A framework for few-shot evaluation of language models.

FAIR Sequence Modeling Toolkit 2

Large Concept Models: Language modeling in a sentence representation space

🤗 smolagents: a barebones library for agents. Agents write python code to call tools and orchestrate other agents.

[ICLR2025 Spotlight🔥] Official Implementation of TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters

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.

Interpretability for sequence generation models 🐛 🔍

Model interpretability and understanding for PyTorch

GPU Accelerated t-SNE for CUDA with Python bindings

Machine learning metrics for distributed, scalable PyTorch applications.

Explain and train language models that extract information from long medical documents with the Masked Sampling Procedure (MSP)

A collection of ETLs from common data formats to Medical Event Data Standard

A toolkit for evaluating and monitoring AI models in clinical settings

Schema definitions and Python types for Medical Event Data Standard, a standard for medical event data such as EHR and claims data

A massively parallel, high-level programming language

A modern model graph visualizer and debugger

Dataset and modelling infrastructure for modelling "event streams": sequences of continuous time, multivariate events with complex internal dependencies.

interactive visualization of 5 popular gradient descent methods with step-by-step illustration and hyperparameter tuning UI

​TextWorld is a sandbox learning environment for the training and evaluation of reinforcement learning (RL) agents on text-based games.

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

Large Context Attention

Large World Model -- Modeling Text and Video with Millions Context

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

An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

A toolkit for developing and comparing reinforcement learning algorithms.

Building Open-Ended Embodied Agents with Internet-Scale Knowledge

Hackable and optimized Transformers building blocks, supporting a composable construction.

A Deep Learning Python Toolkit for Healthcare Applications.

Python package for machine learning for healthcare using a OMOP common data model