mlfoundations ORG

An open source implementation of CLIP.

An open-source toolkit for training and running CLIP models that understand both images and text, enabling image search by description, zero-shot image classification, and vision-language AI applications.

An open-source framework for training large multimodal models.

DataComp for Language Models

🍃 MINT-1T: A one trillion token multimodal interleaved dataset.

DataComp: In search of the next generation of multimodal datasets

Robust fine-tuning of zero-shot models

Automatic evals for LLMs

Editing Models with Task Arithmetic

A repository for research on medium sized language models.

Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Simple large-scale training of stable diffusion with multi-node support.

Language models scale reliably with over-training and on downstream tasks

Patching open-vocabulary models by interpolating weights

Research on Tabular Foundation Models

A benchmark for distribution shift in tabular data

No description.

Release of ImageNet-Captions

🍨 Gelato — From Data Curation to Reinforcement Learning: Building a Strong Grounding Model for Computer-Use Agents

No description.

No description.

A Python library for processing and filtering TabLib

No description.

No description.

No description.

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Efficiently process webdatasets

No description.

A high-throughput and memory-efficient inference and serving engine for LLMs

No description.

SkyRL: A Modular Full-stack RL Library for LLMs

LLM training code for MosaicML foundation models

No description.

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

The official evaluation suite and dynamic data release for MixEval.

No description.