🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

The agent engineering platform

A natural language interface for computers

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

⚡ A Fast, Extensible Progress Bar for Python and CLI

The official Meta Llama 3 GitHub site

Mamba SSM architecture

[ICLR'24 spotlight] An open platform for training, serving, and evaluating large language model for tool learning.

Robust recipes to align language models with human and AI preferences

The implementation of DeBERTa

A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.

[ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling

Personal AI, On Personal Devices

AI-Powered Data Processing: Use LOTUS to process all of your datasets with LLMs and embeddings. Enjoy up to 1000x speedups with fast, accurate query processing, that's as simple as writing Pandas code

FacTool: Factuality Detection in Generative AI

TAG-Bench: A benchmark for table-augmented generation (TAG)

[ICML 2024] SqueezeLLM: Dense-and-Sparse Quantization

[EMNLP 2024 Demo] TinyAgent: Function Calling at the Edge!

[NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization

Code and data for "Lost in the Middle: How Language Models Use Long Contexts"

[EMNLP 2023] Adapting Language Models to Compress Long Contexts

build and benchmark deep research

The official repo for "LLoCo: Learning Long Contexts Offline"

[EMNLP 2024 Main] Virtual Personas for Language Models via an Anthology of Backstories

Efficient and Scalable Estimation of Tool Representations in Vector Space

Tinker ↔ KernelBench Integration enabling RL for GPU Kernel Generation