LLMs Lost in Translation: M-ALERT uncovers Cross-Linguistic Safety Gaps
Paper
•
2412.15035
•
Published
•
4
Ontocord.AI
AI & ML interests
We dedicate ourselves to bringing lawful and effective data to AI training so that everyone can benefit from human knowledge. Our focus is data-centric ML focused on performance and legal compliance, pre-training and safety for large multimodal foundation models.
Recent Activity
View all activity
ontocord's activity
felfri
authored
a
paper
2 days ago
PSaiml
authored
a
paper
2 days ago
huu-ontocord
updated
a
dataset
4 days ago
huu-ontocord
updated
2
models
7 days ago
huu-ontocord
updated
a
Space
11 days ago
huu-ontocord
updated
a
dataset
14 days ago
anoperson
authored
a
paper
about 1 month ago
Post
3886
nanoLLaVA-1.5 is here! Same size (1B), better performance 🔥🔥🔥
And it is much more powerful than v1.0
Try it out now on HF Spaces: qnguyen3/nanoLLaVA
Model: qnguyen3/nanoLLaVA-1.5
And it is much more powerful than v1.0
Try it out now on HF Spaces: qnguyen3/nanoLLaVA
Model: qnguyen3/nanoLLaVA-1.5
- 3 replies
Post
2274
🚀 Excited to announce the release of our new research paper, "LLAVAGUARD: VLM-based Safeguards for Vision Dataset Curation and Safety Assessment"!
In this work, we introduce LLAVAGUARD, a family of cutting-edge Vision-Language Model (VLM) judges designed to enhance the safety and integrity of vision datasets and generative models. Our approach leverages flexible policies for assessing safety in diverse settings. This context awareness ensures robust data curation and model safeguarding alongside comprehensive safety assessments, setting a new standard for vision datasets and models. We provide three versions (7B, 13B, and 34B) and our data, see below. This achievement wouldn't have been possible without the incredible teamwork and dedication of my great colleagues @LukasHug , @PSaiml , @mbrack . 🙏 Together, we've pushed the boundaries of what’s possible at the intersection of large generative models and safety.
🔍 Dive into our paper to explore:
Innovative methodologies for dataset curation and model safeguarding.
State-of-the-art safety assessments.
Practical implications for AI development and deployment.
Find more at AIML-TUDA/llavaguard-665b42e89803408ee8ec1086 and https://ml-research.github.io/human-centered-genai/projects/llavaguard/index.html
In this work, we introduce LLAVAGUARD, a family of cutting-edge Vision-Language Model (VLM) judges designed to enhance the safety and integrity of vision datasets and generative models. Our approach leverages flexible policies for assessing safety in diverse settings. This context awareness ensures robust data curation and model safeguarding alongside comprehensive safety assessments, setting a new standard for vision datasets and models. We provide three versions (7B, 13B, and 34B) and our data, see below. This achievement wouldn't have been possible without the incredible teamwork and dedication of my great colleagues @LukasHug , @PSaiml , @mbrack . 🙏 Together, we've pushed the boundaries of what’s possible at the intersection of large generative models and safety.
🔍 Dive into our paper to explore:
Innovative methodologies for dataset curation and model safeguarding.
State-of-the-art safety assessments.
Practical implications for AI development and deployment.
Find more at AIML-TUDA/llavaguard-665b42e89803408ee8ec1086 and https://ml-research.github.io/human-centered-genai/projects/llavaguard/index.html
- 2 replies
PSaiml
authored
a
paper
8 months ago
huu-ontocord
authored
a
paper
8 months ago
Post
5306
🎉 Introducing nanoLLaVA, a powerful multimodal AI model that packs the capabilities of a 1B parameter vision language model into just 5GB of VRAM. 🚀 This makes it an ideal choice for edge devices, bringing cutting-edge visual understanding and generation to your devices like never before. 📱💻
Model: qnguyen3/nanoLLaVA 🔍
Spaces: qnguyen3/nanoLLaVA (thanks to @merve )
Under the hood, nanoLLaVA is based on the powerful vilm/Quyen-SE-v0.1 (my Qwen1.5-0.5B finetune) and Google's impressive google/siglip-so400m-patch14-384. 🧠 The model is trained using a data-centric approach to ensure optimal performance. 📊
In the spirit of transparency and collaboration, all code and model weights are open-sourced under the Apache 2.0 license. 🤝
Model: qnguyen3/nanoLLaVA 🔍
Spaces: qnguyen3/nanoLLaVA (thanks to @merve )
Under the hood, nanoLLaVA is based on the powerful vilm/Quyen-SE-v0.1 (my Qwen1.5-0.5B finetune) and Google's impressive google/siglip-so400m-patch14-384. 🧠 The model is trained using a data-centric approach to ensure optimal performance. 📊
In the spirit of transparency and collaboration, all code and model weights are open-sourced under the Apache 2.0 license. 🤝
- 1 reply
spyysalo
authored
a
paper
9 months ago
kenhktsui
authored
a
paper
9 months ago
huu-ontocord
posted
an
update
9 months ago
Post
1641
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!
spyysalo
authored
a
paper
9 months ago
huu-ontocord
authored
a
paper
9 months ago
spyysalo
authored
2
papers
9 months ago