vicgalle

mlx

MLX: An array framework for Apple silicon

mamba

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

GPU-Puzzles

Solve puzzles. Learn CUDA.

mlx-examples

Examples in the MLX framework

weak-to-strong

lorax

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

EasyEdit

An Easy-to-use Knowledge Editing Framework for LLMs.

math-lm

tp

Decompilation of The Legend of Zelda: Twilight Princess (GCN, USA)

HALOs

A library with extensible implementations of DPO, KTO, PPO, and other human-aware loss functions (HALOs).

Awesome-LLM-Safety

A curated list of security-related papers, articles, and resources focused on Large Language Models (LLMs). This repository aims to provide researchers, practitioners, and enthusiasts with insights into the security implications, challenges, and advancements surrounding these powerful models.

prompt-lookup-decoding

RoleLLM-public

RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models

llm-verified-with-monte-carlo-tree-search

LLM verified with Monte Carlo Tree Search

auto-j

Generative Judge for Evaluating Alignment

Multi-Camera-Person-Tracking-and-Re-Identification

Simple model to Track and Re-identify individuals in different cameras/videos.(Yolov3 & Yolov4)

multi_token

Embed arbitrary modalities (images, audio, documents, etc) into large language models.

Jailbreak_LLM

AI-Security-and-Privacy-Events

A curated list of academic events on AI Security & Privacy

SafetyBench

Official github repo for SafetyBench, a comprehensive benchmark to evaluate LLMs' safety.

sycophancy-eval

datasets from the paper "Towards Understanding Sycophancy in Language Models"

Synthetic-Persona-Chat

The Synthetic-Persona-Chat dataset is a synthetically generated persona-based dialogue dataset. It extends the original Persona-Chat dataset.

multi-camera-people-tracking

Multi-camera people tracking is to monitoring people with multiple cameras and connecting each other

cog-sdxl-multi-controlnet-lora

SDXL Multi-controlnet with loras

distilled-self-critique

distilled Self-Critique refines the outputs of a LLM with only synthetic data

finetune-fuyu

example showing finetuning of fuyu

implicitMAP

Code to accompany "Implicit Maximum a Posteriori Filtering via Adaptive Optimization" by Gianluca Bencomo, Jake Snell, and Tom Griffiths (under review at ICLR 2023).

metaprompting

For the paper "On Meta-Prompting"

fsam