Hugging Face's logo

Paris AI Running Club
community
Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

reach-vb  authored a paper 11 days ago
Open ASR Leaderboard: Towards Reproducible and Transparent Multilingual and Long-Form Speech Recognition Evaluation
pcuenq  new activity 12 days ago
paris-ai-running-club/README:Replace event
julien-c  new activity 12 days ago
paris-ai-running-club/README:Replace event
View all activity

Jofthomas 
posted an update 6 days ago
view post
Post
3319
The new Mistral 3 models are here !

Today, we announce Mistral 3, the next generation of Mistral models. Mistral 3 includes three state-of-the-art small, dense models (14B, 8B, and 3B) and Mistral Large 3 – our most capable model to date – a sparse mixture-of-experts trained with 41B active and 675B total parameters.

All models are released under the Apache 2.0 license.

Ministrals :
https://huggingface.co/collections/mistralai/ministral-3

Mistral Large 3:
https://huggingface.co/collections/mistralai/mistral-large-3
  • 2 replies
·
reach-vb 
authored a paper 11 days ago
pcuenq 
in paris-ai-running-club/README 12 days ago

Replace event

1
#6 opened 12 days ago by
pcuenq
julien-c 
in paris-ai-running-club/README 12 days ago

Replace event

1
#6 opened 12 days ago by
pcuenq
eustlb 
authored a paper 14 days ago
pagezyhf 
posted an update about 1 month ago
view post
Post
2787
🚀 Big news for AI builders!

We’re thrilled to announce that the Qwen3-VL family of vision-language models is now available on Azure AI Foundry, thanks to our collaboration with Microsoft.

We bring open-source innovation to enterprise-grade AI infrastructure, making it easier than ever for enterprise to deploy and scale the latest and greatest from models from hugging Face securely within Azure.

🔍 Highlights:

- Deploy Qwen3-VL instantly via managed endpoints
- Built-in governance, telemetry, and lifecycle management
- True multimodal reasoning — vision, language, and code understanding
- State-of-the-art performance, outperforming closed-source models like Gemini 2.5 Pro and GPT-5
- Available in both *Instruct* and *Thinking* modes, across 24 model sizes

👉 Get started today: search for Qwen3-VL in the Hugging Face Collection on Azure AI Foundry.
  • 1 reply
·
merve 
posted an update about 2 months ago
view post
Post
6597
deepseek-ai/DeepSeek-OCR is out! 🔥 my take ⤵️
> pretty insane it can parse and re-render charts in HTML
> it uses CLIP and SAM features concatenated, so better grounding
> very efficient per vision tokens/performance ratio
> covers 100 languages
·
Molbap 
posted an update 2 months ago
view post
Post
3219
🚀 New blog: Maintain the unmaintainable – 1M+ Python LOC, 400+ models

How do you stop a million-line library built by thousands of contributors from collapsing under its own weight?
At 🤗 Transformers, we do it with explicit software-engineering tenets, principles that make the codebase hackable at scale.

🔍 Inside the post:
– One Model, One File: readability first — you can still open a modeling file and see the full logic, top to bottom.
– Modular Transformers: visible inheritance that cuts maintenance cost by ~15× while keeping models readable.
– Config-Driven Performance: FlashAttention, tensor parallelism, and attention scheduling are config-level features, not rewrites.

Written with @lysandre ,@pcuenq and @yonigozlan , this is a deep dive into how Transformers stays fast, open, and maintainable.

Read it here → transformers-community/Transformers-tenets
Sri-Vigneshwar-DJ 
posted an update 2 months ago
view post
Post
327
Do you think domain-specific embedding fine-tuners are needed?
I've been working with embeddings for marketing use cases and noticed something: most embeddings don't get marketing concepts very well. They're trained in general-purpose ways.
The Issue I'm Seeing
When I search marketing content with general embeddings:

"organic growth" returns farming articles
"conversion funnel" matches industrial equipment
"brand lift" doesn't connect to campaign effectiveness
Marketing jargon like CAC, ROAS, CTR aren't properly understood

My Question
Do you think domain-specific embeddings are needed for marketing?
Some thoughts:

Marketing has its own vocabulary and concept relationships
General models trained on Wikipedia/web crawl miss these nuances
But is fine-tuning worth the effort vs just using more retrieval tricks?

Quick Example
I fine-tuned all-mpnet-base-v2 on ~1000 marketing concept pairs and saw 15-20% better retrieval accuracy. But I'm curious:

Has anyone else tried this for marketing or other domains?
When do you think domain-specific embeddings are actually necessary vs overkill?
Are there better approaches I'm missing?

https://huggingface.co/blog/Sri-Vigneshwar-DJ/why-your-marketing-rag-system-needs-domain-specifi
  • 6 replies
·
Sri-Vigneshwar-DJ 
posted an update 2 months ago
view post
Post
4427
🚀 Exciting News! We've released a Performance Marketing Expert Dataset from Hawky.ai [www.hawky.ai] Hawky-ai


This dataset empowers AI models with cutting-edge strategies for Meta, Google Ads, and TikTok campaigns. It includes:
1. Multi-platform strategies for e-commerce, DTC, B2B, and more
2. Creative optimization and audience targeting insights
3. ROI-driven recommendations based on 2025 best practices

Sri-Vigneshwar-DJ/Performance-Marketing-Data
Sri-Vigneshwar-DJ 
posted an update 2 months ago
view post
Post
3331
🚀 Qwen3-Omni for Marketing: A Game-Changer

Just wanted to share something exciting I've been exploring—Qwen3-Omni and how it's transforming marketing workflows.

What makes it special? At Hawky.ai we are started experimenting with Qwen3 recently for Analysis and Optimization.

Unlike traditional tools that look at text, images, or audio separately, Qwen3-Omni analyzes everything together. It handles 119 languages, processes 40-minute audio sequences, and understands both images and videos—all at once.

The cool part? It's 2-3x faster than similar models thanks to its MoE architecture.

Real applications I'm seeing:
Ad Analysis: It scores video ads by combining visual elements, audio tone, and text—giving 25% better CTR predictions than single-mode tools.
Campaign Localization: Drop in one ad, get 10 localized versions with native voiceovers in under a minute. Perfect for testing across markets.

Market Research: Feed it competitor content, podcasts, or UGC videos. It extracts actionable insights like "3-second hooks boost retention by 15%" and saves about 70% of analysis time.

Quality Checks: Automatically catches lip-sync errors and audio-visual mismatches.

Full technical breakdown: https://huggingface.co/blog/Sri-Vigneshwar-DJ/hawky-aiqwen3-omni-advanced-architecture-and-marke

Has anyone else been experimenting with multimodal models for marketing? Would love to hear what you're building!

#MultimodalAI #MarTech #OpenSource
osanseviero 
authored a paper 2 months ago
pagezyhf 
posted an update 3 months ago
view post
Post
844
What’s your biggest headache deploying Hugging Face models to the cloud—and how can we fix it for you?
·
merve 
posted an update 3 months ago
view post
Post
6709
large AI labs open-sourced a ton of models last week 🔥
here's few picks, find even more here merve/sep-16-releases-68d13ea4c547f02f95842f05 🤝
> IBM released a new Docling model with 258M params based on Granite (A2.0) 📝 ibm-granite/granite-docling-258M
> Xiaomi released 7B audio LM with base and instruct variants (MIT) XiaomiMiMo/mimo-audio-68cc7202692c27dae881cce0
> DecartAI released Lucy Edit, open Nano Banana 🍌 (NC) decart-ai/Lucy-Edit-Dev
> OpenGVLab released a family of agentic computer use models (3B/7B/32B) with the dataset 💻 OpenGVLab/scalecua-68c912cf56f7ff4c8e034003
> Meituan Longcat released thinking version of LongCat-Flash 💭 meituan-longcat/LongCat-Flash-Thinking
  • 2 replies
·
merve 
posted an update 3 months ago
view post
Post
3332
IBM just released small swiss army knife for the document models: granite-docling-258M on Hugging Face 🔥

> not only a document converter but also can do document question answering, understand multiple languages 🤯
> best part: released with Apache 2.0 license 👏 use it with your commercial projects!
> it supports transformers, vLLM and MLX from the get-go! 🤗
> built on SigLIP2 & granite-165M

model: ibm-granite/granite-docling-258M
demo: ibm-granite/granite-docling-258m-demo 💗
merve 
posted an update 3 months ago
pagezyhf 
posted an update 3 months ago
pagezyhf 
posted an update 3 months ago
view post
Post
3901
🤝 Collaborating with AMD to ensure Hugging Face Transformers runs smoothly on AMD GPUs!

We run daily CI on AMD MI325 to track the health of the most important model architectures and we’ve just made our internal dashboard public.

By making this easily accessible, we hope to spark community contributions and improve support for everyone!
  • 2 replies
·
merve 
posted an update 3 months ago
view post
Post
977
fan-favorite vision LM Florence-2 is now officially supported in transformers 🤗

find all the models in florence-community org 🫡
merve 
posted an update 3 months ago