Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up

All HF Hub posts

SeaWolf-AIΒ 
posted an update 2 days ago
view post
Post
4004
πŸ”₯ 128 Blackwell GPUs β€” Thank You, Hugging Face

I've been awarded 128 NVIDIA Blackwell GPUs through NIPA (Korea's National IT Industry Promotion Agency). Sharing this here first β€” because Hugging Face is where it all started.

I design LLM architectures from scratch. HF was my lab β€” dissecting Transformers internals, analyzing thousands of checkpoints, iterating on Spaces with global feedback.

Our FINAL Bench reached #5 globally in HF dataset popularity, and this research is exactly what earned the GPU grant.
πŸ‘‰ FINAL-Bench/Leaderboard

These 128 Blackwells will scale AETHER-Net β€” our Proto-AGI architecture (Emergence Engine Β· Meta-Cognition Β· SLAI Β· Multi-Intelligence Β· Synergy & Critique) β€” validated at 0.8B with MoE expansion to 2.1B params. Next stop: 166B.

People I must thank:

@John6666 β€” Guardian of this ecosystem. Never misses a forum question, interested in every project, active 24/7. I've genuinely wondered if you're a machine. Remarkable.

@bartowski β€” Master of quantization. The hidden infrastructure of open-source LLM. Countless experiments possible thanks to you.

@SaylorTwift β€” You see what others miss. Insight that cuts to the essence. Deep respect.

My promise: AETHER-Net design docs, training recipes, checkpoints, and failure logs β€” all shared here openly.

πŸ€— Thank you, Hugging Face. Let's turn the next page together. πŸš€

vidraft Β· VIDRAFT
#OpenScience #HuggingFace #ProtoAGI #AETHER #LLMArchitecture #Blackwell #NIPA
  • 7 replies
Β·
ArtelTalebΒ 
posted an update 1 day ago
view post
Post
1991
🎡 MP3 Player - Drop your music, hit play. No install

MP3 Player - brings that energy back - straight in your browser.

- Drop your files - MP3, WAV, FLAC, AAC, OGG, AIFF, WMA β€” it reads them all
- Build your playlist - add tracks one by one or batch-load a whole folder
- Retro LCD display - scrolling track info, elapsed time, the full throwback
- Full controls - play, pause, skip, shuffle, repeat
- Mobile-first - big tactile buttons, works on phone like an iPod in your pocket

No install. No GPU needed on your end. Just upload and play.

πŸ‘‰ ArtelTaleb/mp3-player

alibidaranΒ 
posted an update 2 days ago
view post
Post
3867
With the release of Gemma 4, I launched a new Space called MEDPAI β€” a medical imaging analysis tool that combines object detection with multimodal AI.
Here's how it works:

Upload a CT scan or X-ray
Computer vision models detect and annotate findings
Gemma 4 33B generates a report or answers your questions about the image

Currently available detectors: dental analysis and bone fracture detection.
More models are in the pipeline β€” follow the Space to stay updated!
alibidaran/MEDPAI
  • 2 replies
Β·
ShrijanagainΒ 
posted an update 1 day ago
view post
Post
2256
sKT-Ai-Labs


Join fast we will soon published tokens and all join and get started because we will soon off join request button if you want you can join fast guys
  • 1 reply
Β·
allisonandreyevΒ 
posted an update 1 day ago
view post
Post
1037
ConfCrawler πŸ•·οΈ β€” never miss a conference deadline again

Keeping track of submission deadlines across CV, NLP, robotics, and ML conferences is a mess. ConfCrawler aggregates them in one place so you can actually plan your research calendar.

What's in it:
- Deadlines for major conferences (CVPR, ICCV, NeurIPS, ICRA, ACL, etc.)
- Updated regularly
- Filterable by field / month

Built this out of personal frustration while juggling multiple submission cycles. Hope it saves someone else the tab-hoarding.
πŸ”— https://confcrawler.vercel.app/
feedback welcome β€” open to adding more conferences if yours isn't listed!
danielhanchenΒ 
posted an update 3 days ago
shriarul5273Β 
posted an update 4 days ago
view post
Post
2250
πŸ” One API. 12 model families. 28 variants. Why depth_estimation makes depth research easier

Switching between depth models usually means rewriting preprocessing, adapting outputs, and dealing with different codebases.

depth_estimation removes that friction.

With the same interface, you can work with:
🌊 Depth Anything
🍎 DepthPro
🧭 MiDaS
πŸ“ ZoeDepth
🧩 MoGe
πŸ›°οΈ VGGT / OmniVGGT
and more

Change one model string, keep the rest of your workflow the same.

That makes it much easier to:
βš–οΈ compare models fairly
πŸ§ͺ prototype quickly
πŸ“ˆ benchmark consistently
πŸ› οΈ build reusable depth pipelines

GitHub: https://github.com/shriarul5273/depth_estimation

#depthestimation #research #computervision #python #machinelearning #opensource #pytorch
ArtelTalebΒ 
posted an update about 5 hours ago
view post
Post
40
HELLO 3D WORLD !

What if you could control a 3D model just by talking to it?

Not clicking. Not dragging sliders. Not writing animation code.
Just… describing what you want.

"Rotate slowly on the Y axis."
"Move forward, don't stop."
"Scale up, then reset."

That's the core idea behind Hello 3D World - a space I've been building
as an open experiment.
───────────────────────────── Here's how it works:

You load a 3D model. You describe it to the LLM
("this is a robot", "this is a hot air balloon").
Then you type a natural language command.

The LLM β€” Qwen 72B, Llama 3, or Mistral - reads your intent
and outputs a JSON action: rotate, move, scale, loop, reset.
The 3D scene executes it instantly.

One model. One prompt. One action.

─────────────────────────────

Why build this?

I'm genuinely curious where the limit is.

Today it's simple geometric commands. But what happens when
the model understands context? When it knows the object has
legs, or wings, or a cockpit? When it can choreograph a sequence
from a single sentence?

Maybe this becomes a prototyping tool for robotics.
Maybe a no-code animation layer for game dev.
Maybe something I haven't imagined yet.

That's why I'm keeping it open β€” I want to see what
other people make it do.
─────────────────────────────

The space includes:

β†’ DR8V Robot + Red Balloon (more models coming)
β†’ 5 lighting modes: TRON, Studio, Neon, Cel, Cartoon
β†’ Import your own GLB / OBJ / FBX
β†’ Built-in screen recorder
β†’ Powered by open LLMs β€” bring your own HF token

Record your best sequences and share them in the comments.
I want to see what this thing can do in other hands.

πŸ”— ArtelTaleb/hello-3d-world
BilsΒ 
posted an update about 12 hours ago
view post
Post
49
Avatars are everywhere, but here is the reality behind full-system marketing automation. πŸš€
Many see "Madame AI" simply as an AI news presenter. She is far deeper than that. Madame AI is a Real-time Agentic AI Assistant we developed to orchestrate entire workflows for marketing and professional media. She manages UGC (User-Generated Content), understands marketing system automation intuitively, and handles complex media tasks.
We have solved the character consistency and high production cost bottlenecks that traditionally required immense training and time. By precisely orchestrating every computational step behind videos and branded designs, we have fully automated the pipeline and significantly reduced costs.
This capability is built on our extensive experience managing large-scale automation projects with complex requirement documentation (PRD).
Grabclip is our public portal and the practical result of that journey. It is the interface where "Madame AI" acts as the intelligent engine.
We have spent three years building this pipeline with a clear goal: a 100% local, end-to-end solution that operates despite external restrictions.
See the live example on YouTube (our fast-paced AI news podcast with Madame AI) and try the automation portal yourselfπŸ‘‡
πŸ“Ί The Playlist: https://www.youtube.com/playlist?list=PLwEbW4bdYBSCVSziFfJYq4zXop_cyHquO
🌐 Our Portal (Grabclip) β€” The first practical step in our pipeline: https://grabclip.bilsimaging.com/
hashtag#AgenticAI hashtag#VirtualInfluencer hashtag#FutureOfWork hashtag#GenerativeAI hashtag#TunisiaTech hashtag#MarketingAutomation hashtag#100PercentLocal hashtag#OSMedia hashtag#Grabclip hashtag#RealTimeAssistant hashtag#UGC hashtag#ProfessionalMedia hashtag#TunisiaAI
prabhatkrΒ 
posted an update 1 day ago
view post
Post
93
Why did FastMemory achieve 100% accuracy at 10 million tokens while the SOTA is stalling at 64%?

It’s not because we have a better "retriever." It’s because we changed the Topology of Truth.

Standard RAG treats your data like a pile of leaves. You search for a leaf, and you hope you find the right one. As the pile grows to 10 million leaves, you inevitably fail.

FastMemory treats your data like a Building.

Topological Isolation: We use Rust-driven Louvain clustering to atomize text into "Logic Rooms."
Crystalline Grounding: Facts don't "decay" in our context; they are locked into a deterministic graph.
Sub-Second O(1) Routing: We don't "search" the haystack; we navigate the floor plan.
If your AI is mission-critical, "mostly right" is a liability. It’s time to move beyond the RAG pile and into the topological foundation.

Verify Yourself: fastbuilderai/fastmemory-supremacy-benchmarks

#MachineLearning #GraphAI #LouvainClustering #FastBuilder #EngineeringExcellence