Hugging Face's logo

huggingPartyParis

community
https://partiful.com/e/oWOMGoPxB5D37qw5F8yN
Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

andreamaduzzi  authored a paper 19 days ago
Scaling LLaNA: Advancing NeRF-Language Understanding Through Large-Scale Training
loubnabnl  authored a paper about 1 month ago
SmolVLM: Redefining small and efficient multimodal models
dovpie  authored a paper about 1 month ago
Semantic Library Adaptation: LoRA Retrieval and Fusion for Open-Vocabulary Semantic Segmentation
View all activity

HuggingPartyParis's activity

m-ric 
posted an update 1 day ago
view post
Post
2184
I've made an open version of Google's NotebookLM, and it shows the superiority of the open source tech task! 💪

The app's workflow is simple. Given a source PDF or URL, it extracts the content from it, then tasks Meta's Llama 3.3-70B with writing the podcast script, with a good prompt crafted by @gabrielchua ("two hosts, with lively discussion, fun notes, insightful question etc.")
Then it hands off the text-to-speech conversion to Kokoro-82M, and there you go, you have two hosts discussion any article.

The generation is nearly instant, because:
> Llama 3.3 70B is running at 1,000 tokens/seconds with Cerebras inference
> The audio is generated in streaming mode by the tiny (yet powerful) Kokoro, generating voices faster than real-time.

And the audio generation runs for free on Zero GPUs, hosted by HF on H200s.

Overall, open source solutions rival the quality of closed-source solutions at close to no cost!

Try it here 👉👉 m-ric/open-notebooklm
  • 2 replies
·
clem 
posted an update 2 days ago
clem 
posted an update 4 days ago
view post
Post
3867
What are you using to evaluate models or AI systems? So far we're building lighteval & leaderboards on the hub but still feels early & a lot more to build. What would be useful to you?
·
clem 
posted an update 9 days ago
clem 
posted an update 9 days ago
view post
Post
1478
The meta-llama org just crossed 40,000 followers on Hugging Face. Grateful for all their impact on the field sharing the Llama weights openly and much more!

We need more of this from all other big tech to make the AI more open, collaborative and beneficial to all!
clem 
posted an update 18 days ago
view post
Post
3983
Energy is a massive constraint for AI but do you even know what energy your chatGPT convos are using?

We're trying to change this by releasing ChatUI-energy, the first interface where you see in real-time what energy your AI conversations consume. Great work from @jdelavande powered by spaces & TGI, available for a dozen of open-source models like Llama, Mistral, Qwen, Gemma and more.

jdelavande/chat-ui-energy

Should all chat interfaces have this? Just like ingredients have to be shown on products you buy, we need more transparency in AI for users!
  • 3 replies
·
clem 
posted an update 19 days ago
view post
Post
2939
Just crossed half a million public apps on Hugging Face. A new public app is created every minute these days 🤯🤯🤯

What's your favorite? http://hf.co/spaces
  • 3 replies
·
m-ric 
posted an update 23 days ago
view post
Post
2737
New king of open VLMs: InternVL3 takes Qwen 2.5's crown! 👑

InternVL have been a wildly successful series of model : and the latest iteration has just taken back their crown thanks to their superior, natively multimodal vision training pipeline.

➡️ Most of the vision language models (VLMs) these days are built like Frankenstein : take a good text-only Large Language Model (LLM) backbone, stitch a specific vision transformer (ViT) on top of it. Then the training is sequential 🔢 : 1. Freeze the LLM weights while you train the ViT only to work with the LLM part, then 2. Unfreeze all weights to train all weights in order to work together.

💫 The Shanghai Lab decided to challenge this paradigm and chose this approach that they call "native". For each of their model sizes, they still start from a good LLM (mostly Qwen-2.5 series, did I tell you I'm a huge fan of Qwen? ❤️), and stitch the ViT, but they don't freeze anything : they train all weights together with interleaved text and image understanding data in a single pre-training phase 🎨.

They claim it results in more seamless interactions between modalities. And the results prove them right: they took the crown of top VLMs, at nearly all sizes, from their Qwen-2.5 parents. 👑
  • 2 replies
·
clem 
posted an update 24 days ago
view post
Post
1471
You can now bill your inference costs from all our inference partners (together, fireworks, fal, sambanova, cerebras, hyperbolic,...) to your Hugging Face organization.

Useful to drive more company-wide usage of AI without the billing headaches!
  • 1 reply
·
nv-nguyen 
authored a paper about 1 month ago
eliebak 
authored a paper about 1 month ago
clem 
posted an update about 1 month ago
view post
Post
2656
Llama 4 is in transformers!

Fun example using the instruction-tuned Maverick model responding about two images, using tensor parallel for maximum speed.

From https://huggingface.co/blog/llama4-release
  • 1 reply
·
clem 
posted an update about 1 month ago
view post
Post
1997
Llama models (arguably the most successful open AI models of all times) just represented 3% of total model downloads on Hugging Face in March.

People and media like stories of winner takes all & one model/company to rule them all but the reality is much more nuanced than this!

Kudos to all the small AI builders out there!
  • 2 replies
·
clem 
posted an update about 1 month ago
view post
Post
1355
Now in Enterprise Hub organizations, you can centralize your billing not only for HF usage but also inference through our inference partners.

Will prevent some headaches for your finance & accounting teams haha (so feel free to share that with them).
  • 3 replies
·
clem 
posted an update about 1 month ago
view post
Post
4031
Before 2020, most of the AI field was open and collaborative. For me, that was the key factor that accelerated scientific progress and made the impossible possible—just look at the “T” in ChatGPT, which comes from the Transformer architecture openly shared by Google.

Then came the myth that AI was too dangerous to share, and companies started optimizing for short-term revenue. That led many major AI labs and researchers to stop sharing and collaborating.

With OAI and sama now saying they're willing to share open weights again, we have a real chance to return to a golden age of AI progress and democratization—powered by openness and collaboration, in the US and around the world.

This is incredibly exciting. Let’s go, open science and open-source AI!
·
m-ric 
posted an update about 1 month ago
view post
Post
2331
🚀 DeepSeek R1 moment has come for GUI agents: Rule-based Reinforcement Learning gives better results than SFT with 500x smaller datasets!

Traditionally (by which I mean "in the last few months"), GUI agents have been trained with supervised fine-tuning (SFT). This meant, collecting huge datasets of screen captures from people using computers, and using these to fine-tune your model. 📚

👉 But last week, a new paper introduced UI-R1, applying DeepSeek's R1-style rule-based reinforcement learning (RL) specifically to GUI action prediction tasks.
This is big news: with RL, maybe we could build good agents without the need for huge datasets.

UI-R1 uses a unified reward function that evaluates multiple responses from models, optimizing via policy algorithms like Group Relative Policy Optimization (GRPO).

Specifically, the reward function assesses:
🎯 Action type accuracy: Does the predicted action match the ground truth?
📍 Coordinate accuracy (specifically for clicks): Is the predicted click within the correct bounding box?
📑 Output format: Does the model clearly articulate both its reasoning and final action?

Using just 136 carefully selected mobile tasks—compared to 76,000 tasks for larger models like OS-Atlas—UI-R1 shows significant efficiency and improved performance:
📈 Boosted action prediction accuracy from 76% to 89% on AndroidControl.
🌐 Outperformed larger, SFT-trained models (e.g., OS-Atlas-7B), demonstrating superior results with vastly fewer data points (136 tasks vs. 76K).
🔍 Enhanced adaptability and generalization, excelling even in out-of-domain scenarios.

The paper tests this RL-based method only in low-level GUI tasks. Could it generalize to more complex interactions? 🧐

Read the full paper here 👉 UI-R1: Enhancing Action Prediction of GUI Agents by Reinforcement Learning (2503.21620)
clem 
posted an update about 1 month ago
view post
Post
2423
What's this cool purple banner haha 😶😶😶
·
osanseviero 
authored a paper about 1 month ago
clem 
posted an update about 1 month ago
clem 
posted an update about 2 months ago