Open to Collab

Pedro Cuenca PRO

pcuenq

AI & ML interests

None yet

Recent Activity

liked a model about 9 hours ago

phanerozoic/segmentation-heads

liked a model about 9 hours ago

phanerozoic/depth-heads

liked a Space about 9 hours ago

phanerozoic/argus

View all activity

Organizations

reactedto fffiloni's post with 😎 about 11 hours ago

Post

2216

AniDoc is back 🎉

I’ve fixed the Space and brought it back to life:
- ✅ Working again after being broken for a while
- ✅ Updated to Gradio 6
- ✅ Compatible with ZeroGPU
- ✅ Output videos now preserve original resolution and FPS

I also added advanced controls so you can experiment more (tracking, seed, motion, sketch).

Try it here: fffiloni/AniDoc

reactedto sergiopaniego's post with 🚀 about 1 month ago

Post

2481

What happens when you make an LLM drive a car where physics are real and actions can't be undone?

I ported CARLA, the autonomous driving simulator, to OpenEnv and added training support via TRL + Hugging Face Spaces.

The model interacts with the simulator through tool calls (observe, brake, change lane) and learns from a reward signal.

In 50 training steps, Qwen 0.6B learns to swerve and brake to avoid pedestrians in emergency situations.

The project supports text and vision (VLMs can see through a camera sensor), open-world driving with traffic, and multiple driving scenarios.

This builds on the carla-env project by sinatras, which originally placed LLMs inside CARLA for evaluation. We extended it with vision, new scenarios, rubric-based rewards, and made it trainable end-to-end.

Blog: https://huggingface.co/blog/sergiopaniego/bringing-carla-to-openenv-trl/
CARLA env in OpenEnv: https://github.com/meta-pytorch/OpenEnv/tree/main/envs/carla_env
Training script: https://github.com/huggingface/trl/blob/main/examples/scripts/openenv/carla.py

posted an update 3 months ago

Post

4316

👉 What happened in AI in 2025? 👈

We prepared the 2025 version of the HF AI Timeline Grid, highlighting open vs API-based model releases, and allowing you to browse and filter by access, modality, and release type!

Play with it here:
2025-ai-timeline/2025-ai-timeline

Here's my personal quarterly TL;DR:

1️⃣ Q1 — Learning to Reason
Deepseek not only releases a top-notch reasoning model, but shows how to train them and compete with closed frontier models. OpenAI debuts Deep Research.

Significant milestones: DeepSeek R1 & R1-Zero, Qwen 2.5 VL, OpenAI Deep Research, Gemini 2.5 Pro (experimental)

2️⃣ Q2 — Multimodality and Coding
More LLMs embrace multimodality by default, and there's a surge in coding agents. Strong vision, audio, and generative models emerge.

Significant milestones: Llama 4, Qwen 3, Imagen 4, OpenAI Codex, Google Jules, Claude 4

3️⃣ Q3 — "Gold" rush, OpenAI opens up, the community goes bananas
Flagship models get gold in Math olympiads and hard benchmarks. OpenAI releases strong open source models and Google releases the much anticipated nano-banana for image generation and editing. Agentic workflows become commonplace.

Significant milestones: Gemini and OpenAI IMO Gold, gpt-oss, Gemini 2.5 Flash Image, Grok 4, Claude Sonnet 4.5

4️⃣ Q4 — Mistral returns, leaderboard hill-climbing
Mistral is back with updated model families. All labs release impressive models to wrap up the year!

Significant milestones: Claude Opus 4.5, DeepSeek Math V2, FLUX 2, GPT 5.1, Kimi K2 Thinking, Nano Banana Pro, GLM 4.7, Gemini 3, Mistral 3, MiniMax M2.1 🤯

Credits
🙏 NHLOCAL for the source data https://github.com/NHLOCAL/AiTimeline

🫡 @reach-vb for the original idea, design and recipe

🙌 @ariG23498 and yours truly for compiling and verifying the 2025 edition

🥳 Here's to 2026, wishing it becomes the best year ever for open releases and on-device-first use-cases! 🥂

3 replies

reactedto sergiopaniego's post with 🚀 4 months ago

Post

3099

NEW: @EssentialAI just released Rnj-1, their first 8B model.

You can easily fine-tune it with GRPO using TRL to add reasoning capabilities to a compact mode

Free Colab link: https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/grpo_rnj_1_instruct.ipynb

More free TRL notebooks: https://huggingface.co/docs/trl/main/en/example_overview#notebooks

reactedto sergiopaniego's post with 🔥 4 months ago

Post

2466

NEW: @mistralai released a fantastic family of multimodal models, Ministral 3.

You can fine-tune them for free on Colab using TRL ⚡️, supporting both SFT and GRPO

Link to the notebooks:
- SFT: https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/sft_ministral3_vl.ipynb
- GRPO: https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/grpo_ministral3_vl.ipynb
- TRL and more examples: https://huggingface.co/docs/trl/index

2 replies

reactedto merve's post with 👍🚀 6 months ago

Post

11186

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

4 replies

reactedto andito's post with 🚀 6 months ago

Post

2528

Finally, our new paper is out! "𝗙𝗶𝗻𝗲𝗩𝗶𝘀𝗶𝗼𝗻: 𝗢𝗽𝗲𝗻 𝗗𝗮𝘁𝗮 𝗜𝘀 𝗔𝗹𝗹 𝗬𝗼𝘂 𝗡𝗲𝗲𝗱"! 🥳
FineVision: Open Data Is All You Need (2510.17269)

If you've ever trained a VLM, you know this problem: nobody shares their data mixtures. It's a black box, making replicating SOTA work impossible.
We wanted to change that.

FineVision unifies 200 sources into 24 million samples. With 17.3 million images and 9.5 billion answer tokens, it's the largest open resource of its kind.

In the paper, we share how we built it:
🔍 finding and cleaning data at scale
🧹 removing excessive duplicates across sources
🤗 decontaminating against 66 public benchmarks

My favorite part is Figure 6 (in the video!). It's our visual diversity analysis. It shows that FineVision isn't just bigger; it's more balanced and conceptually richer than other open datasets.
NVIDIA's Eagle 2 paper highlighted just how critical this visual diversity is, and our results confirm it: models trained on FineVision consistently outperform those trained on any other open dataset on 11 benchmarks!

🎉 To celebrate the paper, I’m also releasing a concatenated and shuffled version of the full dataset! 👉HuggingFaceM4/FineVision_full_shuffled

It’s ready to stream, so you can start training your own models right away:

from datasets import load_dataset
d = load_dataset("HuggingFaceM4/FineVision_full_shuffled", split="train", streaming=True)
print(next(iter(d)))

A big shoutout to the first authors: Luis Wiedmann and Orr Zohar. They are rockstars!

reactedto paulml's post with 🔥 6 months ago

Post

3692

Qwen3-VL-4B is incredibly easy to fine-tune!
We've trained the first DSE model based on this model, and it's already performing at the same level as Jina v4!

While Jina Embeddings v4 is built on Qwen2.5-VL-3B (which has a non-commercial license), our model is based on Qwen3-VL-4B and released under Apache 2.0—making it fully commercially permissive.

Check out our DSE model here:
racineai/QwenAmann-4B-dse

reactedto branikita's post with 🚀 6 months ago

Post

2598

With

Robonine team we released an open-source 3D-printed parallel gripper designed for robotics applications, compatible with popular budget servos like Feetech STS3215 and Waveshare ST3215.

This precision gripper offers parallel jaw movement, real-time monitoring, and positioning accuracy of ±0.1°, making it ideal for both robotics enthusiasts and professionals. Complete build cost: Just $69.45–$74.45, with all components available for purchase on Amazon. Direct links are provided in the Bill of Materials on GitHub.

Check out the project on github: https://github.com/roboninecom/3D-Printed-Parallel-Gripper-for-Robotics-Arms

We encourage you to Watch, Fork, and Star the repository to support our open-source initiative and stay updated on future developments. Your feedback is also welcome!

reactedto tomaarsen's post with 🤗🚀 6 months ago

Post

4576

🤗 Sentence Transformers is joining Hugging Face! 🤗 This formalizes the existing maintenance structure, as I've personally led the project for the past two years on behalf of Hugging Face! Details:

Today, the Ubiquitous Knowledge Processing (UKP) Lab is transferring the project to Hugging Face. Sentence Transformers will remain a community-driven, open-source project, with the same open-source license (Apache 2.0) as before. Contributions from researchers, developers, and enthusiasts are welcome and encouraged. The project will continue to prioritize transparency, collaboration, and broad accessibility.

Read our full announcement for more details and quotes from UKP and Hugging Face leadership: https://huggingface.co/blog/sentence-transformers-joins-hf

We see an increasing wish from companies to move from large LLM APIs to local models for better control and privacy, reflected in the library's growth: in just the last 30 days, Sentence Transformer models have been downloaded >270 million times, second only to transformers.

I would like to thank the UKP Lab, and especially Nils Reimers and Iryna Gurevych, both for their dedication to the project and for their trust in myself, both now and two years ago. Back then, neither of you knew me well, yet you trusted me to take the project to new heights. That choice ended up being very valuable for the embedding & Information Retrieval community, and I think this choice of granting Hugging Face stewardship will be similarly successful.

I'm very excited about the future of the project, and for the world of embeddings and retrieval at large!

1 reply

reactedto Molbap's post with ❤️🔥 6 months ago

Post

3473

🚀 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

reactedto onekq's post with 👍 7 months ago

Post

2371

So 🐋DeepSeek🐋 hits the mainstream media. But it has been a star in our little cult for at least 6 months. Its meteoric success is not overnight, but two years in the making.

To learn their history, just look at their 🤗 repo

deepseek-ai

* End of 2023, they launched the first model (pretrained by themselves) following Llama 2 architecture
* June 2024, v2 (MoE architecture) surpassed Gemini 1.5, but behind Mistral
* September, v2.5 surpassed GPT 4o mini
* December, v3 surpassed GPT 4o
* Now R1 surpassed o1

Most importantly, if you think DeepSeek success is singular and unrivaled, that's WRONG. The following models are also near or equal the o1 bar.

* Minimax-01
* Kimi k1.5
* Doubao 1.5 pro

1 reply

reactedto sergiopaniego's post with 🔥 7 months ago

Post

4360

gpt-oss was possible thanks to new engineering efforts in 🤗 transformers. We just dropped a blog covering them:

- Kernels from the Hub
- MXFP4 Quantization
- Tensor & Expert Parallelism
- Dynamic Sliding Window & Cache
- Continuous Batching & Paged Attention

Grab a coffee & dive in! ☕️

https://huggingface.co/blog/faster-transformers

reactedto ArthurZ's post with 🔥 8 months ago

Post

5995

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! 🔥

reactedto sergiopaniego's post with 🚀 9 months ago

Post

2037

Updated my HF Space for vibe testing smol VLMs on object detection, visual grounding, keypoint detection & counting! 👓

🆕 Compare Qwen2.5 VL 3B vs Moondream 2B side-by-side with annotated images & text outputs.

Try examples or test your own images! 🏃

📱Space: sergiopaniego/vlm_object_understanding

reactedto yeonseok-zeticai's post with 🔥 10 months ago

Post

3221

🚀 Real-Time On-Device AI Agent with Polaris-4B — Run It Yourself, No Cloud, No Cost

We just deployed a real-time on-device AI agent using the Polaris-4B-Preview model — one of the top-performing <6B open LLMs on Hugging Face.

📱 What’s remarkable?
This model runs entirely on a mobile device, without cloud, and without any manual optimization. It was built using ZETIC.MLange, and the best part?

➡️ It’s totally automated, free to use, and anyone can do it.
You don’t need to write deployment code, tweak backends, or touch device-specific SDKs. Just upload your model — and ZETIC.MLange handles the rest.

🧠 About the Model
- Model: Polaris-4B-Preview
- Size: ~4B parameters
- Ranking: Top 3 on Hugging Face LLM Leaderboard (<6B)
- Tokenizer: Token-incremental inference supported
- Modifications: None — stock weights, just optimized for mobile

⚙️ What ZETIC.MLange Does
ZETIC.MLange is a fully automated deployment framework for On-Device AI, built for AI engineers who want to focus on models — not infrastructure.

Here’s what it does in minutes:
- 📊 Analyzes model structure
- ⚙️ Converts to mobile-optimized format (e.g., GGUF, ONNX)
- 📦 Generates a runnable runtime environment with pre/post-processing
- 📱 Targets real mobile hardware (CPU, GPU, NPU — including Qualcomm, MediaTek, Apple)
- 🎯 Gives you a downloadable SDK or mobile app component — ready to run
And yes — this is available now, for free, at https://mlange.zetic.ai

🧪 For AI Engineers Like You, If you want to:
- Test LLMs directly on-device
- Run models offline with no latency
- Avoid cloud GPU costs
- Deploy to mobile without writing app-side inference code

Then this is your moment. You can do exactly what we did, using your own models — all in a few clicks.

🎯 Start here → https://mlange.zetic.ai

📬 Want to try Polaris-4B on your own app? contact@zetic.ai, or just visit https://mlange.zetic.ai , it is opened as free!

Great work @Chancy , @Zhihui , @tobiaslee !

reactedto pagezyhf's post with 🔥 10 months ago

Post

3272

Hackathons in Paris on July 5th and 6th!

Hugging Face just wrapped 4 months of deep work with AMD to push kernel-level optimization on their MI300X GPUs. Now, it's time to share everything we learned.

Join us in Paris at STATION F for a hands-on weekend of workshops and a hackathon focused on making open-source LLMs faster and more efficient on AMD.

Prizes, amazing host speakers, ... if you want more details, navigate to https://lu.ma/fmvdjmur!

2 replies

Pedro Cuenca PRO

AI & ML interests

Recent Activity

Organizations

pcuenq's activity