🏗️ Building on HF

AxionLab

AxionLab-official

·

AI & ML interests

Owner of SupraLabs

Recent Activity

liked a model about 4 hours ago

BananaMind/BananaMind-2.5-Pro

repliedto DavidAU's post about 5 hours ago

Qwen3.8-27B-Ultimate-Heretic-Uncensored-Turbo-Brilliance-50x-AGI A specialized fine tune with the core goal to improve instruction following and nuance, combined with the firepower of Turbo Brilliance V2 50X AGI, featuring 21 dynamically generated AGI constructs. This system pushes SOTA Qwen 3.8 fine tuned to the absolute limit, while at the same time drastically reducing tokens usage and improving quality. Examples, with detailed usage/use cases at the repo. But it is also simple: Download a quant, type "help" in the chat -> and the interactive systems will work with you to handle any use case(s) with Turbo Brilliance. This example ("fusion") is particularly potent and showcases an AGI construct using the "Elon Musk" and "Marie Curie" AI constructs: "{REASON:agi-musk-curie} Invent fusion (not fission) reactor and/or technology to make it possible." Full example at the repo ; with a lot more. https://huggingface.co/DavidAU/Qwen3.8-27B-Ultimate-Heretic-Uncensored-Turbo-Brilliance-50x-AGI-NEO-GGUF PS: We are ready for Qwen 4 27B / NEXT ... and so is Turbo Brilliance V2 AGI. PS2: TWO 40B Qwen 3.8 versions with Turbo Brilliance V2 AGI are dropping this week too.

liked a model about 15 hours ago

klein-ml/Klein-TTS-X1.5-Pro

View all activity

Organizations

upvoted a collection 17 days ago

Supra2.5

Supra2.5: Latest state-of-the-art flagship model family releases • 2 items • Updated 9 days ago • 5

upvoted an article 18 days ago

Article

When Benchmark Numbers Become Marketing

DedeProGames

•

Sep 17

• 12

upvoted a collection 22 days ago

SupraLabs' Space

All important SupraLabs models. We are advancing the very small open models frontier. • 10 items • Updated 22 days ago • 2

upvoted a changelog 22 days ago

Hugging Face Changelog

Filter Models & Datasets Pages by Author

23 days ago

• 109

upvoted a collection 28 days ago

SupraNeo

SupraNeo: The subfamily of the Supra models, delivering intelligence in a compact size • 1 item • Updated 28 days ago • 3

upvoted 3 collections about 1 month ago

Benchmarks

1 item • Updated 28 days ago • 2

Benchmarks

Axiomic Small LLM benchmarks • 5 items • Updated Oct 3 • 4

OpenFineTrain

Very fine 55 trillion+ tokens worth of ungated huggingface datasets for LLM training across 80+ datasets. • 92 items • Updated Oct 7 • 14

upvoted an article about 2 months ago

Article

How Did We Get Here?

NILKNARFGonzo

•

Sep 13

• 8

upvoted an article 2 months ago

Article

Introducing @huggingface/kernels: 200+ WebGPU Kernels for Local AI

nico-martin, Xenova

•

Sep 1

• 99

upvoted 2 collections 3 months ago

Supra-Experiments

Experimental research models • 11 items • Updated 28 days ago • 7

text to audio

ai models that create audio from text prompts • 1 item • Updated 11 days ago • 1

upvoted an article 3 months ago

Article

DAVIDAU DELETED MY POST AND BANNED ME FOR ASKING ABOUT BENCHMARKS — HERE IS THE FULL ANALYSIS (9B + 27B + 390 MODELS)

DedeProGames

•

Aug 11

• 22

upvoted a collection 3 months ago

Our flagship CHAT models

This is a collection of all our flagship chat models to make it more easy for you! • 3 items • Updated May 3 • 5

upvoted an article 3 months ago

Article

LFM2.5-Encoders for Fast Long-Context Inference on CPU

LiquidAI

•

Jul 28

• 69

upvoted an article 4 months ago

Article

The influx of specialist models on the Open SLM Leaderboard

Banaxi-Tech

•

Jul 23

• 10

upvoted a collection 4 months ago

Supra2

Supra2: Previous state-of-the-art flagship model family release • 7 items • Updated 18 days ago • 13

upvoted a changelog 4 months ago

Hugging Face Changelog

Filter Models page by Hardware

Jun 30

• 228

upvoted 2 collections 4 months ago

ternary-models: VLMs, Multimodal & Audio

Ternary-quantized models for architectures GGUF can't handle. tritplane3 scheme. • 16 items • Updated Apr 17 • 6

WTF GENIUS PAPERS

Papers that made me appreciate my major and my life a little more. obs=Observation, innov=Innovation. Most papers are abt improving tiny models. • 522 items • Updated about 11 hours ago • 108