mlfoundations Goto Github PK

advancedml-sp23

au21

clip_quality_not_quantity

datacomp

DataComp: In search of the next generation of multimodal datasets

datacomp_site

dataset2metadata

imagenet-applications-transfer

imagenet-captions

Release of ImageNet-Captions

llm-foundry

LLM training code for MosaicML foundation models

model-soups

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

open-diffusion

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

open_clip

An open source implementation of CLIP.

open_flamingo

An open-source framework for training large multimodal models.

open_lm

A repository for research on medium sized language models.

patching

Patching open-vocabulary models by interpolating weights

qa_robustness

scaling

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

spark-commoncrawl

tableshift

A benchmark for distribution shift in tabular data

task_vectors

Editing Models with Task Arithmetic

visit-bench

webdataset-resharder

Efficiently process webdatasets

wise-ft

Robust fine-tuning of zero-shot models