NTT123

flux-fp8-api

Flux diffusion model implementation using quantized fp8 matmul & remaining layers use faster half precision accumulate, which is ~2x faster on consumer devices.

speech-to-speech

Speech To Speech: an effort for an open-sourced and modular GPT4-o

descript-audio-codec

State-of-the-art audio codec with 90x compression factor. Supports 44.1kHz, 24kHz, and 16kHz mono/stereo audio.

parler-tts

Inference and training library for high-quality TTS models.

llm2vec

Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'

LS-LLaMA

A Simple but Powerful SOTA NER Model | Official Code For Label Supervised LLaMA Finetuning

fusion

A hobby OS implemented in Nim

COLD-Attack

[ICML 2024] COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

llama3-jailbreak

A trivial programmatic Llama 3 jailbreak. Sorry Zuck!

hard-prompts-made-easy

llm-attacks

Universal and Transferable Attacks on Aligned Language Models

TacotronS

Tacotron w/ stepwise monotonic attention

llm-sp

Papers and resources related to the security and privacy of LLMs 🤖

llama3-neurons

Explore MLP features inside Llama3 models

llama3

The official Meta Llama 3 GitHub site

Awesome-LLM-Interpretability

A curated list of LLM Interpretability related material - Tutorial, Library, Survey, Paper, Blog, etc..

nnsight

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

nbsanity

Render notebooks like nbviewer, but using Quarto as the renderer

do-not-answer

Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs

torchtune

A Native-PyTorch Library for LLM Fine-tuning

llm-transparency-tool

LLM Transparency Tool (LLM-TT), an open-source interactive toolkit for analyzing internal workings of Transformer-based language models. *Check out demo at* https://huggingface.co/spaces/facebook/llm-transparency-tool-demo

attorch

A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.

torch-cublas-hgemm

PyTorch half precision gemm lib w/ fused optional bias + optional relu/gelu

dolma

Data and tools for generating and inspecting OLMo pre-training data.

flash_attn_jax

JAX bindings for Flash Attention v2

gemma

Open weights LLM from Google DeepMind.

jax-smi

JAX Synergistic Memory Inspector

QuaRot

Code for QuaRot, an end-to-end 4-bit inference of large language models.

light-speed

A modified VITS that utilizes phoneme duration's ground truth for better robustness

pgx

♟️ Vectorized RL game environments in JAX