SFEvent (Open-Source AI Meetup)

posted an update 2 days ago

Post

740

Community fine-tuned models are more carbon efficient than the models they are derived from! 🥳🌿

@alozowski @clefourrier @SaylorTwift @albertvillanova evaluated CO₂ emissions associated with model inference for over 3000 models on the Open LLM Leaderboard. Interesting trends and new insights emerged...👀

Blog Post: https://huggingface.co/blog/leaderboard-emissions-analysis

Leaderboard: open-llm-leaderboard/open_llm_leaderboard

julien-c

posted an update about 1 month ago

Post

8205

After some heated discussion 🔥, we clarify our intent re. storage limits on the Hub

TL;DR:
- public storage is free, and (unless blatant abuse) unlimited. We do ask that you consider upgrading to PRO and/or Enterprise Hub if possible
- private storage is paid above a significant free tier (1TB if you have a paid account, 100GB otherwise)

docs: https://huggingface.co/docs/hub/storage-limits

We optimize our infrastructure continuously to scale our storage for the coming years of growth in Machine learning, to the benefit of the community 🔥

cc: @reach-vb @pierric @victor and the HF team

28 replies

·

julien-c

posted an update about 1 month ago

Post

2485

wow 😮

INTELLECT-1 is the first collaboratively trained 10 billion parameter language model trained from scratch on 1 trillion tokens of English text and code.

PrimeIntellect/INTELLECT-1-Instruct

BrigitteTousi

posted an update about 2 months ago

Post

998

I'm biased but I think HF Posts is the #1 social platform for the AI community! 🤗 That being said, most of us are already on X and now also joining Bluesky.

Looking for us on Bsky? We started a team list here: https://bsky.app/starter-pack/did:plc:yyfrnpcutxghwc6eac4xplwp/3lbem54cnxp26

DavidVivancos

posted an update 6 months ago

Post

1719

#ICLM 2024 is almost there 🔥🔥🔥 PM if you will be in Vienna next week, Glad to catchup with the Hugging Face community there!

I would like to contribute 🎁 by releasing the sixth Knowledge Vault, with 100 lectures visualized from the last 10 years of ICML from 2014 to 2024, (10 from 2024 will be included after the conference) including knowledge graphs for all the Invited Lectures and some extras, with almost 3000 topics represented using AI.

You can explore it here:
🌏 https://theendofknowledge.com/Vaults/6/ICML-2015-2024.html

And you can learn more about the Vaults here:
📝https://www.linkedin.com/pulse/knowledge-vaults-david-vivancos-lbjef/

And previous Vaults relevant to the #huggingface community are:

🌏 [ @lexfridman 2018-2024 Interviews] https://theendofknowledge.com/Vaults/1/Lex100-2024.html

🌏 [ICLR 2014-2023] https://theendofknowledge.com/Vaults/2/ICLR2014-2023.html

🌏 [AIForGood 2017-2024] https://theendofknowledge.com/Vaults/4/AIForGood2017-2024.html

🌏 [CVPR 2015-2024] https://theendofknowledge.com/Vaults/5/CVPR-2015-2024.html

Hope you like them!

And great to see you all at #icml2024 @clem @thomwolf @julien-c and team

julien-c

posted an update 8 months ago

Post

5183

Hey it was good meeting you yesterday @MaziyarPanahi 🔥

thanks @mishig for setting this up

Let's make the Hub as useful as possible for the community ❤️

1 reply

·

pcuenq

posted an update 9 months ago

Post

4780

OpenELM in Core ML

Apple recently released a set of efficient LLMs in sizes varying between 270M and 3B parameters. Their quality, according to benchmarks, is similar to OLMo models of comparable size, but they required half the pre-training tokens because they use layer-wise scaling, where the number of attention heads increases in deeper layers.

I converted these models to Core ML, for use on Apple Silicon, using this script: https://gist.github.com/pcuenca/23cd08443460bc90854e2a6f0f575084. The converted models were uploaded to this community in the Hub for anyone that wants to integrate inside their apps: corenet-community/openelm-core-ml-6630c6b19268a5d878cfd194

The conversion was done with the following parameters:
- Precision: float32.
- Sequence length: fixed to 128.

With swift-transformers (https://github.com/huggingface/swift-transformers), I'm getting about 56 tok/s with the 270M on my M1 Max, and 6.5 with the largest 3B model. These speeds could be improved by converting to float16. However, there's some precision loss somewhere and generation doesn't work in float16 mode yet. I'm looking into this and will keep you posted! Or take a look at this issue if you'd like to help: https://github.com/huggingface/swift-transformers/issues/95

I'm also looking at optimizing inference using an experimental kv cache in swift-transformers. It's a bit tricky because the layers have varying number of attention heads, but I'm curious to see how much this feature can accelerate performance in this model family :)

Regarding the instruct fine-tuned models, I don't know the chat template that was used. The models use the Llama 2 tokenizer, but the Llama 2 chat template, or the default Alignment Handbook one that was used to train, are not recognized. Any ideas on this welcome!

4 replies

·

DavidVivancos

posted an update 9 months ago

Post

1972

#ICLR 2024 is almost there 🔥🔥🔥 counting the days to be again in the beautiful city of Vienna participating in the The Twelfth International Conference on Learning Representations, hope to see many of the Hugging Face comunity there!

I would like to contribute 🎁 by releasing the second Knowledge Vault, with 100 lectures visualized from the last 10 years of ICLR from 2014 to 2023, including knowledge graphs for all the Invited Lectures and some extras, with almost 3000 topics represented. (Of course using several AI tools including Llama3)

You can explore it here:
🌏 https://theendofknowledge.com/Vaults/2/ICLR2014-2023.html

And you can learn more about the Vaults here:
📝https://www.linkedin.com/pulse/knowledge-vaults-david-vivancos-lbjef/

Hope you like the Knowledge Vault!

julien-c

posted an update 9 months ago

Post

6882

text-generation-inference (TGI) is now fully open-source again!

Along with text-embeddings-inference.

We just switched both of those repos' license back to Apache 2. 🔥

julien-c

posted an update 10 months ago

Post

3171

Very glad to welcome @josefprusa , pioneer of 3D printing and open source hardware, founder of https://www.prusa3d.com/, to the HF Hub 👋

AI applied to 3D printing could be big.

1 reply

·

julien-c

posted an update 10 months ago

Post

671 authors 🤯

Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context (2403.05530) Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

2 replies

·

julien-c

posted an update 10 months ago

Post

What if you could casually access your remote GPU in HF Spaces from the comfort of your local VSCode 🤯

8 replies

·

DavidVivancos

posted an update 11 months ago

Post

Are you up to a 🤗 challenge 🏆 ?
if so 👀 Check out the new MindBigData Leaderboard 🔥🔥🔥
🚀 DavidVivancos/MindBigData-Leaderboard

Decode the "source" 🧠 with the largest multimodal opendata of brain signals for Machine Learning.

Try to beat the whopping 🥇98,97% accuracy of Smita Tiwari Shivani Goel School of CSET Bennett University, India and Arpit Bhardwaj BML Munjal University decoding the multiclass Yann LeCun mnist of brain digits caputured with EMOTIV Epoc and 🥇89,62% with Insight

Or the 🥇96,18% of Dr. Nrushingh Charan Mahapatra Intel Corporation and Prof.(Dr). Prachet Bhuyan Kalinga Institute of Industrial Technology, Bhubaneswar also with the mnist of brain digits but captured with Muse® by Interaxon Inc.

Or the 🥇85% of Matthew Zhang Westlake High School and Jeremy Lu now at Purdue University decoding brain images captured from imagenet

Or be the first to break the 🧊 with the largest open dataset 2023 (8+ billion datapoints), the multimodal MindBigData2023_MNIST-8B captured with a custom 128 channels EEG that I built and with the real 70,000 MNIST digits and put your NVIDIA gpus to work.

All the datasets are open and ready at HuggingFace, dare to try?

Hope to see you all soon in the LeaderBoard

Thanks
@DavidVivancos

2 replies

·

julien-c

posted an update 12 months ago

Post

📣 NEW on HF

the Dataset Viewer is now available on *private datasets* too

You need to be a PRO or a Enterprise Hub user. 🔥

Great work from our Datasets team 🥰: @lhoestq @severo @polinaeterna @asoria @albertvillanova and the whole team 🥰