mattmdjaga (Mateusz Dziemian)

reacted to their post with 🔥 2 months ago

Post

1588

🚨 New Agent Benchmark 🚨
AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents

ai-safety-institute/AgentHarm

Collaboration between UK AI Safety Institute and Gray Swan AI to create a dataset for measuring harmfulness of LLM agents.

The benchmark contains both harmful and benign sets of 11 categories with varied difficulty levels and detailed evaluation, not only testing success rate but also tool level accuracy.

We provide refusal and accuracy metrics across a wide range of models in both no attack and prompt attack scenarios.

AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents (2410.09024)

posted an update 2 months ago

Post

1588

🚨 New Agent Benchmark 🚨
AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents

ai-safety-institute/AgentHarm

Collaboration between UK AI Safety Institute and Gray Swan AI to create a dataset for measuring harmfulness of LLM agents.

The benchmark contains both harmful and benign sets of 11 categories with varied difficulty levels and detailed evaluation, not only testing success rate but also tool level accuracy.

We provide refusal and accuracy metrics across a wide range of models in both no attack and prompt attack scenarios.

AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents (2410.09024)

reacted to their post with 🚀 4 months ago

Post

2162

$40K in Bounties: Ultimate Jailbreaking Championship 2024

🚨Ultimate Jailbreaking Championship 2024 🚨
Hackers vs. AI in the arena. Let the battle begin!
🏆 $40,000 in Bounties
🗓️ Sept 7, 2024 @ 10AM PDT
🔗Register Now: https://app.grayswan.ai/arena
====

Can you push an aligned language model to generate a bomb recipe or a fake news article? Join fellow hackers in a jailbreaking arena where you can test the boundaries of advanced LLMs.

====

The Objective
Your goal is to jailbreak as many LLMs as possible, as quickly as possible in the arena!

====

The Stakes
Break a model and claim your share of the $40,000 in bounties! With various jailbreak bounties and top hacker rewards, there are plenty of opportunities to win. Winners will also receive priority consideration for employment and internship opportunities at Gray Swan AI.

====

Ready to rise to the challenge? Join us and show the world what you can do!

See you in the arena!

1 reply

·

posted an update 4 months ago

Post

2162

$40K in Bounties: Ultimate Jailbreaking Championship 2024

🚨Ultimate Jailbreaking Championship 2024 🚨
Hackers vs. AI in the arena. Let the battle begin!
🏆 $40,000 in Bounties
🗓️ Sept 7, 2024 @ 10AM PDT
🔗Register Now: https://app.grayswan.ai/arena
====

Can you push an aligned language model to generate a bomb recipe or a fake news article? Join fellow hackers in a jailbreaking arena where you can test the boundaries of advanced LLMs.

====

The Objective
Your goal is to jailbreak as many LLMs as possible, as quickly as possible in the arena!

====

The Stakes
Break a model and claim your share of the $40,000 in bounties! With various jailbreak bounties and top hacker rewards, there are plenty of opportunities to win. Winners will also receive priority consideration for employment and internship opportunities at Gray Swan AI.

====

Ready to rise to the challenge? Join us and show the world what you can do!

See you in the arena!

1 reply

·

reacted to alvdansen's post with 🤗 5 months ago

Post

6875

Alright Ya'll

I know it's a Saturday, but I decided to release my first Flux Dev Lora.

A retrain of my "Frosting Lane" model and I am sure the styles will just keep improving.

Have fun! Link Below - Thanks again to @ostris for the trainer and Black Forest Labs for the awesome model!

alvdansen/frosting_lane_flux

reacted to victor's post with 🔥 7 months ago

Post

2392

Congrats to @alvdansen for one of the nicest SD LoRA ever. It's so sharp and beautiful!
Check the model page to try it on your own prompts: alvdansen/BandW-Manga
And follow @alvdansen for more 😙

5 replies

·

reacted to merve's post with 🔥 7 months ago

Post

1274

We will be providing ZeroGPU grants (for Spaces inference) to those who want to fine-tune PaliGemma and build a Space 🔥

You can pick any dataset of your choice!

Example code: https://colab.research.google.com/drive/1x_OEphRK0H97DqqxEyiMewqsTiLD_Xmi?usp=sharing (you can use a lower GPU with QLoRA)

Datasets:
https://huggingface.co/datasets?task_categories=task_categories:text-to-image&sort=trending
https://huggingface.co/datasets?task_categories=task_categories:image-to-text&sort=trending

5 replies

·

reacted to Taylor658's post with 🔥 7 months ago

Post

1311

The Hugging Face Computer Vision community will have the first in a series of online hangouts/study groups this Saturday June 1st at 10:00 am EDT.🚀

Join us on the Hugging Face Discord channel for the Hangout!

https://discord.gg/hugging-face-879548962464493619?event=1243129304863215656 🤗

reacted to tomaarsen's post with 🔥 7 months ago

Post

1984

‼️Sentence Transformers v3.0 is out! You can now train and finetune embedding models with multi-GPU training, bf16 support, loss logging, callbacks & much more. I also release 50+ datasets to train on.

1️⃣ Training Refactor
Embedding models can now be trained using an extensive trainer with a lot of powerful features:
- MultiGPU Training (Data Parallelism (DP) and Distributed Data Parallelism (DDP))
- bf16 training support; loss logging
- Evaluation datasets + evaluation loss
- Improved callback support + an excellent Weights & Biases integration
- Gradient checkpointing, gradient accumulation
- Improved model card generation
- Resuming from a training checkpoint without performance loss
- Hyperparameter Optimization
and much more!
Read my detailed blogpost to learn about the components that make up this new training approach: https://huggingface.co/blog/train-sentence-transformers

2️⃣ Similarity Score
Not sure how to compare embeddings? Don't worry, you can now use model.similarity(embeddings1, embeddings2) and you'll get your similarity scores immediately. Model authors can specify their desired similarity score, so you don't have to worry about it anymore!

3️⃣ Additional Kwargs
Sentence Transformers relies on various Transformers instances (AutoModel, AutoTokenizer, AutoConfig), but it was hard to provide valuable keyword arguments to these (like 'torch_dtype=torch.bfloat16' to load a model a lower precision for 2x inference speedup). This is now easy!

4️⃣ Hyperparameter Optimization
Sentence Transformers now ships with HPO, allowing you to effectively choose your hyperparameters for your data and task.

5️⃣ Dataset Release
To help you out with finetuning models, I've released 50+ ready-to-go datasets that can be used with training or finetuning embedding models: sentence-transformers/embedding-model-datasets-6644d7a3673a511914aa7552

Full release notes: https://github.com/UKPLab/sentence-transformers/releases/tag/v3.0.0

reacted to MoritzLaurer's post with 🚀 7 months ago

Post

3294

We are hiring a "Developer Experience Engineer for Inference" at Hugging Face! If you want to make it easier for millions of people to use modern machine learning inference, apply! You can either work from one of our offices e.g. in Paris or New York, or work fully remotely. Details: https://apply.workable.com/huggingface/j/E732F4B8FC/

reacted to Dref360's post with 🚀 7 months ago

Post

1092

Baal, our Bayesian Active Learning library is working on a major version and we want to know more about you!

If you use Baal for Active Learning, Uncertainty Estimation or Bayesian Deep Learning, we would **love** to talk to you! 😎

In more detail, we want to understand when our users use our library and how.

You can take a spot in our Calendly: https://calendly.com/baal-org/30min?month=2024-05

reacted to rwightman's post with ❤️ 7 months ago

Post

1862

timm 1.0 is finally out. The big feature that I wanted to complete before doing this? Having the unified feature map extraciton interface (features_only=True) supporting almost all models (97%) 🎉 See docs at https://huggingface.co/docs/timm/en/feature_extraction

Also in this release, the new set of SBB (searching for better baselins) ViT models, covering new architectures and hparam exploration between tiny and base. See timm/searching-for-better-vit-baselines-663eb74f64f847d2f35a9c19

I also snuck in image-tower loading for PaliGemma (via jax weights on Hub) google/paligemma-release-6643a9ffbf57de2ae0448dda

reacted to their post with 🚀 8 months ago

Post

1815

NEW HF 🤗 COURSE to help people dive into Computer Vision built by the HF community. Over the last 6 months the hugging face discord community has been hard at work developing a new computer vision course. Receive a Certificate of completion and share it on your socials 🤗.

https://huggingface.co/learn/computer-vision-course/unit0/welcome/welcome

1 reply

·

posted an update 8 months ago

Post

1815

NEW HF 🤗 COURSE to help people dive into Computer Vision built by the HF community. Over the last 6 months the hugging face discord community has been hard at work developing a new computer vision course. Receive a Certificate of completion and share it on your socials 🤗.

https://huggingface.co/learn/computer-vision-course/unit0/welcome/welcome

1 reply

·

reacted to merve's post with 🔥 8 months ago

Post

3842

just landed at Hugging Face Hub: community-led computer vision course 📖🤍
learn from fundamentals to details of the bleeding edge vision transformers!

1 reply

·

reacted to mvaloatto's post with ❤️ 10 months ago

Post

Want more “good machine learning” in your X feed? Here is a new Space for you:
🔔 Top HF Users To Follow On X - https://huggingface.co/spaces/mvaloatto/HF2X

Ever since I fell down the AI rabbit hole, it hasn’t been super easy to spot and follow the most impactful Hugging Face contributors on X. So, inspired by @Weyaxi leaderboards, I decided to create a list just for this purpose.

Why, you ask?

First, it’s quite surprising how so many talented AI pioneers and independent contributors on X don't get the visibility/reach you might expect. Sad but true: follower count doesn't always match up with the value or innovation an individual brings to the table (just stating the obvious here).

Open source AI, in particular, thrives not just on innovation but also on the collective spirit of its believers and builders. With Hugging Face standing out as a prime hub for top AI engineers and contributors, compiling a directory of X profiles from influential figures on this platform felt like a natural step.

This Space aims to not only connect these top contributors but also guide open AI enthusiasts and newcomers towards the field's leading lights.

I put this modest page together using some web scraping and what I remember from my web dev class ages ago! Suggestions/likes are welcome - I’m hoping to keep tweaking/upgrading it, especially if you all find it useful.

Now, let’s follow each other! It’s time to accelerate the dissemination of our ideas, encourage collaboration within our community, and ensure that open AI developments receive the attention and recognition they deserve. 🔥

9 replies

·

replied to isidentical's post 11 months ago

I quite like using https://github.com/s0md3v/sd-webui-roop which you can combine with SDXL and other tools compatible with SDXL, especially when dealing with multiple faces in an image. Here are some examples for a specific output style :

reacted to merve's post with ❤️ 12 months ago

Post

Last month was great for faster/smaller segmentation models, and I wanted to dedicate my first post to compile the recently released SAM variants! 🤗
📚 All models and their demos can be found in this collection 👉🏼 merve/segment-anything-model-6585835fc76915aa14e2bcbd
The ideas behind them are mostly about making heavy image encoder lighter either through distillation or changing the pre-training. 💡
⚡️MobileSAM: It decouples the heavy image encoder of SAM and distills it into a TinyViT to make SAM smaller. The architecture is same except for the encoder.
⚡️TinySAM: It distills the whole model with online hard prompt sampling. The authors also quantized it and released Q-TinySAM.
⚡️ EfficientSAM: This model combines masked image pre-training for training lightweight image encoders (like ViTMAE, learns to reconstruct the images) and mask decoder.
⚡️ FastSAM: It's a CNN-based model where the problem is modeled as segments generation. The inference takes place as everything is segmented at once and then you can prompt with boxes or points or text (and this is how it is similar to SAM). So the architecture is nowhere similar to original SAM itself.
✨ [NEW] SlimSAM: It's a pruned-distilled version of pre-trained SAM. The architecture is same so @nielsr recently converted the weights and you can use it with the same API you use with SAM models. You can find the available checkpoints in the collection.
I hope you liked it!

Mateusz Dziemian

AI & ML interests

Recent Activity

Organizations

mattmdjaga's activity