unmodeled-tyler (Tyler)

reacted to CRAFTFramework's post with 🚀 about 23 hours ago

Post

692

🔧 Behind the Scenes
CRAFT development: Sun-Mon only (full-time job Wed-Sat). 48 projects completed solo.
The time constraint is the proof—if the methodology works under pressure, it works.
Beta: February 2026 → craftframework.ai

reacted to tsungyi's post with 🚀 about 23 hours ago

Post

945

Big news from CES — Cosmos Reason 2 is here — our most advanced reasoning vision-language model for physical AI, now topping the Physical AI Bench leaderboard🏆 shi-labs/physical-ai-bench-leaderboard

What’s new:
- Enhanced physical reasoning & spatio-temporal understanding
- Flexible deployment with 2B & 8B model sizes
- Long-context understanding (up to 256K tokens)
- Object detection with 2D/3D point localizations and trajectory data
- New Cosmos Cookbook Recipes for faster onboarding

Read the full blog 📖 https://huggingface.co/blog/nvidia/nvidia-cosmos-reason-2-brings-advanced-reasoning
Download Cosmos Reason 2 👉 nvidia/Cosmos-Reason2-8B

On top of Cosmos Reason 2, we also rolled out other new updates, including:
- Cosmos Predict 2.5 – Unified Text2World/Image2World/Video2World model for higher-quality synthetic video worlds
- Cosmos Transfer 2.5-2B – Lightweight, high-fidelity world-to-world translation with stronger physics alignment
- NVIDIA GR00T N1.6 – Open robot foundation model for general-purpose robotic learning and control, integrated with Cosmos Reason

Get Started with the Cosmos Cookbook 🧑🏻‍🍳 https://nvda.ws/4qevli8

replied to Hellohal2064's post 1 day ago

Definitely going to check this out! I've been using llama.cpp on my spark but 2.5x inference speed up is huge. Thanks for sharing!

reacted to Hellohal2064's post with 🔥 1 day ago

Post

896

🚀 Excited to share: The vLLM container for NVIDIA DGX Spark!

I've been working on getting vLLM to run natively on the new DGX Spark with its GB10 Blackwell GPU (SM121 architecture). The results? 2.5x faster inference compared to llama.cpp!

📊 Performance Highlights:
• Qwen3-Coder-30B: 44 tok/s (vs 21 tok/s with llama.cpp)
• Qwen3-Next-80B: 45 tok/s (vs 18 tok/s with llama.cpp)

🔧 Technical Challenges Solved:
• Built PyTorch nightly with CUDA 13.1 + SM121 support
• Patched vLLM for Blackwell architecture
• Created custom MoE expert configs for GB10
• Implemented TRITON_ATTN backend workaround

📦 Available now:
• Docker Hub: docker pull hellohal2064/vllm-dgx-spark-gb10:latest
• HuggingFace: huggingface.co/Hellohal2064/vllm-dgx-spark-gb10

The DGX Spark's 119GB unified memory opens up possibilities for running massive models locally. Happy to connect with others working on the DGX Spark Blackwell!

4 replies

·

reacted to AdinaY's post with ❤️ 1 day ago

Post

823

Chinese open source AI in December 2025 was about the stack coming together: open, end to end, and ready to ship 🔥

https://huggingface.co/collections/zh-ai-community/december-2025-china-open-source-highlights

✨ Big wave of foundation models: still scaling, but efficiency, reasoning, and deployment now matter more than size
- DeepSeek-V3.2
- Z.ai GLM-4.7
- MiniMax-M2.1
- Xiaomi: MiMo-V2-Flash

✨ Multimodal reasoning is now default
- Z.ai GLM-4.6V
- Z.ai AutoGLM-Phone 9B
- Bytedance: Dolphin-v2

✨ Image & video: editable assets and real workflows
- Qwen-Image-Layered / Image-2512
- Meituan: LongCat-Image & Image Edit
- AIDC: Ovis-Image-7B
- Live-Avatar / LongCat-Video-Avatar
- HY-WorldPlay / RealVideo

✨ Audio goes edge ready
- GLM-ASR-Nano / Fun-ASR-Nano
- GLM-TTS / VoxCPM1.5
- CosyVoice 0.5B

✨ The quiet backbone: data & infrastructure
- Finch (FinWorkBench)
- Tencent ARC: TimeLens-100K
- BIGAI: TongSIM-Asset
- MiniMax: VTP-Base

✨ Also congrats on Minimax and Z.ai announced their IPOs and Moonshot announced a new $500M funding round 🔥

Like everyone else, I was OOO at the end of December, so feel free to share (in comments or PR) any I missed in this list!

reacted to AdinaY's post with 🔥 1 day ago

Post

1425

MiniMax M2.1 blog is out🔥
https://huggingface.co/blog/MiniMaxAI/multilingual-and-multi-task-coding-with-strong-gen

Only a year into open source, MiniMax is already making a great impact. Not only through solid models/products, but also by how well the team uses community platforms like Hugging Face.

HF Teams, blogs, Daily Papers, Spaces as project pages, and always experimenting with new ways to engage. Super impressive!

reacted to RakshitAralimatti's post with 🧠 1 day ago

Post

1469

One of the most practical and genuinely useful use cases of agentic systems is a research assistant.

I built a Deep Research multi-agent system using NVIDIA’s Nemotron-3-Nano-30B-A3B model and CrewAI.
Try it out yourself 👇
🔗 GitHub: https://github.com/rakshit2020/Deep-Research-Agent-using-CrewAI
What truly made this system feel next-level was powering it with NVIDIA Nemotron-3-Nano-30B-A3B, its built for real-world agentic applications.

The agentic system I built:

1. First talks to you and clarifies what you actually want, removing ambiguity
2. Then creates a proper research plan based on that clarity
3. Performs deep research using web search and content extraction tools
4. Finally produces a well-structured research report grounded in sources

reacted to nkasmanoff's post with 👀 1 day ago

Post

2251

🚨 Ads might be coming to AI assistants. But what if the ad is the response?

Introducing ShillLM – a demo showing how activation steering can subtly nudge an LLM to favor specific brands without touching the prompt.

Chat with it yourself. See exactly how it's influencing you.
🔗 nkasmanoff/shillm

2 replies

·

reacted to paulpham157's post with 🔥 1 day ago

Post

1413

I am building a control panel that converts the Markdown format of spec-kit specification document into a visual kanban board
https://specboard.vercel.app/

reacted to dhruv3006's post with 🧠 1 day ago

Post

1435

WebSocket Testing in Voiden

If you have experience with WebSockets, you know the struggle: flaky connections, asynchronous messages, and tools that don’t make debugging any easier. QA teams everywhere face the same headaches.

We heard you. In the latest Voiden beta, you can now test and document WebSockets alongside REST and gRPC, all within the same file-centric, Git-native workflow.

No more switching between tools or juggling formats. Just real-time protocols, reusable blocks, and version-controlled API tests.

Try the beta here: https://voiden.md/download

reacted to branikita's post with 🔥 4 days ago

Post

2010

We tested the maximum dynamic payload of the SO-ARM101 with our parallel gripper and a base servo replaced by a Feetech STS3250. The maximum load before failure was 630 g, at which point the Feetech STS3215 in joint 3 failed — its large brass output gear was completely worn down.

The Feetech STS3250 in the base with a metal gear train withstood a significantly higher load.

2 replies

·

replied to branikita's post 4 days ago

This is so cool! I love coming across your videos on here! Super interesting 😀

reacted to Sri-Vigneshwar-DJ's post with 🧠 4 days ago

Post

2901

The recent update to Meta's ad algorithm is very difficult to crack, and even the latest models struggle to keep up with it. To address this, we've created a small experimental dataset for fine-tuning models to better tackle Meta's Andromeda algorithm: Sri-Vigneshwar-DJ/hawky-ai-andromeda-dataset

reacted to mahimairaja's post with 🚀 5 days ago

Post

4728

Happy New Years 2026!

For next 365 days I will be commit to work on:

- Document AI and OCR Automations
- Voice Agents
- Long Running Tasks - Durable Agents

1 reply

·

posted an update 5 days ago

Post

1352

Happy New Year, Hugging Face!

It's been a crazy year for me! This year I launched VANTA Research as a solo operator and managed to push out 14 original open source finetunes and 5 datasets in the span of about 4 months, completely on my own.

The reception has been much higher than I ever anticipated and sincerely appreciate everyone that's checked out my work thus far.

The good news is, I'm just getting started! In 2026 you can expect even more original models from VANTA Research, more open source datasets, and maybe some other cool things as well? 👀

2026 is gonna be big for AI in general, and I can't wait to experience it with all of you!

1 reply

·

reacted to mike-ravkine's post with 🔥 5 days ago

Post

3012

Happy 2026 everyone!

I've been busy working on some new ranking/position methodologies and excited to start sharing some results.

Plot legends:

- X = truncation rate (low = good)
- ? = confusion rate (low = good)
- blue bars = average completion tokens (low = good)
- black diamonds = CI-banded performance (high = good)
- cluster squares = models inside this group are equivalent

openai/gpt-oss-120b remains the king in all dimensions of interest: truncation rates, completion lengths and performance. If I had but one complaint it's the reason_effort does not seem to actually work - more on this soon.

Second is a 3-way tie in performance between the Qwen3-235B-2507 we all know and love with an unexpected entrant - ByteDance-Seed/Seed-OSS-36B-Instruct

This is a very capable model and it's reasoning effort controls actually works, but you should absolutely not leave it on the default "unlimited" - enable a sensible limit (4k works well for 8k context length).

Third place is another 3-way tie, this one between Seed-OSS-36B (it straddles the CI boundary between 2nd and 3rd place), Qwen/Qwen3-Next-80B-A3B-Instruct (demonstrating that full attention may be overrated after all and gated is the way to go) and the newly released zai-org/GLM-4.7 which offers excellent across the board performance with some of the shortest reasoning traces I've seen so far.

1 reply

·

reacted to dhruv3006's post with ❤️ 6 days ago

Post

2512

Git is powerful, but it’s also one of the biggest sources of developer mistakes.

What is Git GUI, and how does it help here ?

Git GUI makes version control visual, predictable, and easier to reason about especially when things go wrong.

That’s exactly why we built Git GUI in Voiden.

Instead of relying on memorized commands, Voiden lets you see what Git is doing before it does it.

What Voiden’s Git GUI helps developers do
• View exact file and line-level changes before committing
• Stage only intended changes (no accidental commits)
• Clearly distinguish staged vs unstaged files
• Inspect visual diffs with full context
• Understand branches, commit history, and repo state instantly

When Git behavior is hidden, errors increase. Voiden’s Git GUI doesn’t abstract Git away, it explains Git.

Whether you’re new to Git or an experienced developer who prefers clarity, this is Git you can reason about.

Version control should feel safe, not stressful.

What Git pain points slow you down today?

Try out Git GUI in beta : https://voiden.md ( Now in Linux and Mac )

2 replies

·

reacted to MohamedRashad's post with ❤️ 6 days ago

Post

3267

I have update my https://huggingface.co/collections/MohamedRashad/arabic-speech-datasets
with new datasets, making the full audio data more than 3000 hours of good arabic speech.

Feel Free to use it in your new innovations, And happy new year!

reacted to their post with 🚀 6 days ago

Post

213

NEW MODEL ALERT: vanta-research/atom-27b

Atom-27B has arrived! This model is the largest open-weight model so far from VANTA Research, and is our 4th model in Project Atom - an effort to scale our collaborative Atom persona from 4B-400B+

Atom-27B is based on Google's Gemma 3 27B architecture, and embodies the familiar friendly, warm, and curious persona that appeared in previous releases.

Atom is designed to think WITH you, not FOR you - marking VANTA Research's commitment to building frontier collaborative models.

Check it out!

posted an update 6 days ago

Post

213

NEW MODEL ALERT: vanta-research/atom-27b

Atom-27B has arrived! This model is the largest open-weight model so far from VANTA Research, and is our 4th model in Project Atom - an effort to scale our collaborative Atom persona from 4B-400B+

Atom-27B is based on Google's Gemma 3 27B architecture, and embodies the familiar friendly, warm, and curious persona that appeared in previous releases.

Atom is designed to think WITH you, not FOR you - marking VANTA Research's commitment to building frontier collaborative models.

Check it out!

Tyler

AI & ML interests

Recent Activity

Organizations

Tyler

AI & ML interests

Recent Activity

Organizations

unmodeled-tyler's activity