Joe El Khoury's repositories
auto-code-rover
A project structure aware autonomous software engineer aiming for autonomous program improvement. Resolved 15.95% tasks in full SWE-bench
PLTranslationEmpirical
Artifact repository for the paper "Lost in Translation: A Study of Bugs Introduced by Large Language Models while Translating Code", In Proceedings of The 46th IEEE/ACM International Conference on Software Engineering (ICSE 2024), Lisbon, Portugal, April 2024
codeditor
Multilingual Code Co-Evolution Using Large Language Models
neural-speed
An innovative library for efficient LLM inference via low-bit quantization
FSE-24-UniTrans
Source Code for "Exploring and Unleashing the Power of Large Language Models in Automated Code Translation"
SWE-agent
SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.29% of bugs in the SWE-bench evaluation set and takes just 1.5 minutes to run.
llm.c
LLM training in simple, raw C/CUDA
max
A collection of sample programs, notebooks, and tools which highlight the power of the MAX platform
jepa
PyTorch code and models for V-JEPA self-supervised learning from video.
private-gpt
Interact with your documents using the power of GPT, 100% privately, no data leaks
containers
🐳 | Dockerfiles for the RunPod container images used for our official templates.
Adan
Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models
FlagEmbedding
Retrieval and Retrieval-augmented LLMs
opro
official code for "Large Language Models as Optimizers"
quiet-star
Code for Quiet-STaR
simba
Simba
search_with_lepton
Building a quick conversation-based search demo with Lepton AI.
grok-1
Grok open release
CodeGen
Reference implementation of code generation projects from Facebook AI Research. General toolkit to apply machine learning to code, from dataset creation to model training and evaluation. Comes with pretrained models.
Time-LLM
[ICLR 2024] Official implementation of " 🦙 Time-LLM: Time Series Forecasting by Reprogramming Large Language Models"
Verba
Retrieval Augmented Generation (RAG) chatbot powered by Weaviate
mindspore
MindSpore is a new open source deep learning training/inference framework that could be used for mobile, edge and cloud scenarios.
puter
The Internet OS!
screenshot-to-code
Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue)
modelscope
ModelScope: bring the notion of Model-as-a-Service to life.
rebuff
LLM Prompt Injection Detector
guardrails
Adding guardrails to large language models.