Mrw33554432

accelerate

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

Adam-mini

Code for Adam-mini: Use Fewer Learning Rates To Gain More https://arxiv.org/abs/2406.16793

alignment-handbook

Robust recipes to align language models with human and AI preferences

AudioTokenizer

A quick demo to our latest research result.

Bitlinear4HF

A custom implementation of BitLinear. You can change a HF model to BitLinear in few lines of code.

BitNet

Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch

EZProxyWorkers

A Proxy for OpenAI API

LlamaImage

Try to fine-tune a llama model to output 32x32 color grid (Image)

SelfReflectionGPT

TTS_personal_alt

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

Mrw33554432/Bitlinear4HF

A custom implementation of BitLinear. You can change a HF model to BitLinear in few lines of code.

Mrw33554432/SelfReflectionGPT

Mrw33554432/EZProxyWorkers

A Proxy for OpenAI API

Mrw33554432/TTS_personal_alt

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

Mrw33554432/accelerate

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

Mrw33554432/Adam-mini

Code for Adam-mini: Use Fewer Learning Rates To Gain More https://arxiv.org/abs/2406.16793

Mrw33554432/alignment-handbook

Robust recipes to align language models with human and AI preferences

Mrw33554432/AudioTokenizer

A quick demo to our latest research result.

Mrw33554432/BitNet

Implementation of "BitNet: Scaling 1-bit Transformers for Large Language Models" in pytorch

Mrw33554432/LlamaImage

Try to fine-tune a llama model to output 32x32 color grid (Image)

Mrw33554432/Medusa

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

Mrw33554432/py7zr

7zip in python3 with ZStandard, PPMd, LZMA2, LZMA1, Delta, BCJ, BZip2, and Deflate compressions, and AES encryption.

Mrw33554432/Spacetitanic

This is a simple project for the space titanic challenge on Kaggle. Course Assignment

Mrw33554432/textrank4ch

基于Textrank的关键字提取 & 摘要提取

Mrw33554432/Trans4Init

Exploring the replacement of traditional Transformer math components with neural networks.

Mrw33554432/transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.