tnguyen21

Awesome-Interpretability-in-Large-Language-Models

This repository collects all relevant resources about interpretability in LLMs

CPM

sycophancy-intervention

Scripts for generating synthetic finetuning data for reducing sycophancy.

llama-stack-apps

Agentic components of the Llama Stack APIs

llama-models

Utilities intended for use with Llama models.

weak-to-strong

CLIP

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

flash-attention

Fast and memory-efficient exact attention

llama_deploy

Deploy your agentic worfklows to production

grokfast

Official repository for the paper "Grokfast: Accelerated Grokking by Amplifying Slow Gradients"

tcp-server

A single-threaded TCP server with an event loop using the poll system call written in C.

gpu-optimization-workshop

Slides, notes, and materials for the workshop

dangerous-capability-evaluations

torax

TORAX: Tokamak transport simulation in JAX

code_qa

Question answering on codebase

flash-linear-attention

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

Scalable-Electrolyte-Simulation

This repository contains the data and scripts necessary to reproduce the results presented in the paper: **"Scalable molecular simulation of electrolyte solutions with quantum chemical accuracy"** by Junji Zhang, Joshua Pagotto, Tim Gould, and Timothy T. Duignan.

openpom

Replication of the Principal Odor Map paper by Lee et al (2022). The model is implemented such that it integrates with DeepChem

OpenCRISPR

AI-generated gene editing systems

llama3-from-scratch

llama3 implementation one matrix multiplication at a time

deepchem

Democratizing Deep-Learning for Drug Discovery, Quantum Chemistry, Materials Science and Biology

pytorch_geometric

Graph Neural Network Library for PyTorch

equiformer_v2

[ICLR 2024] EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations

fairchem

FAIR Chemistry's library of machine learning methods for chemistry

inspect_ai

Inspect: A framework for large language model evaluations

gpt-neox

An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries

InfiniTransformer

Unofficial PyTorch/🤗Transformers(Gemma/Llama3) implementation of Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention

Automatic-Circuit-Discovery

nnsight

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

function_vectors

Function Vectors in Large Language Models (ICLR 2024)