blog-explorers (Blog-explorers)

posted an update about 9 hours ago

Post

114

Introducing QIE-Bbox-Studio! 🔥🤗

The QIE-Bbox-Studio demo is now live — more precise and packed with more options. Users can manipulate images with object removal, design addition, and even move objects from one place to another, all in just 4-step fast inference.

🤗 Demo: prithivMLmods/QIE-Bbox-Studio
🔗 GitHub: https://github.com/PRITHIVSAKTHIUR/QIE-Bbox-Studio

🚀 Models [LoRA] :

● QIE-2511-Object-Mover-Bbox: prithivMLmods/QIE-2511-Object-Mover-Bbox
● QIE-2511-Object-Remover-Bbox-v3: prithivMLmods/QIE-2511-Object-Remover-Bbox-v3
● QIE-2511-Outfit-Design-Layout: prithivMLmods/QIE-2511-Outfit-Design-Layout
● QIE-2509-Object-Remover-Bbox-v3: prithivMLmods/QIE-2509-Object-Remover-Bbox-v3
● QIE-2509-Object-Mover-Bbox: prithivMLmods/QIE-2509-Object-Mover-Bbox

🚀 Collection:

● Qwen Image Edit [Layout Bbox]: https://huggingface.co/collections/prithivMLmods/qwen-image-edit-layout-bbox

To learn more, visit the app page or the respective model pages.

prithivMLmods

posted an update 3 days ago

Post

4902

QIE-2509-Object-Remover-Bbox-v3 is a more stable version of the Qwen Image Edit visual grounding–based object removal model. The app was previously featured in HF Spaces of the Week and is now updated with the latest Bbox-v3 LoRA adapter.

🤗 Demo: prithivMLmods/QIE-Object-Remover-Bbox
🤗 LoRA: prithivMLmods/QIE-2509-Object-Remover-Bbox-v3
🤗 Collection: https://huggingface.co/collections/prithivMLmods/qwen-image-edit-layout-bbox

To learn more, visit the app page or the respective model pages.

2 replies

·

sergiopaniego

posted an update 4 days ago

Post

260

ICYMI, great blog by @kashif and @stas on Ulysses Sequence Parallelism: train with million-token contexts

on 4×H100s: 12x longer sequences, 3.7x throughput

learn how to integrate it with Accelerate, Transformers, and TRL ⤵️
https://huggingface.co/blog/ulysses-sp

AdinaY

submitted a paper to Daily Papers 5 days ago

Training Language Models via Neural Cellular Automata

Paper • 2603.10055 • Published 8 days ago • 7

sergiopaniego

posted an update 5 days ago

Post

182

We just released a big blog surveying 16 OSS frameworks for async RL training of LLMs!

We're building a new async GRPO trainer for TRL and as first step, we needed to understand how the ecosystem solves this problem today.

The problem: in synchronous RL training, generation dominates wall-clock time. 32K-token rollouts on a 32B model take hours while training GPUs sit completely idle. With reasoning models and agentic RL making rollouts longer and more variable, this only gets worse.

The ecosystem converged on the same fix: separate inference + training onto different GPU pools, rollout buffer, and async weight sync.

We compared 16 frameworks across 7 axes: orchestration, buffer design, weight sync, staleness management, partial rollouts, LoRA, and MoE support.

This survey is step one. The async GRPO trainer for TRL is next!

https://huggingface.co/blog/async-rl-training-landscape

sergiopaniego

posted an update 6 days ago

Post

220

Nemotron 3 Super by @nvidia is here! NVIDIA's hybrid Mamba2/Transformer models are now natively supported in transformers (no trust_remote_code needed)

Fine-tune them with TRL in just a few lines of code. Notebook + script included to get started right away. goooo!

- Notebook: https://colab.research.google.com/github/huggingface/trl/blob/main/examples/notebooks/sft_nemotron_3.ipynb
- Script: https://github.com/huggingface/trl/blob/main/examples/scripts/sft_nemotron_3.py
- Collection with all the models: https://huggingface.co/collections/nvidia/nvidia-nemotron-v3

sdiazlor

posted an update 7 days ago

Post

2574

More OSS than ever with the latest pruna 0.3.2 release. It extends existing algorithm families, such as compilers, kernels, and pruners, and adds new ones, including decoders, distillers, enhancers, and recoverers. But it's not only a collection of algorithms; instead, you can easily combine them to get the biggest efficiency win.

Read the full blog here: https://huggingface.co/blog/PrunaAI/pruna-0-3-2-open-source-optimization-algorithms

AdinaY

submitted a paper to Daily Papers 9 days ago

Planning in 8 Tokens: A Compact Discrete Tokenizer for Latent World Model

Paper • 2603.05438 • Published 12 days ago • 38

prithivMLmods

posted an update 11 days ago

Post

4968

The Qwen3.5 Multimodal Understanding Demo, powered by Qwen3.5-2B, is now available on HF Spaces! It is a lightweight model designed for fast image and video reasoning. Built with Gradio, the demo showcases Image QA, Video QA, object detection, and 2D point tracking, along with real-time token streaming.

🤗 Demo: prithivMLmods/Qwen-3.5-HF-Demo
✅ Collection: https://huggingface.co/collections/prithivMLmods/multimodal-implementations
🔗 Qwen3.5-2B: Qwen/Qwen3.5-2B

To learn more, visit the app page or the respective model pages.

sergiopaniego

posted an update 14 days ago

Post

494

did you know you can train agentic models with RL deploying the environments on HF Spaces? 🤗

with TRL + OpenEnv, your training script connects to remote environments hosted as Spaces

want to train faster? → just add more Spaces (TRL handles the parallelization natively)

we used this to train a model to solve the trolley problem in CARLA. 2 HF Spaces running a full driving simulator, each on a T4 GPU

full write-up with code and results → https://huggingface.co/blog/sergiopaniego/bringing-carla-to-openenv-trl

prithivMLmods

posted an update 15 days ago

Post

3971

QIE-Object-Remover-Bbox Demo removes objects and artifacts from selected regions using bounding box grounding. Built on Qwen-Image-Edit-2509 with Rapid Diffusers acceleration, it delivers fast 4-step inference via the QIE-2509 adapter. 🤗🔥

🔗Demo Space: prithivMLmods/QIE-Object-Remover-Bbox
🔗Qwen-Image-Edit-Rapid-AIO: prithivMLmods/Qwen-Image-Edit-Rapid-AIO-V4
🔗Adapter-(LoRA): prithivMLmods/QIE-2509-Object-Remover-Bbox

🔗Collection: https://huggingface.co/collections/prithivMLmods/qwen-image-edit-layout-bbox

To learn more, visit the app page or the respective model pages.

1 reply

·

sergiopaniego

posted an update 15 days ago

Post

377

Qwen3.5 dense (smol 🤏) models just dropped

- natively multimodal
- 0.8B · 2B · 4B · 9B (+ base variants)
- 262K context extensible to 1M
- built-in thinking

fine-tune them with TRL out of the box → SFT, GRPO, DPO and more!

examples: https://huggingface.co/docs/trl/example_overview
collection: https://huggingface.co/collections/Qwen/qwen35

sergiopaniego

posted an update 19 days ago

Post

2360

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

prithivMLmods

posted an update 21 days ago

Post

2517

FireRed-Image-Edit-1.0 (Rapid) Fast Experimental Demo is Out! 🚀🤗

Demo: prithivMLmods/FireRed-Image-Edit-1.0-Fast

-> Paired the EditPlusPipeline with the Diffusers-compatible transformer weights of Rapid AIO from Qwen-Image-Edit. (experimental)
-> This fusion delivers more accurate instruction following, higher image quality, and consistent visual coherence @ 4-step fast inference.
-> Better maintains text styles with high fidelity, along with high-quality old photo restoration, enhancement, and best-in-class virtual try-on.