Finetuning

Notebooks accompanying Anthropic's "Toy Models of Superposition" paper

OODRobustBench: a Benchmark and Large-Scale Analysis of Adversarial Robustness under Distribution Shift. ICML 2024 and ICLRW-DMLR 2024

📰 Must-read papers and blogs on LLM based Long Context Modeling 🔥

Jailbreak artifacts for JailbreakBench

Context is Environment