Hugging Face's logo
Gordon's picture
9 3 34

Gordon

GordonM
hlydecker's profile picture ntse-usyd's profile picture
Β·
https://gordonmcd.com

AI & ML interests

Data Science for good

Recent Activity

reacted to MoritzLaurer's post with πŸ‘ about 1 month ago
Quite excited by the ModernBERT release! 0.15/0.4B small, 2T modern pre-training data and tokenizer with code, 8k context window, great efficient model for embeddings & classification! This will probably be the basis for many future SOTA encoders! And I can finally stop using DeBERTav3 from 2021 :D Congrats @answerdotai, @LightOnIO and collaborators like @tomaarsen ! Paper and models here πŸ‘‡https://huggingface.co/collections/answerdotai/modernbert-67627ad707a4acbf33c41deb
reacted to MoritzLaurer's post with πŸ”₯ about 1 month ago
πŸš€ Releasing a new zeroshot-classifier based on ModernBERT! Some key takeaways: - ⚑ Speed & efficiency: It's multiple times faster and uses significantly less memory than DeBERTav3. You can use larger batch sizes and enabling bf16 (instead of fp16) gave me a ~2x speed boost as well - πŸ“‰ Performance tradeoff: It performs slightly worse than DeBERTav3 on average across my zeroshot classification task collection - 🧠 Use cases: I recommend using it for scenarios requiring speed and a larger context window (8k). - πŸ’‘ What’s next? I’m preparing a newer version trained on better + longer synthetic data to fully leverage the 8k context window and improve upon the training mix of my older zeroshot-v2.0 models. I also hope that there will be a multilingual variant in the future. Great work by https://huggingface.co/answerdotai ! If you’re looking for a high-speed zeroshot classifier, give it a try! πŸ“„ Resources below: πŸ‘‡ Base model: https://huggingface.co/MoritzLaurer/ModernBERT-base-zeroshot-v2.0 Large model: https://huggingface.co/MoritzLaurer/ModernBERT-large-zeroshot-v2.0 Updated zeroshot collection: https://huggingface.co/collections/MoritzLaurer/zeroshot-classifiers-6548b4ff407bb19ff5c3ad6f ModernBERT collection with paper: https://huggingface.co/collections/answerdotai/modernbert-67627ad707a4acbf33c41deb
liked a model 2 months ago
Varosa/SeamlessExpressive
View all activity

Organizations

Sydney Informatics Hub's profile picture marsupial.ai's profile picture The University of Sydney's profile picture

GordonM's activity

reacted to MoritzLaurer's post with πŸ‘ about 1 month ago
view post
Post
2631
Quite excited by the ModernBERT release! 0.15/0.4B small, 2T modern pre-training data and tokenizer with code, 8k context window, great efficient model for embeddings & classification!

This will probably be the basis for many future SOTA encoders! And I can finally stop using DeBERTav3 from 2021 :D

Congrats @answerdotai , @LightOnIO and collaborators like @tomaarsen !

Paper and models here πŸ‘‡https://huggingface.co/collections/answerdotai/modernbert-67627ad707a4acbf33c41deb
Β·
reacted to MoritzLaurer's post with πŸ”₯ about 1 month ago
view post
Post
2258
πŸš€ Releasing a new zeroshot-classifier based on ModernBERT! Some key takeaways:

- ⚑ Speed & efficiency: It's multiple times faster and uses significantly less memory than DeBERTav3. You can use larger batch sizes and enabling bf16 (instead of fp16) gave me a ~2x speed boost as well
- πŸ“‰ Performance tradeoff: It performs slightly worse than DeBERTav3 on average across my zeroshot classification task collection
- 🧠 Use cases: I recommend using it for scenarios requiring speed and a larger context window (8k).
- πŸ’‘ What’s next? I’m preparing a newer version trained on better + longer synthetic data to fully leverage the 8k context window and improve upon the training mix of my older zeroshot-v2.0 models. I also hope that there will be a multilingual variant in the future.

Great work by answerdotai !

If you’re looking for a high-speed zeroshot classifier, give it a try!

πŸ“„ Resources below: πŸ‘‡
Base model: MoritzLaurer/ModernBERT-base-zeroshot-v2.0
Large model: MoritzLaurer/ModernBERT-large-zeroshot-v2.0
Updated zeroshot collection: MoritzLaurer/zeroshot-classifiers-6548b4ff407bb19ff5c3ad6f
ModernBERT collection with paper: answerdotai/modernbert-67627ad707a4acbf33c41deb
liked a model 2 months ago
liked a Space 2 months ago
upvoted a collection 7 months ago
updated a Space 8 months ago
liked 2 Spaces 9 months ago
reacted to Xenova's post with β€οΈπŸ˜ŽπŸš€ 10 months ago
view post
Post
15144
I'm excited to announce that Transformers.js V3 is finally available on NPM! πŸ”₯ State-of-the-art Machine Learning for the web, now with WebGPU support! 🀯⚑️

Install it from NPM with:
πš—πš™πš– πš’ @πš‘πšžπšπšπš’πš—πšπšπšŠπšŒπšŽ/πšπš›πšŠπš—πšœπšπš˜πš›πš–πšŽπš›πšœ

or via CDN, for example: https://v2.scrimba.com/s0lmm0qh1q

Segment Anything demo: webml-community/segment-anything-webgpu
Β·
liked a model 10 months ago
reacted to Xenova's post with πŸš€ 10 months ago
view post
Post
14072
I can't believe this... Phi-3.5-mini (3.8B) running in-browser at ~90 tokens/second on WebGPU w/ Transformers.js and ONNX Runtime Web! 🀯 Since everything runs 100% locally, no messages are sent to a server β€” a huge win for privacy!
- πŸ€— Demo: webml-community/phi-3.5-webgpu
- πŸ§‘β€πŸ’» Source code: https://github.com/huggingface/transformers.js-examples/tree/main/phi-3.5-webgpu
Β·
upvoted a collection 10 months ago
reacted to Xenova's post with πŸ”₯ 10 months ago
view post
Post
15144
I'm excited to announce that Transformers.js V3 is finally available on NPM! πŸ”₯ State-of-the-art Machine Learning for the web, now with WebGPU support! 🀯⚑️

Install it from NPM with:
πš—πš™πš– πš’ @πš‘πšžπšπšπš’πš—πšπšπšŠπšŒπšŽ/πšπš›πšŠπš—πšœπšπš˜πš›πš–πšŽπš›πšœ

or via CDN, for example: https://v2.scrimba.com/s0lmm0qh1q

Segment Anything demo: webml-community/segment-anything-webgpu
Β·
liked a model 11 months ago
liked a Space 11 months ago
reacted to Xenova's post with β€οΈπŸ§ πŸ‘€ 11 months ago
view post
Post
6901
Introducing Whisper Timestamped: Multilingual speech recognition with word-level timestamps, running 100% locally in your browser thanks to πŸ€— Transformers.js! Check it out!
πŸ‘‰ Xenova/whisper-word-level-timestamps πŸ‘ˆ

This unlocks a world of possibilities for in-browser video editing! 🀯 What will you build? 😍

Source code: https://github.com/xenova/transformers.js/tree/v3/examples/whisper-word-timestamps
  • 1 reply
Β·