Bruno Cabral (bratao)

bratao

Geek Repo

Company:Escavador

Github PK Tool:Github PK Tool


Organizations
FORMAS

Bruno Cabral's starred repositories

llm.c

LLM training in simple, raw C/CUDA

Language:CudaLicense:MITStargazers:20326Issues:204Issues:109

phidata

Build AI Assistants with memory, knowledge and tools.

Language:PythonLicense:MPL-2.0Stargazers:9725Issues:75Issues:121

instructor

structured outputs for llms

Language:PythonLicense:MITStargazers:5967Issues:47Issues:213

klogg

Really fast log explorer based on glogg project

Language:C++License:GPL-3.0Stargazers:2054Issues:35Issues:577

schedule_free

Schedule-Free Optimization in PyTorch

Language:PythonLicense:Apache-2.0Stargazers:1399Issues:14Issues:17

R2R

Build and deploy a fully-featured, observable user-facing RAG backend in minutes.

Language:HTMLLicense:MITStargazers:1283Issues:10Issues:35

hypercorn

Hypercorn is an ASGI and WSGI Server based on Hyper libraries and inspired by Gunicorn.

Language:PythonLicense:MITStargazers:1028Issues:16Issues:180

llm-datasets

High-quality datasets, tools, and concepts for LLM fine-tuning.

ludic

🌳 Web Development in Pure Python with Type-Guided Components.

Language:PythonLicense:MITStargazers:582Issues:5Issues:10

wikitextparser

A Python library to parse MediaWiki WikiText

Language:PythonLicense:GPL-3.0Stargazers:271Issues:9Issues:116

qserve

QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving

Language:PythonLicense:Apache-2.0Stargazers:269Issues:6Issues:15

MoRA

MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning

PyxLSTM

PyxLSTM is a Python library that provides an efficient and extensible implementation of the Extended Long Short-Term Memory (xLSTM) architecture. xLSTM enhances the traditional LSTM by introducing exponential gating, memory mixing, and a matrix memory structure, enabling improved performance and scalability for sequence modeling tasks.

Language:PythonLicense:MITStargazers:163Issues:3Issues:5

zfs-hetzner-vm

script to install Debian 10, 11, 12 and Ubuntu 18, 20, 22 LTS with ZFS root on Hetzner VPS

Language:PythonLicense:Apache-2.0Stargazers:156Issues:4Issues:6

BitMat

An efficent implementation of the method proposed in "The Era of 1-bit LLMs"

Language:PythonLicense:Apache-2.0Stargazers:141Issues:0Issues:0

fp6_llm

An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).

Language:CudaLicense:Apache-2.0Stargazers:136Issues:4Issues:7

linearboost-classifier

LinearBoost Classifier is a rapid and accurate classification algorithm that builds upon a very fast, linear classifier.

Language:PythonLicense:MITStargazers:100Issues:4Issues:2

auto-round

SOTA Weight-only Quantization Algorithm for LLMs. This is official implementation of "Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs"

Language:PythonLicense:Apache-2.0Stargazers:86Issues:9Issues:20

improved-t5

Experiments for efforts to train a new and improved t5

sailcraft

Data Toolkit for Sailor Language Models

Language:PythonStargazers:65Issues:5Issues:0
Language:PythonLicense:Apache-2.0Stargazers:59Issues:2Issues:3
Language:CLicense:Apache-2.0Stargazers:51Issues:0Issues:0

flashT5

A fast implementation of T5/UL2 in PyTorch using Flash Attention

Language:PythonLicense:Apache-2.0Stargazers:46Issues:0Issues:0

free-threaded-compatibility

A central repository to keep track of the status of work on and support for free-threaded CPython (see PEP 703), with a focus on the scientific and ML/AI ecosystem

License:MITStargazers:22Issues:0Issues:0

AutoMonkey

Python Automation using Mouse and Keyboard, for the masses

Language:PythonLicense:NOASSERTIONStargazers:16Issues:5Issues:2
Language:PythonLicense:MITStargazers:11Issues:2Issues:3

awesome-nlpbr

Curadoria dos melhores links compartilhados no grupo https://t.me/nlpbr no Telegram.

License:MITStargazers:10Issues:4Issues:0

rpapy

RPAPY is a open source easy tool for automating boring stuffs on any screen with robotframework, pyautogui, pywinauto and others.

Language:PythonLicense:MITStargazers:5Issues:2Issues:0

xlstm-models

xLSTM Language Models

Stargazers:3Issues:0Issues:0