EU-Guard/EU_alert_working_copy
Updated • 34
EU AI Act Safety Evaluations
community
AI & ML interests
Redteaming; Safety
Recent Activity
View all activity
huu-ontocord
updated a
dataset 11 days ago
huu-ontocord
updated a
dataset 17 days ago
huu-ontocord
published a
dataset 17 days ago
huu-ontocord
published a
dataset 18 days ago
huu-ontocord
updated a
dataset 18 days ago
huu-ontocord
published a
dataset 18 days ago
huu-ontocord
updated a
dataset 18 days ago
huu-ontocord
published a
dataset 18 days ago
huu-ontocord
authored a
paper 3 months ago
huu-ontocord
authored a
paper 10 months ago
huu-ontocord
authored 2
papers about 1 year ago
geoalgo
authored a
paper about 1 year ago
huu-ontocord
authored 3
papers over 1 year ago
RedPajama: an Open Dataset for Training Large Language Models
Paper • 2411.12372 • Published • 59
LLMs Lost in Translation: M-ALERT uncovers Cross-Linguistic Safety Gaps
Paper • 2412.15035 • Published • 4
Project Alexandria: Towards Freeing Scientific Knowledge from Copyright Burdens via LLMs
Paper • 2502.19413 • Published • 22
huu-ontocord
authored a
paper over 2 years ago
huu-ontocord
posted an update over 2 years ago
Post
1943
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!
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!
huu-ontocord
authored 2
papers over 2 years ago