John6666 (John Smith)

reacted to nroggendorff's post with 🤗 1 day ago

Post

1832

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?

reacted to nicolay-r's post with ❤️ 1 day ago

Post

1152

📢 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

reacted to codelion's post with 🔥 1 day ago

Post

1598

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

reacted to FlameF0X's post with 👍 1 day ago

Post

1463

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

·

reacted to kanaria007's post with 👀 1 day ago

Post

168

✅ New Article on Hugging Face: Structure Governing Structure — The Meta-Orchestration Layer for Advanced AI Reasoning

Title:
🧠 Understanding the Superstructure Protocol: Meta-Layers for Orchestrated Cognitive Integrity
🔗 https://huggingface.co/blog/kanaria007/understanding-the-superstructure-protocol

---

Summary:
What if an AI could reason not just with structure — but about structure?

This article introduces the *Superstructure Protocol*, a meta-governance layer that enables AI to orchestrate multiple cognitive protocols *recursively and coherently*.
It doesn’t generate outputs directly — it governs how reasoning happens.

Think of it as a cognitive operating system for protocol-level decision-making.

---

Why It Matters:
AGI systems don’t reason in a vacuum.
They jump, reflect, remember, rollback, and ethically restrain themselves — often simultaneously.
Without *meta-layer coordination*, these forces compete. With it, they integrate.

The Superstructure Protocol ensures:

• Coordinated protocol activation
• Recursive contradiction containment
• Structural coherence across memory, ethics, and abstraction
• Pattern-aware protocol meta-learning

---

Core Modules:
• *Activation Orchestration* – Manages when/why protocols engage
• *Recursive Stability Layer* – Prevents runaway contradictions
• *Cross-Protocol Integrity Monitor* – Ensures coherent outputs
• *Meta-Pattern Tracker* – Enables protocol-level self-learning

---

📈 *This is not just protocol chaining.*
It’s structural reflexivity at the system level.

---

Relevant For:
• Researchers building multi-layered reasoning architectures
• Developers designing AI agents with protocol coordination needs
• Anyone interested in how AGI governs *how* it governs

---

🧠 Protocol Dataset: kanaria007/agi-structural-intelligence-protocols

---

*This isn’t execution logic.*
It’s orchestration logic — for cognitive systems that coordinate, adapt, and align from the top down.

reacted to Blazgo's post with 👀 2 days ago

Post

2301

🚀 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

5 replies

·

reacted to Gil85's post with 👀 2 days ago

Post

260

Hi ,
I subscribed to the professional version for 9 dollars and I do not have access to the site and application builder which constantly redirects me to a request for payment for the Pro version.

1 reply

·

replied to Gil85's post 2 days ago

Try contact support: [email protected]

reacted to DualityAI-RebekahBogdanoff's post with 🚀 2 days ago

Post

1957

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

reacted to Wauplin's post with 🤗🔥 2 days ago

Post

2274

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

reacted to BrigitteTousi's post with 🤗 2 days ago

Post

273

This is what Hugging Face is all about. We want everyone, hobbyists, researchers and industry alike, to be able to contribute to AI because everyone is affected by it. Kudos to HF's @irenesolaiman for spreading the word!🔥🤗

reacted to AdinaY's post with 🔥 2 days ago

Post

1579

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 🙌

reacted to AdinaY's post with 🔥 2 days ago

Post

233

Ming-lite-omni v1.5 🔥 upgrade version of Ming-lite-omni, by AntGroup.

inclusionAI/Ming-Lite-Omni-1.5

✨ 20.3B / 3B active - MoE
✨ SOTA video understanding via 3D MRoPE + curriculum learning
✨ Real time speech synthesis + dialect support
✨ Enhanced multimodal generation with ID & scene consistency

reacted to KaraKaraWitch's post with ❤️ 2 days ago

Post

166

What if LLMs used thinking emojis to develop their state?

:blob_think: Normal Thinking
:thinkies: Casual Thinking
:Thonk: Serious Thinking
:think_bold: Critical Thinking
:thinkspin: Research Thinking
:thinkgod: Deep Research Thinking

The last 2 are gifs. But the upload doesn't render them :)

(Credits: SwayStar123 on EAI suggested it to be a range selector, Original base idea was from me)

1 reply

·

reacted to prithivMLmods's post with ❤️ 2 days ago

Post

2137

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. !!

reacted to georgewritescode's post with 👍 2 days ago

Post

973

🎵 Announcing Artificial Analysis Music Arena! Vote for songs generated by leading music models across genres from pop to metal to rock & more

Key details:
🏁 Participate in Music Arena and after a day of voting we’ll unveil the world’s first public ranking of AI music models.

✨ Currently featuring models from Suno, Riffusion, Meta, Google, udio and Stability AI!

🎤 Support for both a vocals mode and an instrumental mode

🎸 A diverse array of prompts from genres including pop, RnB, metal, rock, classical, jazz, and more

Check it out here:
ArtificialAnalysis/Music-Arena-Leaderboard

reacted to AdinaY's post with 🔥 2 days ago

Post

1468

Qwen is on fire this week 🔥
They just released Qwen3-MT 🌍 a translation model supports 92 languages.

Demo is available on the hub.
Qwen/Qwen3-MT-Demo

✨ Highly Customizable: Supports custom terms, domain prompts, and translation memory for accurate, context-aware results.
✨ Fast and affordable: $0.5 per million tokens.

reacted to DualityAI-RebekahBogdanoff's post with 🔥 2 days ago

Post

773

Excuse the lag, it's from the real-time inference from the webcam 👀 . Did you know that YOLOv11 added Streamlit for live object detection straight from your webcam?

📸 Learn about live inference with YOLOv11 and the Streamlit Application -
https://docs.ultralytics.com/guides/streamlit-live-inference/

🥫 Join the mentioned Kaggle competition here -
https://www.kaggle.com/competitions/multi-class-object-detection-challenge/overview

👀 Checkout Duality AI -
https://www.duality.ai/?utm_source=hf&utm_medium=post&utm_campaign=video

🫡 Checkout 3LC.AI -
https://3lc.ai/

reacted to Xenova's post with 🔥 2 days ago

Post

1748

Introducing Voxtral WebGPU: State-of-the-art audio transcription directly in your browser! 🤯
🗣️ Transcribe videos, meeting notes, songs and more
🔐 Runs on-device, meaning no data is sent to a server
🌎 Multilingual (8 languages)
🤗 Completely free (forever) & open source

That's right, we're running Mistral's new Voxtral-Mini-3B model 100% locally in-browser on WebGPU, powered by Transformers.js and ONNX Runtime Web! 🔥

Try it out yourself! 👇
webml-community/Voxtral-WebGPU

John Smith PRO

AI & ML interests

Recent Activity

Organizations

John Smith PRO

AI & ML interests

Recent Activity

Organizations

John6666's activity