Fancy Stateful Metaflow Service + UI on Google Colab ?
โข
4
Aurรฉlien-Morgan CLAUDON
Aurelien-Morgan
AI & ML interests
None yet
Recent Activity
upvoted
an
article
1 day ago
Letโs make a generation of amazing image generation models
Articles
Organizations
Aurelien-Morgan's activity
Reacted to
merve's
post with ๐
about 7 hours ago
Post
375
The authors of ColPali trained a retrieval model based on SmolVLM ๐ค
vidore/colsmolvlm-alpha
TLDR;
- ColSmolVLM performs better than ColPali and DSE-Qwen2 on all English tasks
- ColSmolVLM is more memory efficient than ColQwen2 ๐
TLDR;
- ColSmolVLM performs better than ColPali and DSE-Qwen2 on all English tasks
- ColSmolVLM is more memory efficient than ColQwen2 ๐
upvoted
an
article
1 day ago
Article
Letโs make a generation of amazing image generation models
By
โข
โข
28
Reacted to
thomwolf's
post with ๐ง
2 days ago
Post
1461
Interesting long read from
@evanmiller-anthropic
on having a better founded statistical approach to Language Model Evaluations:
https://www.anthropic.com/research/statistical-approach-to-model-evals
Worth a read if you're into LLM evaluations!
Cc @clefourrier
https://www.anthropic.com/research/statistical-approach-to-model-evals
Worth a read if you're into LLM evaluations!
Cc @clefourrier
- 1 reply
Reacted to
danielhanchen's
post with ๐ฅ
3 days ago
Post
1198
Vision finetuning is in ๐ฆฅUnsloth! You can now finetune Llama 3.2, Qwen2 VL, Pixtral and all Llava variants up to 2x faster and with up to 70% less VRAM usage! Colab to finetune Llama 3.2: https://colab.research.google.com/drive/1j0N4XTY1zXXy7mPAhOC1_gMYZ2F2EBlk?usp=sharing
- 1 reply
liked
a
dataset
5 days ago
upvoted
a
collection
8 days ago
Reacted to
AdinaY's
post with ๐
8 days ago
Post
998
Build a collection for the trending demos recently released by the Chinese community ๐ From Qwen2.5 Turbo to FishAgent, see what these models can really do ๐ฅ
zh-ai-community/trending-demo-673b6ca2416a3b3c9d3bf8f1
zh-ai-community/trending-demo-673b6ca2416a3b3c9d3bf8f1
Reacted to
PLB's
post with ๐
8 days ago
Post
1843
โ ๏ธ People selling AI chatbots for websites hate us.
Add an open source chat assistant on your website in 5 minutes: https://github.com/phospho-app/ai-chat-bubble
How does it work ?
- You give an URL
- The AI assistant crawls the website content and embed it
- Add it to your frontend in one line of code
- People on your website can ask the assistant questions
Powered by BAAI/bge-small-en-v1.5 and Mistral AI
Add an open source chat assistant on your website in 5 minutes: https://github.com/phospho-app/ai-chat-bubble
How does it work ?
- You give an URL
- The AI assistant crawls the website content and embed it
- Add it to your frontend in one line of code
- People on your website can ask the assistant questions
Powered by BAAI/bge-small-en-v1.5 and Mistral AI
- 5 replies
liked
a
model
8 days ago
Reacted to
m-ric's
post with ๐
9 days ago
Post
377
๐ ๐ฒ๐๐ฎ ๐๐ฒ๐ฎ๐บ ๐ท๐๐๐ ๐ฑ๐ฟ๐ผ๐ฝ๐ฝ๐ฒ๐ฑ ๐๐ต๐ฒ ๐ณ๐ถ๐ฟ๐๐ ๐ช๐ฎ๐๐ฒ๐ฟ๐บ๐ฎ๐ฟ๐ธ๐ถ๐ป๐ด ๐บ๐ผ๐ฑ๐ฒ๐น ๐๐ต๐ฎ๐ ๐ป๐ผ๐ ๐ฒ๐ฑ๐ถ๐ ๐ฐ๐ฎ๐ป ๐ฏ๐ฟ๐ฒ๐ฎ๐ธ!๐ก๏ธ
๐ค Ever heard of watermarking? It's a technique that allows you to mark in an image its original source. It's our best shield against AI-generated deepfakes, or content stolen from artists! ๐จ
๐ญ Watermarking systems are actually a pair of models: a watermark embedder that applies the watermark on the image, and its corresponding decoder that should detect the original watermark.
โ But current methods were very limited: they can only apply and detect the watermark on your image as a whole. So, if you're an attacker it's easy to break: just crop it! add text on top! or whatever, really, anything would work to break the watermark.
A team of researchers at Meta was not happy with this. ๐ค
So to withstand real-world attacks, they decided to make a watermarking model that would also work on any sub-part of the image. It's a real paradigm shift: they consider watermarking not as an image classification task, but as an image segmentation task!
๐๏ธ ๐๐ฟ๐ฐ๐ต๐ถ๐๐ฒ๐ฐ๐๐๐ฟ๐ฒ
โธ The "Embedder" (a variational autoencoder + embedder, 1.1M parameters in total) encodes a n-bit message into a watermark signal that is added to the original image
โธ [Only during training] The "Augmenter" randomly distorts the image: masks parts, crops, resizes, compresses. It's basically torture at this point.
โธ The "Extractor" (a vision transformer, or ViT, with 96M parameters) then re-extracts the message from the distorted image, by predicting a (1+n) vector per pixel to predict the watermarked parts and decode corresponding messages.
The performance blows existing models out of the water, they even created new tasks (segmentation-related) just to grok them!
Gerat work @pierrefdz and @tomsander1998 !
Paper here ๐ Watermark Anything with Localized Messages (2411.07231)
๐ค Ever heard of watermarking? It's a technique that allows you to mark in an image its original source. It's our best shield against AI-generated deepfakes, or content stolen from artists! ๐จ
๐ญ Watermarking systems are actually a pair of models: a watermark embedder that applies the watermark on the image, and its corresponding decoder that should detect the original watermark.
โ But current methods were very limited: they can only apply and detect the watermark on your image as a whole. So, if you're an attacker it's easy to break: just crop it! add text on top! or whatever, really, anything would work to break the watermark.
A team of researchers at Meta was not happy with this. ๐ค
So to withstand real-world attacks, they decided to make a watermarking model that would also work on any sub-part of the image. It's a real paradigm shift: they consider watermarking not as an image classification task, but as an image segmentation task!
๐๏ธ ๐๐ฟ๐ฐ๐ต๐ถ๐๐ฒ๐ฐ๐๐๐ฟ๐ฒ
โธ The "Embedder" (a variational autoencoder + embedder, 1.1M parameters in total) encodes a n-bit message into a watermark signal that is added to the original image
โธ [Only during training] The "Augmenter" randomly distorts the image: masks parts, crops, resizes, compresses. It's basically torture at this point.
โธ The "Extractor" (a vision transformer, or ViT, with 96M parameters) then re-extracts the message from the distorted image, by predicting a (1+n) vector per pixel to predict the watermarked parts and decode corresponding messages.
The performance blows existing models out of the water, they even created new tasks (segmentation-related) just to grok them!
Gerat work @pierrefdz and @tomsander1998 !
Paper here ๐ Watermark Anything with Localized Messages (2411.07231)
Reacted to
erikkaum's
post with ๐๐ฅ
9 days ago
Post
1667
A while ago I started experimenting with compiling the Python interpreter to WASM.
To build a secure, fast, and lightweight sandbox for code execution โ ideal for running LLM-generated Python code.
- Send code simply as a POST request
- 1-2ms startup times
Hack away:
https://github.com/ErikKaum/runner
To build a secure, fast, and lightweight sandbox for code execution โ ideal for running LLM-generated Python code.
- Send code simply as a POST request
- 1-2ms startup times
Hack away:
https://github.com/ErikKaum/runner
Reacted to
merve's
post with ๐
9 days ago
Post
1759
๐ค transformers pipelines now support vision language models for easy local inference ๐ซฐ๐ป
h/t @yonigozlan for shipping this ๐ฉ๐
you can also use inference API to infer hosted vision LMs (via Python, JS and cURL) https://huggingface.co/docs/api-inference/en/tasks/image-text-to-text
h/t @yonigozlan for shipping this ๐ฉ๐
you can also use inference API to infer hosted vision LMs (via Python, JS and cURL) https://huggingface.co/docs/api-inference/en/tasks/image-text-to-text
Reacted to
maxiw's
post with ๐ค
9 days ago
Post
4576
I was curious to see what people post here on HF so I created a dataset with all HF Posts:
maxiw/hf-posts
Some interesting stats:
Top 5 Authors by Total Impressions:
-----------------------------------
@merve : 171,783 impressions (68 posts)
@fdaudens : 135,253 impressions (81 posts)
@singhsidhukuldeep : 122,591 impressions (81 posts)
@akhaliq : 119,526 impressions (78 posts)
@MonsterMMORPG : 112,500 impressions (45 posts)
Top 5 Users by Number of Reactions Given:
----------------------------------------
@osanseviero : 1278 reactions
@clem : 910 reactions
@John6666 : 899 reactions
@victor : 674 reactions
@samusenps : 655 reactions
Top 5 Most Used Reactions:
-------------------------
โค๏ธ: 7048 times
๐ฅ: 5921 times
๐: 4856 times
๐: 2549 times
๐ค: 2065 times
Some interesting stats:
Top 5 Authors by Total Impressions:
-----------------------------------
@merve : 171,783 impressions (68 posts)
@fdaudens : 135,253 impressions (81 posts)
@singhsidhukuldeep : 122,591 impressions (81 posts)
@akhaliq : 119,526 impressions (78 posts)
@MonsterMMORPG : 112,500 impressions (45 posts)
Top 5 Users by Number of Reactions Given:
----------------------------------------
@osanseviero : 1278 reactions
@clem : 910 reactions
@John6666 : 899 reactions
@victor : 674 reactions
@samusenps : 655 reactions
Top 5 Most Used Reactions:
-------------------------
โค๏ธ: 7048 times
๐ฅ: 5921 times
๐: 4856 times
๐: 2549 times
๐ค: 2065 times
- 10 replies
Reacted to
ArthurZ's
post with ๐ฅ
9 days ago
Post
2267
Native tensor parallel has landed in transformers!!! https://github.com/huggingface/transformers/pull/34184 thanks a lot to the torch team for their support!
Contributions are welcome to support more models! ๐ฅ
Contributions are welcome to support more models! ๐ฅ
upvoted
a
paper
10 days ago
Reacted to
AdinaY's
post with ๐ฅ
12 days ago
Post
2516
Letโs dive into the exciting releases from the Chinese community last week ๐ฅ๐
More details ๐ https://huggingface.co/zh-ai-community
Code model:
โจQwen 2.5 coder by Alibaba Qwen
Qwen/qwen25-coder-66eaa22e6f99801bf65b0c2f
โจOpenCoder by InflyAI - Fully open code model๐
infly/opencoder-672cec44bbb86c39910fb55e
Image model:
โจHunyuan3D-1.0 by Tencent
tencent/Hunyuan3D-1
MLLM:
โจJanusFlow by DeepSeek
deepseek-ai/JanusFlow-1.3B
deepseek-ai/JanusFlow-1.3B
โจMono-InternVL-2B by OpenGVlab
OpenGVLab/Mono-InternVL-2B
Video model:
โจCogVideoX 1.5 by ChatGLM
THUDM/CogVideoX1.5-5B-SAT
Audio model:
โจFish Agent by FishAudio
fishaudio/fish-agent-v0.1-3b
Dataset:
โจOPI dataset by BAAIBeijing
BAAI/OPI
More details ๐ https://huggingface.co/zh-ai-community
Code model:
โจQwen 2.5 coder by Alibaba Qwen
Qwen/qwen25-coder-66eaa22e6f99801bf65b0c2f
โจOpenCoder by InflyAI - Fully open code model๐
infly/opencoder-672cec44bbb86c39910fb55e
Image model:
โจHunyuan3D-1.0 by Tencent
tencent/Hunyuan3D-1
MLLM:
โจJanusFlow by DeepSeek
deepseek-ai/JanusFlow-1.3B
deepseek-ai/JanusFlow-1.3B
โจMono-InternVL-2B by OpenGVlab
OpenGVLab/Mono-InternVL-2B
Video model:
โจCogVideoX 1.5 by ChatGLM
THUDM/CogVideoX1.5-5B-SAT
Audio model:
โจFish Agent by FishAudio
fishaudio/fish-agent-v0.1-3b
Dataset:
โจOPI dataset by BAAIBeijing
BAAI/OPI
liked
a
Space
14 days ago
liked
a
dataset
18 days ago
upvoted
a
paper
18 days ago