Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up

All HF Hub posts
Wauplin 
posted an update 2 days ago
view post
Post
2226
Say hello to hf: a faster, friendlier Hugging Face CLI ✨

We are glad to announce a long-awaited quality-of-life improvement: the Hugging Face CLI has been officially renamed from huggingface-cli to hf!

So... why this change?

Typing huggingface-cli constantly gets old fast. More importantly, the CLI’s command structure became messy as new features were added over time (upload, download, cache management, repo management, etc.). Renaming the CLI is a chance to reorganize commands into a clearer, more consistent format.

We decided not to reinvent the wheel and instead follow a well-known CLI pattern: hf <resource> <action>. Isn't hf auth login easier to type and remember?

The full rationale, implementation details, and migration notes are in the blog post: https://huggingface.co/blog/hf-cli
nroggendorff 
posted an update 1 day ago
view post
Post
1612
Is it possible to apply for a resources grant for a whole organization, or do you need to apply for each repo individually? I think it'd be pretty cool to have something like the discord-community org for None-yet in terms of resource allocation (multiple spaces running on cpu upgrade.

I realize the scale of the community is just a tiny bit different, and that having this for a public org (one where anyone can join) isn't super fiscally responsible, but we'll be good. I promise we will! Right, guys?
Blazgo 
posted an update 2 days ago
view post
Post
2266
🚀 Deca 3 Ultra Alpha is coming in the next 72 hours! 🚀

We're on the verge of something monumental. Right now, we're in the final stages of testing, and we're about to drop a game-changing milestone in the open-source AI community. 🎉

In just two weeks, we've managed to almost 4x the size of the largest open-source LLM at that time (and we are still 2.6x bigger than the largest LLM). This is unprecedented and a testament to the power of collaboration, innovation, and the relentless pursuit of pushing AI to its limits.

The future of open-source AI is now. Stay tuned for the release – we’re just getting started.

- Model testing finishes: 24hrs from now
- Model gets uploaded: 30hrs from now
- Related code/inference stack gets published: 70-90hrs from now
·
FlameF0X 
posted an update 1 day ago
view post
Post
1204
The development of SnowflakeCore-G1-7B-MoE. I can't say when it would be publish yet because it's big and it requires a lot of computational power.
  • 1 reply
·
prithivMLmods 
posted an update 3 days ago
view post
Post
2116
Excited to introduce the new experimental model "Qwen2.5-VL-7B-Abliterated-Caption-it", which is performing exceptionally well on image captioning tasks. This variant is specifically tailored for Abliterated Captioning and Uncensored Image Captioning. It is designed to generate highly detailed and descriptive captions across a broad range of visual categories including images with complex, sensitive, or nuanced content while handling varying aspect ratios and resolutions.🧪🤗

✨ Try the demo here : prithivMLmods/Qwen2.5-VL
✨ Qwen2.5-VL-7B-Abliterated-Caption-it : prithivMLmods/Qwen2.5-VL-7B-Abliterated-Caption-it
✨ Multimodal VLMs : prithivMLmods/multimodal-vlms-until-july25-688312e6b840e1e156f13027
✨ Multimodal Implementations : prithivMLmods/multimodal-implementations-67c9982ea04b39f0608badb0

.
.
.
To know more about it, visit the model card of the respective model. !!
codelion 
posted an update 1 day ago
view post
Post
1332
Implemented Test-Time Diffusion Deep Researcher (TTD-DR) in OptiLLM! 🚀

Just shipped a game-changing feature that turns any LLM into a powerful research agent. TTD-DR applies diffusion-inspired techniques to iteratively refine research reports while grounding them in real web sources.

How it works:
• Generates initial draft
• Identifies knowledge gaps
• Searches web for missing info
• Iteratively refines through "denoising" steps
• Produces comprehensive reports with 15-30+ sources

The magic? It works with ANY model so you can choose your favorite open-source models on HF!

Key results:
- 47 complex research queries tested
- Every report backed by real web sources
- Quality rivals human research analysts
- No more hallucinations on current events!

Try it:
pip install optillm
Then use "deep_research-your-model-name" as the model identifier

- Implementation: https://github.com/codelion/optillm/tree/main/optillm/plugins/deep_research
- Paper: https://arxiv.org/abs/2507.16075v1
- Sample reports: https://github.com/codelion/optillm/tree/main/optillm/plugins/deep_research/sample_reports

Special thanks to the TTD-DR paper authors for this brilliant approach!

#research #llm #opensource #inference
AdinaY 
posted an update 3 days ago
view post
Post
1559
Big respect to the Qwen team! They just dropped another model🔥

Qwen3-235B-A22B-Thinking-2507 🧠 new reasoning model by Qwen

Qwen/Qwen3-235B-A22B-Thinking-2507

✨ 235B total / 22B active (8 experts)
✨ 256K context window
✨ Agent-ready with tool use & <think> reasoning mode

Hope the team gets some well-deserved rest this weekend after all the massive releases 🙌
Kseniase 
posted an update about 13 hours ago
view post
Post
559
9 new policy optimization techniques

Reinforcement Learning (RL) won't stuck in the same old PPO loop - in the last two months alone, researchers have introduced a new wave of techniques, reshaping how we train and fine-tune LLMs, VLMs, and agents.

Here are 9 fresh policy optimization techniques worth knowing:

1. GSPO: Group Sequence Policy Optimization → Group Sequence Policy Optimization (2507.18071)
Shifts from token-level to sequence-level optimization, clipping, and rewarding to capture the full picture and increase stability compared to GRPO. GSPO-token variation also allows token-level fine-tuning.

2. LAPO: Length-Adaptive Policy Optimization → LAPO: Internalizing Reasoning Efficiency via Length-Adaptive Policy Optimization (2507.15758)
A two-stage RL framework that trains models to adaptively control reasoning length by learning typical solution lengths for shorter and more efficient reasoning.

3. HBPO: Hierarchical Budget Policy Optimization → Hierarchical Budget Policy Optimization for Adaptive Reasoning (2507.15844)
This one trains model to adapt reasoning depth based on problem complexity. It divides training samples into subgroups with different token budgets, using budget-aware rewards to align reasoning effort with task difficulty.

4. SOPHIA: Semi-off-policy reinforcement learning → Semi-off-Policy Reinforcement Learning for Vision-Language Slow-thinking Reasoning (2507.16814)
Combines on-policy visual understanding from the Vision Language Models (VLMs) with off-policy reasoning from an LM, assigning outcome-based rewards and propagating visual rewards backward through the reasoning steps.

5. RePO: Replay-Enhanced Policy Optimization → RePO: Replay-Enhanced Policy Optimization (2506.09340)
Introduces a replay buffer into on-policy RL for LLMs, retrieving diverse off-policy samples for each prompt to broaden the training data per prompt

Read further below ⬇️
If you like it, also subscribe to the Turing Post: https://www.turingpost.com/subscribe
  • 1 reply
·
nicolay-r 
posted an update 1 day ago
view post
Post
983
📢 For those who planning to start a PhD or research in the UK 🇬🇧 (including AI field in particular) but facing ATAS (Academic Technology Approval Scheme) issues.
Excited to share the ultimate guide for dealing with ATAS refusals and how to write effective rebuttal letters.

🎬 https://youtu.be/bfknM3n-SHs

🔍 From the video you will find:
1. Why appealing an ATAS decision matters even if your visa is approved
2. Which docments to use in understanding the principles behind sponsorship decisions
3. Key tips for proper rebuttal letter structuring
DualityAI-RebekahBogdanoff 
posted an update 2 days ago
view post
Post
1945
NEW ARTICLE: "Detecting Beyond Sight: Building AI-Enabled SAR Intelligence with Synthetic Data"

Synthetic Aperture Radar (SAR) reveals what optical sensors can’t. AI can turn that information into actionable intelligence—but only with the right training data.

In our latest blog, we explore how Falcon’s new virtual SAR sensor solves the SAR data bottleneck for AI development. As the newest addition to Falcon’s sensor library, it models radar returns with precision—including azimuth, range resolution, signal intensity, and noise. This Falcon-specific, GPU-accelerated raytraced SAR model is exposed via Falcon’s Python API, giving teams precise, control over radar wave propagation and enabling physically grounded, highly customizable, and user-friendly SAR simulation.

The result? High-fidelity, automatically labeled synthetic SAR imagery from any scenario—on demand. No custom setup. No external workflows. Just mission-ready data for building AI models across defense, disaster response, agriculture, intelligence, and beyond.

📡 Read how it works → https://huggingface.co/blog/DualityAI-RebekahBogdanoff/ai-enabled-sar-intelligence-synthetic-data

Recently active users