Ferdinand Mom (3outeille)

3outeille

Geek Repo

Company:ferdinand.mom@epita.fr

Location:France

Home Page:3outeille.github.io

Twitter:@FerdinandMom

Github PK Tool:Github PK Tool


Organizations
huggingface

Ferdinand Mom's repositories

CNNumpy

A Numpy implementation of a Convolutional Neural Network: slow & fast (im2col/col2im).

Yaae

Yaae: Yet another autodiff engine (written in Numpy).

Language:PythonStargazers:27Issues:1Issues:0
Language:HTMLLicense:MITStargazers:1Issues:0Issues:0

kernl

Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackable.

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:1Issues:0Issues:0

nanoGPT

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Language:PythonLicense:MITStargazers:1Issues:0Issues:0

AutoGPTQ

An easy-to-use model quantization package with user-friendly apis, based on GPTQ algorithm.

Language:PythonLicense:MITStargazers:0Issues:0Issues:0

candle

Minimalist ML framework for Rust

License:Apache-2.0Stargazers:0Issues:0Issues:0

ChatRWKV

ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.

Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0
Language:PythonStargazers:0Issues:1Issues:0
Language:Jupyter NotebookStargazers:0Issues:1Issues:0

ggml

Tensor library for machine learning

License:MITStargazers:0Issues:0Issues:0

gptcore

Fast modular code to create and train cutting edge LLMs

Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0

GPTQ-for-LLaMa

4 bits quantization of LLaMA using GPTQ

Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0
Language:PythonStargazers:0Issues:1Issues:0

lightning-GPT

Train and run GPTs with Lightning

Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0

mamba-minimal

Simple, minimal implementation of the Mamba SSM in one file of PyTorch.

License:Apache-2.0Stargazers:0Issues:0Issues:0

megatron-smol-cluster

Megatron-LM setup in the smol-cluster

Stargazers:0Issues:0Issues:0

MS-AMP

Microsoft Automatic Mixed Precision Library

Language:PythonLicense:MITStargazers:0Issues:0Issues:0

nanotron

Minimalistic large language model 3D-parallelism training

Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0

OBC

Code for the NeurIPS 2022 paper "Optimal Brain Compression: A Framework for Accurate Post-Training Quantization and Pruning".

Language:PythonStargazers:0Issues:0Issues:0

pipegoose

Large scale 4D parallelism pre-training for 🤗 transformers in Mixture of Experts *(still work in progress)*

Language:PythonLicense:MITStargazers:0Issues:0Issues:0

RWKV-CUDA

The CUDA version of the RWKV language model ( https://github.com/BlinkDL/RWKV-LM )

Language:CudaStargazers:0Issues:0Issues:0

RWKV-LM

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.

Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0

too-many-lists

Learn Rust by writing Entirely Too Many linked lists

License:MITStargazers:0Issues:0Issues:0
Language:PythonLicense:MITStargazers:0Issues:0Issues:0
Language:Jupyter NotebookStargazers:0Issues:2Issues:0

whisper-jax

JAX implementation of OpenAI's Whisper model for up to 70x speed-up on TPU.

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:0Issues:0Issues:0