AI & ML interests

JAX, Flax, TPU, 🤗

Recent Activity

flax-community's activity

thomwolf 
posted an update 16 days ago
view post
Post
4324
We are proud to announce HuggingFaceFW/fineweb-2: A sparkling update to HuggingFaceFW/fineweb with 1000s of 🗣️languages.

We applied the same data-driven approach that led to SOTA English performance in🍷 FineWeb to thousands of languages.

🥂 FineWeb2 has 8TB of compressed text data and outperforms other multilingual datasets in our experiments.

The dataset is released under the permissive 📜 ODC-By 1.0 license, and the 💻 code to reproduce it and our evaluations is public.

We will very soon announce a big community project, and are working on a 📝 blogpost walking you through the entire dataset creation process. Stay tuned!

In the mean time come ask us question on our chat place: HuggingFaceFW/discussion

H/t @guipenedo @hynky @lvwerra as well as @vsabolcec Bettina Messmer @negar-foroutan and @mjaggi
  • 2 replies
·
stefan-it 
posted an update 16 days ago
view post
Post
1127
My latest project is the outcome of the last 2+ years working with TPUs from the amazing TPU Research Cloud (TRC) program and training Encoder-only LMs with the TensorFlow Model Garden library.

👉 Link: https://github.com/stefan-it/model-garden-lms

An overview of some features:

- Cheatsheet for setting-up a TPU VM Pod (with all necessary dependencies) to pretrain LMs with TF Model Garden
- Conversion scripts that convert TF Model Garden weights to Hugging Face Transformers-compatible models
- Supported architectures include BERT, BERT with Token Dropping and TEAMS

I also released BERT-based models pretrained on the great Hugging Face FineWeb and FineWeb-Edu datasets (10BT subset). With more to come!

👉 Model Hub Link: https://huggingface.co/model-garden-lms

If you find these resources useful, please give them a like!

Made from Bavarian Oberland with ❤️ and 🥨.
christopher 
posted an update 17 days ago
view post
Post
1562
The folks at Foursquare released a dataset of 104.5 million places of interest ( foursquare/fsq-os-places) and here's all of them on a plot
·
christopher 
posted an update 19 days ago
thomwolf 
posted an update 19 days ago
thomwolf 
posted an update 21 days ago
rwightman 
posted an update 21 days ago
view post
Post
1307
There's a new timm release, v 1.0.12, with a focus on optimizers. The optimizer factory has been refactored, there's now a timm.optim.list_optimizers() and new way to register optimizers and their attributes. As always you can use an timm optimizer like a torch one, just replace torch.optim with timm.optim

New optimizers include:
* AdafactorBigVision - adfactorbv
* ADOPT - adopt / adoptw (decoupled decay)
* MARS - mars
* LaProp - laprop
* Cautious Optimizers - a modification to all of the above, prefix with c as well as cadamw, cnadamw, csgdw, clamb, crmsproptf

I shared some caution comparisons in this model repo: rwightman/timm-optim-caution

For details, references, see the code: https://github.com/huggingface/pytorch-image-models/tree/main/timm/optim

  • 3 replies
·
thomwolf 
posted an update about 1 month ago
rwightman 
posted an update about 1 month ago
view post
Post
1276
I'm currently on a push to expand the scope of image based datasets on the Hub. There's certainly a lot already, but for anyone who's looked closely, there's not a whole lot of standardization. I am to fix that, datasets under the https://huggingface.co/timm and https://huggingface.co/pixparse orgs will serve as canonical examples for various task / modality combinations and be useable without fuss in libraries like timm, OpenCLIP, and hopefully more.

I just uploaded the first multi-label dataset that I'll support with timm scripts soon: timm/plant-pathology-2021

Next up object detection & segmentation! I've got an annotation spec sorted out, a lot of datasets ready to rip, and yeah that means timm support for object detection, eventually segmentation, is finally under development :O
rwightman 
posted an update about 1 month ago
view post
Post
1056
Want to validate some hparams or figure out what timm model to use before commiting to download or training with a large dataset? Try mini-imagenet: timm/mini-imagenet

I had this sitting on my drive and forgot where I pulled it together from. It's 100 classes of imagenet, 50k train and 10k val images (from ImageNet-1k train set), and 5k test images (from ImageNet-1k val set). 7.4GB instead of > 100GB for the full ImageNet-1k. This ver is not reduced resolution like some other 'mini' versions. Super easy to use with timm train/val scripts, checkout the dataset card.

I often check fine-tuning with even smaller datasets like:
* timm/resisc45
* timm/oxford-iiit-pet
But those are a bit small to train any modest size model w/o starting from pretrained weights.
thomwolf 
posted an update about 1 month ago
rwightman 
posted an update about 1 month ago
view post
Post
1579
New MobileNetV4 weights were uploaded a few days ago -- more ImageNet-12k training at 384x384 for the speedy 'Conv Medium' models.

There are 3 weight variants here for those who like to tinker. On my hold-out eval they are ordered as below, not that different, but the Adopt 180 epochs closer to AdamW 250 than to AdamW 180.
* AdamW for 250 epochs - timm/mobilenetv4_conv_medium.e250_r384_in12k
* Adopt for 180 epochs - timm/mobilenetv4_conv_medium.e180_ad_r384_in12k
* AdamW for 180 epochs - timm/mobilenetv4_conv_medium.e180_r384_in12k

This was by request as a user reported impressive results using the 'Conv Large' ImagNet-12k pretrains as object detection backbones. ImageNet-1k fine-tunes are pending, the weights do behave differently with the 180 vs 250 epochs and the Adopt vs AdamW optimizer.

nbroad 
posted an update about 2 months ago
view post
Post
3547
hi florent and livestream!
·
thomwolf 
posted an update 2 months ago
view post
Post
4114
Parents in the 1990: Teach the kids to code
Parents now: Teach the kids to fix the code when it starts walking around 🤖✨
  • 2 replies
·
rwightman 
posted an update 2 months ago
view post
Post
646
A new timm release (1.0.11) is out now. A also wrote an article on one of the included models: https://huggingface.co/blog/rwightman/mambaout

Featured in the release are:
* The MambaOut model, a cheeky arch inspired by SSM but without the SSM part, a ConvNeXt with gating.
* Several timm trained MambaOut variations with arch tweaks and ImageNet-12k pretrain to verify scaling, supplement ported weights.
* The smallest MobileNetV4, a 0.5x width scaled Conv-Small.
* Two impressive MobileNetV3 Large models outperforming all previous, using MNV4 Small recipe.
* 'Zepto,' a new compact ConvNeXt variant even smaller than the previous Atto, 2.2M params, RMSNorm, and solid results for its size.
* Newly ported SigLIP SO400M/16 ViT multi-lingual weights, the largest i18n weights, prevous was B/16.
* Two ImageNet-1k fine-tuned SigLIP SO400M models at 378x378
* InternViT 300M weight port. A really solid ViT encoder distilled from OpenGVLab 6B VL model encoder.
* An assortment of very small, sub 1M param pretrained test models to improve library unit tests and serve low-resource applications.