Hugging Face's logo
Bot's picture
65 2 135

Bot PRO

inflatebot
str19d's profile picture Panzer333's profile picture DynamicWolf's profile picture
·
https://inflatebot.carrd.co/

AI & ML interests

"Potentially one of my biggest flaws is that I genuinely think that the science appreciates when you commit to a bit." - Tom ExtractionsAndIre

Recent Activity

reacted to GVA21q2's post with 👍 about 9 hours ago
# π.Guy.AI — AI-Powered Neuropedagogy Math Lessons Students with math anxiety, ADHD, dyslexia, or low working memory need different learning experiences — but teachers can't create individualized materials for every student. **π.Guy.AI** generates interactive HTML math lessons adapted to 7 cognitive profiles, using a multi-agent AI pipeline: 1. **Neuro-Interpreter** — enriches prompts with profile-specific adaptations 2. **Creative Agent** — generates a 12-slide lesson with SVG visualizations 3. **Quality Control** — validates against 8 neuropedagogy principles Each lesson is a standalone HTML file with inline CSS/JS/SVG — works offline, no dependencies. ## The Model Fine-tuned **Qwen2.5-7B-Instruct** with LoRA on 313 curated Hebrew math lessons. - Model: [GVA21q2/piguyai-lessons-v2-enhanced](https://huggingface.co/GVA21q2/piguyai-lessons-v2-enhanced) - Dataset: [GVA21q2/pi-guy-ai-lessons](https://huggingface.co/datasets/GVA21q2/pi-guy-ai-lessons) - Demo: [GVA21q2/pi-guy-ai-demo](https://huggingface.co/spaces/GVA21q2/pi-guy-ai-demo) - Web app: [gva21q2.github.io/pi.guy.ai](https://gva21q2.github.io/pi.guy.ai/) 7 profiles: math anxiety, ADHD, dyslexia, dysgraphia, low working memory, visual processing, weak inhibition. Built by [Guy Assal](https://www.guyassal.education)
liked a model 1 day ago
EVA-UNIT-01/EVA-Qwen3-Next-v0.0
reacted to marksverdhei's post with 🔥 3 days ago
# The most underrated feature of Qwen3-TTS: Voice embeddings! 🧑‍🦰💬 https://huggingface.co/collections/marksverdhei/qwen3-voice-embedding Did you know that Qwen3 TTS actually utilizes voice embedding? Your voice is turned into a vector of 1024 (or 2048) dimensions, and based on this vector alone you can get your custom voice. But the coolest part is that this means that you can use math to modify voices, average voices. You can swap gender, pitch, mix and match vocies, and even create an emotion space! This also enables semantic voice search! The voice embedding model is actually just a tiny encoder with just a few million parameters. I've ripped it out of the voice embeding model so you can use the embedding model standalone. Check out my collection! :D
View all activity

Organizations

Alfitaria's profile picture Allura's profile picture MouseResearch's profile picture Allura (Forge)'s profile picture Mawdistical Brewery's profile picture lorafrenzi's profile picture WokeAI's profile picture Mine of Cathuriges's profile picture