amirsaffari

followers

0

following

stars

Amazon

Cambridge, UK

http://www.ymer.org/amir/

Amir Saffari's starred repositories

llm.c

LLM training in simple, raw C/CUDA

Language:CudaMIT2048900

works

The code of several works on oimo.io/works

Language:HaxeMIT124900

torchtune

A Native-PyTorch Library for LLM Fine-tuning

Language:PythonBSD-3-Clause337900

mergoo

A library for easily merging multiple LLM experts, and efficiently train the merged LLM.

Language:PythonLGPL-3.033900

recurrentgemma

Open weights language model from Google DeepMind, based on Griffin.

Language:PythonApache-2.054400

AbletonOSC

Control Ableton Live 11 via Open Sound Control (OSC)

Language:PythonMIT37300

synthesizer

A multi-purpose LLM framework for RAG and data creation.

Language:PythonApache-2.059500

LongLoRA

Code and documents of LongLoRA and LongAlpaca (ICLR 2024 Oral)

Language:PythonApache-2.0250700

UniAudio

The Open Source Code of UniAudio

Language:Python46000

neural-amp-modeler

Neural network emulator for guitar amplifiers.

Language:PythonMIT167600

curated-transformers

🤖 A PyTorch library of curated Transformer models and their composable components

Language:PythonMIT84900

OpenELM

Evolution Through Large Models

Language:PythonMIT65500

ddpo-pytorch

DDPO for finetuning diffusion models, implemented in PyTorch with LoRA support

Language:PythonMIT34800

elementary

Elementary is a JavaScript library for digital audio signal processing.

Language:CMIT29000

home-robot

Mobile manipulation research tools for roboticists

Language:PythonMIT78600

levanter

Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax

Language:PythonApache-2.045700

pedalboard

🎛 🔊 A Python library for audio.

Language:C++GPL-3.0493300

audiocraft

Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.

Language:PythonMIT1995000

EasyLM

Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Flax.

Language:PythonApache-2.0227300

mppi-isaac

Model Predictive Path Integral Control using isaacgym for rollouts, gpu-accelerated

Language:Python16100

mujoco_mpc

Real-time behaviour synthesis with MuJoCo, using Predictive Control

Language:C++Apache-2.086000

superagent

🥷 Run AI-agents with an API

Language:TypeScriptNOASSERTION461900

chain-of-thought-hub

Benchmarking large language models' complex reasoning ability with chain-of-thought prompting

Language:Jupyter NotebookMIT241200

Minari

A standard format for offline reinforcement learning datasets, with popular reference datasets and related utilities

Language:PythonNOASSERTION22800

soundstorm-pytorch

Implementation of SoundStorm, Efficient Parallel Audio Generation from Google Deepmind, in Pytorch

Language:PythonMIT113700

FlexFlow

FlexFlow Serve: Low-Latency, High-Performance LLM Serving

Language:C++Apache-2.0156200

guidance

A guidance language for controlling large language models.

Language:Jupyter NotebookMIT1788900

llama.cpp

Port of Facebook's LLaMA model in C/C++

Language:CMIT4500

RedPajama-Data

The RedPajama-Data repository contains code for preparing large datasets for training large language models.

Language:PythonApache-2.0440900

wordcraft

✨✍️ Wordcraft is an AI-powered text editor with an emphasis on short story writing

Language:TypeScriptApache-2.023100