dargor

sglang

SGLang is a fast serving framework for large language models and vision language models.

ammonia

Repair and secure untrusted HTML

bacon

background rust code check

stats

macOS system monitor in your menu bar

SQL-tips-and-tricks

SQL tips and tricks

GPU-Puzzles

Solve puzzles. Learn CUDA.

void

Time-MoE

Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts

ragbuilder

A toolkit to create optimal Production-ready RAG setup for your data

MisguidedAttention

A collection of prompts to challenge the reasoning abilities of large language models in presence of misguiding information

GenAI_Agents

This repository provides tutorials and implementations for various Generative AI Agent techniques, from basic to advanced. It serves as a comprehensive guide for building intelligent, interactive AI systems.

spark-operator

Kubernetes operator for managing the lifecycle of Apache Spark applications on Kubernetes.

MiniCheck

MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents [EMNLP 2024]

llama-stack

Model components of the Llama Stack APIs

OneChart

[ACM'MM 2024 Oral] Official code for "OneChart: Purify the Chart Structural Extraction via One Auxiliary Token"

GOT-OCR2.0

Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

Yi-Coder

🌟 Yi-Coder is a series of open-source code language models that delivers state-of-the-art coding performance with fewer than 10 billion parameters.

LLaMA-Omni

LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabilities at the GPT-4o level.

dataherald

Interact with your SQL database, Natural Language to SQL using LLMs

rainfrog

🐸 a database management tui for postgres

django-allauth

Integrated set of Django applications addressing authentication, registration, account management as well as 3rd party (social) account authentication.

itext2kg

Incremental Knowledge Graphs Constructor Using Large Language Models

lady-deirdre

Compiler front-end foundation technology.

FluxMusic

Text-to-Music Generation with Rectified Flow Transformers

nviwatch

NviWatch: A blazingly fast rust based TUI for managing and monitoring NVIDIA GPU processes

cookbook

steady-state-stack

Stack of Rust crates for stead state projects

MiniCPM-V

MiniCPM-V 2.6: A GPT-4V Level MLLM for Single Image, Multi Image and Video on Your Phone

pyserde

Yet another serialization library on top of dataclasses, inspired by serde-rs.

mflux

A MLX port of FLUX based on the Huggingface Diffusers implementation.