Agno is a lightweight framework for building multi-modal Agents

Official repository for our work on micro-budget training of large-scale diffusion models.

💡 All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows

Tensors, for human consumption

Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.

PyTorch native post-training library

$100K or 100 Days: Trade-offs when Pre-Training with Academic Resources

Movie Gen Bench - two media generation evaluation benchmarks released with Meta Movie Gen

Train high-quality text-to-image diffusion models in a data & compute efficient manner

MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering

Megatron's multi-modal data loader

Replicating O1 inference-time scaling laws

Adversarial Attacks on GPT-4 via Simple Random Search [Dec 2023]

TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients.

Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]

High accuracy RAG for answering questions from scientific documents with citations

Robust recipes to align language models with human and AI preferences

Recipes to train reward model for RLHF.

A minimal PyTorch implementation of probabilistic diffusion models for 2D datasets.

Lecture materials for Cornell CS5785 Applied Machine Learning (Fall 2024)

A (somewhat) minimal library for finetuning language models with PPO on human feedback.

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

Non-parametric Entropy Estimation Toolbox

Kolors Team

A Survey on Text-to-Video Generation/Synthesis.

Official inference repo for FLUX.1 models