betoesquivel

Jose Alberto Esquivel 's starred repositories

BrowserGym

BrowserGym, a gym environment for web task automation in the Chromium browser.

Language:PythonNOASSERTION18900

aeon

A toolkit for machine learning from time series

Language:PythonBSD-3-Clause83600

postgresml

The GPU-powered AI application database. Get your app to market faster using the simplicity of SQL and the latest NLP, ML + LLM models.

Language:RustMIT560200

mirage

A multi-level tensor algebra superoptimizer

Language:C++Apache-2.024700

ai-town

A MIT-licensed, deployable starter kit for building and customizing your own version of AI town - a virtual town where AI characters live, chat and socialize.

Language:TypeScriptMIT703500

WhisperKit

Swift native on-device speech recognition with Whisper for Apple Silicon

Language:SwiftMIT253900

seamless_communication

Foundational Models for State-of-the-Art Speech and Text Translation

Language:Jupyter NotebookNOASSERTION1040800

emo-connect-python

Python library for connecting and interacting with an EMO pet

Language:PythonGPL-3.01800

wishful-search

Natural language search for complex JSON arrays, with AI Quickstart.

Language:TypeScriptApache-2.036100

whisperkittools

Python tools for WhisperKit: Model conversion, optimization and evaluation

Language:PythonMIT12700

surya

OCR, layout analysis, reading order, line detection in 90+ languages

Language:PythonGPL-3.0851800

mixtral-offloading

Run Mixtral-8x7B models in Colab or consumer desktops

Language:PythonMIT226100

data-engineer-handbook

This is a repo with links to everything you'd ever want to learn about data engineering

957200

axolotl

Go ahead and axolotl questions

Language:PythonApache-2.0649200

text-generation-webui

A Gradio web UI for Large Language Models. Supports transformers, GPTQ, AWQ, EXL2, llama.cpp (GGUF), Llama models.

Language:PythonAGPL-3.03758000

ComfyUI

The most powerful and modular stable diffusion GUI, api and backend with a graph/nodes interface.

Language:PythonGPL-3.03713800

litgpt

Pretrain, finetune, deploy 20+ LLMs on your own data. Uses state-of-the-art techniques: flash attention, FSDP, 4-bit, LoRA, and more.

Language:PythonApache-2.0760200

FastChat

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

Language:PythonApache-2.03515800

qlora

QLoRA: Efficient Finetuning of Quantized LLMs

Language:Jupyter NotebookMIT960100

private-gpt

Interact with your documents using the power of GPT, 100% privately, no data leaks

Language:PythonApache-2.05256900

MiniGPT-4

Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)

Language:PythonBSD-3-Clause2505400

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:PythonApache-2.01184300