HyperTanker

HyperTanker

·

AI & ML interests

AI Horde interested. Like only models i have.

Recent Activity

liked a model about 16 hours ago

mradermacher/DeepSeek-V4-Pro-Qwen3.5-4B-UNCENSORED-heretic-i1-GGUF

liked a model 7 days ago

Green-Sky/CyberRealisticPony-GGUF

liked a model 8 days ago

mradermacher/Dolphin3.0-Llama3.2-3B-i1-GGUF

View all activity

Organizations

None yet

upvoted 2 collections 8 days ago

🛡️ Qwensploit / Cybersec

Awesome fine-tunes for cyber security, vulnerability research, blue- and red teaming • 20 items • Updated 11 minutes ago • 5

🗿⚛️ Deep Thought

Fine-tuned for scientific exploration, math, technical problem-solving and drug discovery. • 15 items • Updated about 22 hours ago • 6

upvoted a collection 9 days ago

😈 Awesome Uncensored Models

Abliterated/uncensored/heretic versions of awesome fine-tunes • 23 items • Updated about 3 hours ago • 57

upvoted an article 10 days ago

Article

Norm-Preserving Biprojected Abliteration

grimjim

•

Nov 6, 2025

• 102

upvoted 2 papers about 1 month ago

It's a TRAP! Task-Redirecting Agent Persuasion Benchmark for Web Agents

Paper • 2512.23128 • Published Jun 4 • 1

SPILLage: Agentic Oversharing on the Web

Paper • 2602.13516 • Published Feb 13 • 1

upvoted 2 papers 2 months ago

OPT: Open Pre-trained Transformer Language Models

Paper • 2205.01068 • Published May 2, 2022 • 3

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

Paper • 2512.13655 • Published Dec 15, 2025 • 7

upvoted a collection 3 months 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 • 256

upvoted an article 3 months ago

Article

SmolLM - blazingly fast and remarkably powerful

+1

loubnabnl, anton-l, eliebak

•

Jul 16, 2024

• 471

upvoted a paper 5 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 6 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. • 139 items • Updated 5 days ago • 188

upvoted an article about 1 year ago

Article

Uncensor any LLM with abliteration

mlabonne

•

Jun 13, 2024

• 956