mlfoundations

All

29 repositories

evalchemy
Public
Automatic Evals for Instruction-Tuned Models
HTML
•2•67•2•1•Updated Nov 22, 2024Nov 22, 2024
open_lm
Public
A repository for research on medium sized language models.
Python
•
MIT License
•69•480•33•36•Updated Nov 20, 2024Nov 20, 2024
dclm
Public
DataComp for Language Models
HTML
•
MIT License
•107•1.2k•10•4•Updated Nov 18, 2024Nov 18, 2024
open_clip
Public
An open source implementation of CLIP.
computer-vision pretrained-models language-model contrastive-loss multi-modal-learning zero-shot-classification deep-learning pytorch
Python
•
Other
•986•10k•61•34•Updated Nov 12, 2024Nov 12, 2024
MixEval
Public
The official evaluation suite and dynamic data release for MixEval.
Python
•35•0•0•0•Updated Sep 20, 2024Sep 20, 2024
datacomp_site
Public
HTML
•2•6•0•0•Updated Sep 19, 2024Sep 19, 2024
open_flamingo
Public
An open-source framework for training large multimodal models.
computer-vision language-model flamingo multimodal-learning in-context-learning deep-learning pytorch
Python
•
MIT License
•285•3.8k•44•5•Updated Aug 31, 2024Aug 31, 2024
tabliblib
Public
A Python library for processing and filtering TabLib
Python
•
MIT License
•0•7•0•0•Updated Aug 24, 2024Aug 24, 2024
rtfm
Public
Research on Tabular Foundation Models
Python
•
MIT License
•7•27•10•0•Updated Aug 22, 2024Aug 22, 2024
MINT-1T
Public
MINT-1T: A one trillion token multimodal interleaved dataset.
20•775•1•0•Updated Jul 31, 2024Jul 31, 2024
model-soups
Public
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
Python
•
MIT License
•39•429•8•0•Updated Jul 15, 2024Jul 15, 2024
tableshift
Public
A benchmark for distribution shift in tabular data
Python
•
MIT License
•7•44•9•1•Updated Jun 6, 2024Jun 6, 2024
scaling
Public
Language models scale reliably with over-training and on downstream tasks
Jupyter Notebook
•
MIT License
•6•94•2•0•Updated Apr 2, 2024Apr 2, 2024
dataset2metadata
Public
Python
•
MIT License
•7•21•0•0•Updated Mar 21, 2024Mar 21, 2024
task_vectors
Public
Editing Models with Task Arithmetic
Python
•36•430•7•0•Updated Jan 11, 2024Jan 11, 2024
datacomp
Public
DataComp: In search of the next generation of multimodal datasets
Python
•
Other
•55•659•24•3•Updated Jan 2, 2024Jan 2, 2024
VisIT-Bench
Public
Python
•2•45•0•0•Updated Oct 29, 2023Oct 29, 2023
patching
Public
Patching open-vocabulary models by interpolating weights
Python
•
MIT License
•8•90•0•0•Updated Sep 28, 2023Sep 28, 2023
imagenet-applications-transfer
Public
Python
•2•2•0•0•Updated Aug 22, 2023Aug 22, 2023
llm-foundry
Public
LLM training code for MosaicML foundation models
Python
•
Apache License 2.0
•530•1•0•0•Updated Aug 10, 2023Aug 10, 2023
advancedml-sp23
Public
CSS
•
MIT License
•0•1•0•0•Updated Jun 2, 2023Jun 2, 2023
open-diffusion
Public
Simple large-scale training of stable diffusion with multi-node support.
Python
•9•126•2•0•Updated May 8, 2023May 8, 2023
webdataset-resharder
Public
Efficiently process webdatasets
webdataset webdataset-format
Python
•0•4•1•0•Updated Apr 5, 2023Apr 5, 2023
imagenet-captions
Public
Release of ImageNet-Captions
MIT License
•4•45•0•0•Updated Jan 20, 2023Jan 20, 2023
qa_robustness
Public
0•0•0•0•Updated Jan 17, 2023Jan 17, 2023
spark-commoncrawl
Public
Jupyter Notebook
•
MIT License
•3•6•1•0•Updated Nov 3, 2022Nov 3, 2022
clip_quality_not_quantity
Public
Python
•1•29•0•0•Updated Oct 18, 2022Oct 18, 2022
wise-ft
Public
Robust fine-tuning of zero-shot models
Python
•
Other
•67•649•7•0•Updated Apr 29, 2022Apr 29, 2022
au21
Public
Jupyter Notebook
•
MIT License
•0•1•0•0•Updated Nov 8, 2021Nov 8, 2021