8 13 42

Simone Tedeschi

sted97

https://scholar.google.com/citations?user=wXvkdigAAAAJ&hl=it&oi=ao

AI & ML interests

Multilingual Named Entity Recognition and Entity Linking.

Recent Activity

authored a paper about 2 months ago

What's the Meaning of Superhuman Performance in Today's NLU?

authored a paper about 2 months ago

Truth or Mirage? Towards End-to-End Factuality Evaluation with LLM-OASIS

authored a paper about 2 months ago

LLMs Lost in Translation: M-ALERT uncovers Cross-Linguistic Safety Gaps

View all activity

Organizations

sted97's activity

reacted to as-cle-bert's post with 🚀 7 months ago

Post

1077

Responsibly building AI also means knowing its impact on the environment and the hidden carbon costs associated with it🌱
If you're interested in the subject, you can check out my latest community article: https://huggingface.co/blog/as-cle-bert/is-ai-carbon-footprint-worrisome
Where I try to unravel AI's carbon footprint and potential solutions to reduce it🌻
Enjoy!🤗

reacted to not-lain's post with ❤️ 7 months ago

Post

2684

I have finished writing a blogpost about building an image-based retrieval system, This is one of the first-ever approaches to building such a pipeline using only open-source models/libraries 🤗

You can checkout the blogpost in https://huggingface.co/blog/not-lain/image-retriever and the associated space at not-lain/image-retriever .

✨ If you want to request another blog post consider letting me know down below or you can reach out to me through any of my social media

📖 Happy reading !

reacted to clem's post with 🚀❤️ 7 months ago

Post

5785

5,000 new repos (models, datasets, spaces) are created EVERY DAY on HF now. The community is amazing!

reacted to alex-abb's post with 🔥 8 months ago

Post

4834

Hi everyone!
I'm Alex, I'm 16, I've been an internship at Hugging Face for a little over a week and I've already learned a lot about using and prompting LLM models. With @victor as tutor I've just finished a space that analyzes your feelings by prompting an LLM chat model. The aim is to extend it so that it can categorize hugging face posts.

alex-abb/LLM_Feeling_Analyzer

4 replies

reacted to Xenova's post with 🔥 8 months ago

Post

6060

Florence-2, the new vision foundation model by Microsoft, can now run 100% locally in your browser on WebGPU, thanks to Transformers.js! 🤗🤯

It supports tasks like image captioning, optical character recognition, object detection, and many more! 😍 WOW!
- Demo: Xenova/florence2-webgpu
- Models: https://huggingface.co/models?library=transformers.js&other=florence2
- Source code: https://github.com/xenova/transformers.js/tree/v3/examples/florence2-webgpu

reacted to yushun0410's post with 🚀 8 months ago

Post

4628

Hi Huggingfacers!

Thrilled to introduce Adam-mini, an optimizer that achieves on-par or better performance than AdamW with 45% to 50% less memory footprint. Adam-mini can also achieve 49.5% higher throughput than AdamW on Llama2-7B pre-training.

The design of Adam-mini is inspired by certain Hessian structures we observed on Transformers.

Feel free to try it out! Try switching to Adam-mini with the same hyperparams of AdamW, it would work with only half memory. Hope Adam-mini can help save time, cost, and energy in your tasks!

Paper: "Adam-mini: Use Fewer Learning Rates To Gain More" https://arxiv.org/abs/2406.16793

Code: https://github.com/zyushun/Adam-mini

1 reply

posted an update 8 months ago

Post

471

📢 Interested in #LLM safety?

We have just uploaded a new version of ALERT 🚨 on ArXiv with novel insights into the weaknesses and vulnerabilities of LLMs! 👀 https://arxiv.org/abs/2404.08676

For a summary of the paper, read this blog post: https://huggingface.co/blog/sted97/alert 🤗

posted an update 10 months ago

Post

2459

📣 I'm thrilled to announce "ALERT: A Comprehensive #Benchmark for Assessing #LLMs’ Safety through #RedTeaming" 🚨

📄 Paper: https://arxiv.org/pdf/2404.08676.pdf
🗃️ Repo: https://github.com/Babelscape/ALERT
🤗 ALERT benchmark: Babelscape/ALERT
🤗 ALERT DPO data: Babelscape/ALERT_DPO

As a key design principle for ALERT, we developed a fine-grained safety risk taxonomy (Fig. 2). This taxonomy serves as the foundation for the benchmark to provide detailed insights about a model’s weaknesses and vulnerabilities as well as inform targeted safety enhancements 🛡️

For collecting our prompts, we started from the popular
Anthropic's HH-RLHF data, and used automated strategies to filter/classify prompts. We then designed templates to create new prompts (providing sufficient support for each category, cf. Fig. 3) and implemented adversarial attacks.

In our experiments, we extensively evaluated several open- and closed-source LLMs (e.g. #ChatGPT, #Llama and #Mistral), highlighting their strengths and weaknesses (Table 1).

For more details, check out our preprint: https://arxiv.org/pdf/2404.08676.pdf 🤓

Huge thanks to @felfri , @PSaiml , Kristian Kersting, @navigli , @huu-ontocord and @BoLi-aisecure (and all the organizations involved: Babelscape, Sapienza NLP, TU Darmstadt, Hessian.AI, DFKI, Ontocord.AI, UChicago and UIUC)🫂

1 reply

reacted to huu-ontocord's post with 🔥❤️ 10 months ago

Post

1661

We would like to announce our Aurora-M multilingual models which is based on Starcoderplus.
Twitter: https://twitter.com/ontocord/status/1772778544051155029
LinkedIn: https://www.linkedin.com/feed/update/urn:li:activity:7178521998845759488/
Blog post: https://huggingface.co/blog/mayank-mishra/aurora
Arxiv: Aurora-M: The First Open Source Multilingual Language Model Red-teamed according to the U.S. Executive Order (2404.00399)

Current LLMs are very susceptible to generating toxic, harmful and even dangerous content. They can also generate outputs with gender or racial biases. The Biden-Harris Executive Order https://www.federalregister.gov/documents/2023/11/01/2023-24283/safe-secure-and-trustworthy-development-and-use-of-artificial-intelligence) sets forth guidelines on what is considered a safe AI system.
Following up on these guidelines, we present the world's first open source Biden-Harris Executive Order Red teamed Multilingual Language Model: Aurora-M. Inspired by BigScience, the model is trained on 5 languages: English, Hindi, Japanese, Vietnamese and Finnish.

* Red teamed model: aurora-m/aurora-m-biden-harris-redteamed tuned according to the order mentioned above)
* Base model: aurora-m/aurora-m-base (not safety tuned)
* Instruct model: aurora-m/aurora-m-instruct (not safety tuned)

@mayank-mishra @cabbage972 @sted97 @Xa9aX @Taishi-N324 @Muennighoff @vumichien @prateeky2806 @felfri @spyysalo and many many others!

reacted to mayank-mishra's post with 🔥 11 months ago

Post

1898

Current LLMs are very susceptible to generating toxic, harmful and even dangerous content. They can also generate outputs with gender or racial biases.

The Biden-Harris Executive Order (https://www.federalregister.gov/documents/2023/11/01/2023-24283/safe-secure-and-trustworthy-development-and-use-of-artificial-intelligence) sets forth guidelines on what is considered a safe AI system.

Following up on these guidelines, we present the world's first open source Biden-Harris Executive Order Red teamed Multilingual Language Model: Aurora-M.

The model is trained on 5 languages: English, Hindi, Japanese, Vietnamese and Finnish.

Blog: https://huggingface.co/blog/mayank-mishra/aurora
Paper coming out soon.

Base model: aurora-m/aurora-m-base (not safety tuned)
Instruct model: aurora-m/aurora-m-instruct (not safety tuned)
Red teamed model: aurora-m/aurora-m-biden-harris-redteamed (safety tuned according to the order mentioned above)