Eugenio Herrera-Berg (ouhenio)

ouhenio

Geek Repo

Company:Centro Nacional de Inteligencia Artificial

Location:Latent Space

Home Page:ouhen.io

Github PK Tool:Github PK Tool

Eugenio Herrera-Berg's starred repositories

LLMs-from-scratch

Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step

Language:Jupyter NotebookLicense:NOASSERTIONStargazers:25083Issues:278Issues:77

just

πŸ€– Just a command runner

Language:RustLicense:CC0-1.0Stargazers:19448Issues:67Issues:987

unilm

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Language:PythonLicense:MITStargazers:19406Issues:299Issues:1344

uv

An extremely fast Python package and project manager, written in Rust.

Language:RustLicense:Apache-2.0Stargazers:17848Issues:33Issues:2644

ml-engineering

Machine Learning Engineering Open Book

Language:PythonLicense:CC-BY-SA-4.0Stargazers:10522Issues:109Issues:20

txtai

πŸ’‘ All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows

Language:PythonLicense:Apache-2.0Stargazers:8577Issues:85Issues:742

TensorRT-LLM

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

Language:C++License:Apache-2.0Stargazers:8002Issues:87Issues:1739

StableCascade

Official Code for Stable Cascade

Language:Jupyter NotebookLicense:MITStargazers:6501Issues:61Issues:121

CTranslate2

Fast inference engine for Transformer models

Language:C++License:MITStargazers:3162Issues:56Issues:671

Vim

[ICML 2024] Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model

Language:PythonLicense:Apache-2.0Stargazers:2742Issues:30Issues:106

jepa

PyTorch code and models for V-JEPA self-supervised learning from video.

Language:PythonLicense:NOASSERTIONStargazers:2594Issues:37Issues:52

LayerDiffuse

Transparent Image Layer Diffusion using Latent Transparency

RPG-DiffusionMaster

[ICML 2024] Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs (PRG)

Language:Jupyter NotebookLicense:AGPL-3.0Stargazers:1633Issues:26Issues:49

alpaca_eval

An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:1400Issues:7Issues:138

KnowLM

An Open-sourced Knowledgable Large Language Model Framework.

Language:PythonLicense:MITStargazers:1177Issues:10Issues:130

MeZO

[NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333

Language:PythonLicense:MITStargazers:1012Issues:19Issues:35

alpaca_farm

A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.

Language:PythonLicense:Apache-2.0Stargazers:753Issues:8Issues:42

AnglE

Train and Infer Powerful Sentence Embeddings with AnglE | πŸ”₯ SOTA on STS and MTEB Leaderboard

Language:PythonLicense:MITStargazers:434Issues:10Issues:46

KIVI

KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache

Language:PythonLicense:MITStargazers:195Issues:5Issues:22

intrinsic-lora

Official repo of π™„π™£π™©π™§π™žπ™£π™¨π™žπ™˜ π™‡π™€π™π˜Ό: 𝘼 π™‚π™šπ™£π™šπ™§π™–π™‘π™žπ™¨π™© 𝘼π™₯π™₯π™§π™€π™–π™˜π™ 𝙛𝙀𝙧 π˜Ώπ™žπ™¨π™˜π™€π™«π™šπ™§π™žπ™£π™œ π™†π™£π™€π™¬π™‘π™šπ™™π™œπ™š π™žπ™£ π™‚π™šπ™£π™šπ™§π™–π™©π™žπ™«π™š π™ˆπ™€π™™π™šπ™‘π™¨, which is previously titled (𝘎𝘦𝘯𝘦𝘳𝘒𝘡π˜ͺ𝘷𝘦 π˜”π˜°π˜₯𝘦𝘭𝘴: 𝘞𝘩𝘒𝘡 π˜₯𝘰 𝘡𝘩𝘦𝘺 𝘬𝘯𝘰𝘸? π˜‹π˜° 𝘡𝘩𝘦𝘺 𝘬𝘯𝘰𝘸 𝘡𝘩π˜ͺ𝘯𝘨𝘴? π˜“π˜¦π˜΅'𝘴 𝘧π˜ͺ𝘯π˜₯ 𝘰𝘢𝘡!)

Language:PythonLicense:NOASSERTIONStargazers:174Issues:4Issues:7

3d-shapes

This repository contains the 3D shapes dataset, used in Kim, Hyunjik and Mnih, Andriy. "Disentangling by Factorising." In Proceedings of the 35th International Conference on Machine Learning (ICML). 2018. to assess the disentanglement properties of unsupervised learning methods.

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:124Issues:10Issues:1

Parameter-Efficient-MoE

Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks

Language:PythonLicense:Apache-2.0Stargazers:122Issues:4Issues:8

pget

parallel fetch

Language:GoLicense:Apache-2.0Stargazers:102Issues:16Issues:57

slow_disentanglement

Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding

Language:Jupyter NotebookLicense:MITStargazers:70Issues:13Issues:3

disentangling-correlated-factors

A benchmarking suite for disentanglement algorithms, suited for evaluating robustness to correlated factors. Codebase for the paper "Disentanglement of Correlated Factors via Hausdorff Factorized Support" by Karsten Roth, Mark Ibrahim, Zeynep Akata, Pascal Vincent, Diane Bouchacourt.

Language:PythonLicense:MITStargazers:64Issues:5Issues:0

keyframed

Simple, expressive, pythonic datatypes for manipulating curves parameterized by keyframes and interpolators.

improved-diffusion

Text-writing denoising diffusion (and much more)

Language:PythonLicense:MITStargazers:30Issues:1Issues:0
Language:PythonLicense:MITStargazers:7Issues:2Issues:0