lxuechen

grok-1

Grok open release

jina

☁️ Build multimodal AI applications with cloud-native stack

SWE-agent

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-bench evaluation set and takes just 1 minute to run.

rustup

The Rust toolchain installer

gemma.cpp

lightweight, standalone C++ inference engine for Google's Gemma models.

rerun

Visualize streams of multimodal data. Fast, easy to use, and simple to integrate. Built in Rust using egui.

LLocalSearch

LLocalSearch is a completely locally running search aggregator using LLM Agents. The user can ask a question and the system will use a chain of LLMs to find the answer. The user can see the progress of the agents and the final answer. No OpenAI or Google API keys are needed.

zsh-autocomplete

🤖 Real-time type-ahead completion for Zsh. Asynchronous find-as-you-type autocompletion.

fswatch

A cross-platform file change monitor with multiple backends: Apple OS X File System Events, *BSD kqueue, Solaris/Illumos File Events Notification, Linux inotify, Microsoft Windows and a stat()-based backend.

llm-answer-engine

Build a Perplexity-Inspired Answer Engine Using Next.js, Groq, Llama-3, Langchain, OpenAI, Upstash, Brave & Serper

LLMLingua

To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.

external-secrets

External Secrets Operator reads information from a third-party service like AWS Secrets Manager and automatically injects the values as Kubernetes Secrets.

cuml

cuML - RAPIDS Machine Learning Library

h2o-llmstudio

H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://h2oai.github.io/h2o-llmstudio/

text-embeddings-inference

A blazing fast inference solution for text embeddings models

golink

A private shortlink service for tailnets

nomic

Interact, analyze and structure massive text, image, embedding, audio and video datasets

distilabel

⚗️ distilabel is a framework for synthetic data and AI feedback for AI engineers that require high-quality outputs, full data ownership, and overall efficiency.

Xwin-LM

Xwin-LM: Powerful, Stable, and Reproducible LLM Alignment

tunnelmole-client

Tunnelmole - Connect to local servers from anywhere

yet-another-applied-llm-benchmark

A benchmark to evaluate language models on questions I've previously asked them to solve.

filelock

A platform-independent file lock for Python.

attorch

A subset of PyTorch's neural network modules, written in Python using OpenAI's Triton.

rank-amateur-cowsay

Fork me if you want to maintain cowsay.

arena-hard-auto

Arena-Hard-Auto: An automatic LLM benchmark.

Data-Provenance-Collection

aiorwlock

Read/Write Lock - synchronization primitive for asyncio

lorax

LoRA for arbitrary JAX models and functions

WildBench

Benchmarking LLMs with Challenging Tasks from Real Users

exaggerated-safety

Röttger et al. (2023): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"