JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf

A creative writing multi-agent solution to help users write articles.

The most beautiful SMS messenger for Android - Revived

Vision agent

Upload of an abandoned ncurses-based programming environment

Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

Langflow is a low-code app builder for RAG and multi-agent AI applications. It’s Python-based and agnostic to any model, API, or database.

Drag & drop UI to build your customized LLM flow

Code for the paper "What's the Magic Word? A Control Theory of LLM Prompting"

Evaluation and Tracking for LLM Experiments

LlamaIndex is a data framework for your LLM applications

GPT-3: Language Models are Few-Shot Learners

Create-tsi is a generative AI RAG toolkit which generates AI Applications with low code.

The official Meta Llama 3 GitHub site

Risk-First Software Development

Question Answering annotation platform - Plateforme d'annotation

LLM training in simple, raw C/CUDA

A curated list of NLP resources for Hungarian

[EMNLP'23, ACL'24] 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.

DSPy: The framework for programming—not prompting—language models

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

Machine Learning Containers for NVIDIA Jetson and JetPack-L4T

A principled instruction benchmark on formulating effective queries and prompts for large language models (LLMs). Our paper: https://arxiv.org/abs/2312.16171

MTEB: Massive Text Embedding Benchmark

pix2tex: Using a ViT to convert images of equations into LaTeX code.

Mamba SSM architecture