HyperTanker

HyperTanker

·

AI & ML interests

AI Horde interested. Like only models i have.

Recent Activity

liked a model 2 days ago

ggerganov/whisper.cpp

liked a model 5 days ago

mradermacher/Ektome-SmolLM2-1.7Bi-PristinelyUncensored-i1-GGUF

liked a model 5 days ago

mradermacher/Ministral-3-3B-Instruct-2512-absolute-heresy-i1-GGUF

View all activity

Organizations

None yet

upvoted a paper 11 days ago

OPT: Open Pre-trained Transformer Language Models

Paper • 2205.01068 • Published May 2, 2022 • 3

upvoted a paper 21 days ago

Comparative Analysis of LLM Abliteration Methods: A Cross-Architecture Evaluation

Paper • 2512.13655 • Published Dec 15, 2025 • 7

upvoted a collection 27 days ago

🪐 SmolLM

A series of smol LLMs: 135M, 360M and 1.7B. We release base and Instruct models as well as the training corpus and some WebGPU demos • 12 items • Updated May 5, 2025 • 252

upvoted an article 27 days ago

Article

SmolLM - blazingly fast and remarkably powerful

+1

loubnabnl, anton-l, eliebak

•

Jul 16, 2024

• 469

upvoted a paper 3 months ago

Gabliteration: Adaptive Multi-Directional Neural Weight Modification for Selective Behavioral Alteration in Large Language Models

Paper • 2512.18901 • Published Dec 21, 2025 • 6

upvoted a collection 4 months ago

Heretic - Abliterated, Uncensored, Unrestricted POWER.

Models that have be abliterated using the HERETIC method. Done properly, this completely removed almost all censorship with no damage to the model. • 137 items • Updated 9 days ago • 167

upvoted an article 12 months ago

Article

Uncensor any LLM with abliteration

mlabonne

•

Jun 13, 2024

• 924