I also experimented with a new TruthfulQA free-generation evaluation setup.
- Responses were judged by Gemma 4 26B A4B - The judge compared generations directly against ground-truth answers - Models were evaluated in 8-bit quantized form to speed up inference
Turns out : if we predict 🌏 earth we can save a lot of time looking for interesting things and less time looking at things that we expect to see.
Sentinel-2 imagery 🛰️basically takes a long time to download towards earth. so our "near real time" systems are quite far from that in practical terms.
meanwhile , if we "predict" what we will see , based on what we do see , we can send down much less data in a timely way , and prioritize 📡earth-bound response .
I'm talking about illegal fishing , logging , mining or building in nature reserves , the more of that we predict early the more we're able to stop it on time.
since everyone liked my previous announcement post ( https://huggingface.co/posts/Tonic/338509028435394 ) so much , i'm back with more high quality proceedural datasets in the Geospacial domain for SFT training !
I’ve been working on a new mathematical approach to real-time video compositing and background removal, and I wanted to share a live demo.
Traditionally, real-time keyers either use 3D color-space bounding boxes (which struggle with semi-transparent hair and motion blur) or heavy Machine Learning models (which require massive GPU compute and often suffer from temporal "jitter" on the edges).
I wanted to see if I could solve this using purely deterministic math so it could run client-side in a standard browser.
The engine uses a custom mathematical framework I call CMT SRL SEFA. Instead of looking at raw color values or guessing semantics like an AI, it treats the video feed as complex-encoded sequences. It uses harmonic frequencies to map phase geometry and applies a "Stability Cost Function" to find the global minimum stability. In short: it isolates the foreground from the background by measuring signal complexity and structural contradictions.
Give it a try using your own messy plates and such. As I am not a VFX artist, I am curious to hear thoughts and what should be improved upon and made better
if you like it give the demo a little star and send a shoutout to : @MaxLSB@jddqd and @GAD-cell for absolutely obliterating the pareto frontier of the french language understanding .
🚀 AutoXLA - Accelerating Large Models on TPU AutoXLA is an experimental library that automates the distribution, optimization, and quantization of large language models for TPUs using PyTorch/XLA. It extends the Hugging Face Transformers interface with TPU-aware features such as automatic sharding, custom attention kernels, and quantization-aware loading, making large-scale deployment and training both simpler and faster. With quantization and Splash Attention kernels, AutoXLA achieves up to 4× speedups over standard Flash Attention implementations, significantly improving throughput for both inference and training workloads. Whether you’re experimenting with distributed setups (FSDP, 2D, or 3D sharding) or optimizing memory via LanguageModelQuantizer, AutoXLA is built to make scaling LLMs on TPU seamless. ⚠️ Note: This is an experimental repository. Expect rough edges! Please report bugs or unexpected behavior through GitHub issues. 🔗 GitHub Repository: https://github.com/Locutusque/AutoXLA
New Technique to Deeply Poison AI on Images and Prove Creative Provenance
I've developed a new method to protect creative work from unauthorized AI training. My Poisonous Shield for Images algorithm embeds a deep, removal-resistant poison into the mathematical structure of your images. It's designed to be toxic to machine learning models, achieving up to 20-348% disruption in AI training convergence in benchmark tests.
Unlike traditional watermarks, this protection survives compression and resizing and is not removed by standard tools. The technique also embeds cryptographic proof of provenance directly into the image, verifying ownership and detecting tampering.
You can see examples and learn more about how and WHY it works better than current methods:
If you are interested in using this technology to protect your work from AI training and unauthorized use, please reach out to me. It is currently in the prototype phase but fully functioning and effective. Still working on expanding it to a production-grade usable app.
This is not intended as a pure self-promotion post. I am genuinely wanting to help creators and want to gauge interest from different communities. I've spent the past year and a half building this from scratch with new math and code to try and solve this massive problem.
I’ve ported the BDH ( https://github.com/pathwaycom/bdh ) model to MLX for Apple Silicon. It’s a faithful conversion of the PyTorch version: same math, same architecture (byte-level vocab, shared weights across layers, ReLU sparsity, RoPE attention with Q=K), with MLX-friendly APIs and a detailed README explaining the few API-level differences and why results are equivalent.
Code, docs, and training script are ready to use. You may need to adjust the training script a bit to fit your own custom dataset. Only tested on M4 so far, but should work perfect for any M1/M2/M3 users out there.
I’m currently training this MLX build on my Internal Knowledge Map (IKM) dataset Severian/Internal-Knowledge-Map Training’s underway; expect a day or so before I publish weights. When it’s done, I’ll upload the checkpoint to Hugging Face for anyone to test.
🎮 Live Model Demo: Upload an Android Screenshot and instructions to see the model in action ! Tonic/l-operator-demo
Built in a garage, funded by pre-orders, no VC. Now we’re scaling to 1 k installer units.
We’re giving 50 limited-edition prototypes to investors , installers & researchers who want to co-design the sovereign smart home.
👇 Drop “EUSKERA” in the comments if you want an invite, tag a friend who still thinks Alexa is “convenient,” and smash ♥️ if AI should belong to people - not servers.
Just wanted to annouce 🏭SmolFactory : it's the quickest and best way to finetune SmolLM3 and GPT-OSS-20B on huggingface !
Basicaly it's an app you can run on huggingface by duplicating the space and running your training directly on huggingface GPUs .
It will help you basically select datasets and models, fine tune your model , make an experiment tracker you can use on your mobile phone , push all your model card and even automatically make a demo for you on huggingface so you can directly test it out when it's done !
🌲🍄 LLM Forest Orchestra: Turning Hidden States into Music
Hello everyone! I'm excited to introduce a new Space I've been developing called LLM Forest Orchestra. This project converts the hidden states and attention patterns of transformer models into layered MIDI compositions. The concept draws inspiration from mushrooms and mycelial networks in forests. Fungi create underground connections linking plants and trees, establishing what some call a "wood-wide web" where signals and nutrients travel. Researchers have discovered that these exchanges form patterns resembling rhythms and pulses. When translated appropriately, these patterns can become music.
Transformers operate through remarkably similar principles: tokens share signals via hidden states and attention heads. This Space transforms those invisible information flows into notes, chords, and rhythms, treating the model as a digital forest orchestra.
🎛 Features
* Two compute modes: - Full model operates on a Hugging Face model (defaulting to unsloth/Qwen3-14B-Base). - Mock latents provides a CPU-friendly option that simulates tensors for immediate experimentation. * Musical controls: You can adjust scale selection, tempo grid, velocity range, instrument/role presets, and seed randomization. * Output: The system generates .mid files compatible with DAWs and remixing workflows.
🌌 Why?
Neural networks already resemble unusual musical instruments: signals flow through them, patterns emerge organically, and careful observation reveals hidden melodies. This is analogous to the forest's secret orchestra of mushrooms and trees.
👉 Try it
Try the Space here: Locutusque/LLM-Forest-Orchestra. I'm excited to hear the sounds you can generate. Please share your created MIDIs or remixes in the comments. Let's explore how this hidden forest of transformers can sound together. 🌳🎶
just submitted my plugin idea to the G-Assist Plugin Hackathon by @nvidia . Check it out, it's a great way to use a local SLA model on a windows machine to easily and locally get things done ! https://github.com/NVIDIA/G-Assist
I couldn't watch innocent people get their rights trampled anymore. So I built something to help.
Stories of families torn apart, U.S. citizens detained for hours, people arrested just for speaking Spanish. This isn't the America I believe in.
Instead of doom-scrolling, I spent a few days building FIREWATCH - a free civil rights protection app.
What it does: • Real-time ICE raid alerts • Know Your Rights education in 10+ languages • Secure evidence recording • Emergency panic button • Legal hotlines and resources • 100% private, no tracking
The catch? There isn't one. You just need a free Google API key that stays on your device. Works completely offline.
