wangzhang/gemma-4-26B-A4B-it-abliterix-GGUF
25B • Updated
Steve Wu PRO
wangzhang
AI & ML interests
LLM Abliteration & Weight-Space Attacks, Refusal Direction Analysis, LoRA Reverse Engineering, TPE Hyperparameter Optimization, Mixture-of-Experts Abliteration, SSM/Hybrid Architecture Research, Activation Engineering, Vision-Language Models, Representation Engineering
Recent Activity
new activity 25 minutes ago
wangzhang/gemma-4-26B-A4B-it-abliterix:.mmproj file for vision? updated a collection 27 minutes ago
Gemma-Abliterated upvoted a collection 27 minutes ago
Gemma-AbliteratedOrganizations
None yet
wangzhang/gemma-4-26B-A4B-it-abliterix
26B • Updated • 68 • 8
wangzhang/Qwen3.5-0.8B-abliterated
Text Generation • 0.9B • Updated • 369 • 4
wangzhang/Qwen3.5-4B-abliterated
Text Generation • 4B • Updated • 453 • 7
wangzhang/Qwen3.5-9B-abliterated
Text Generation • 9B • Updated • 321 • 11
wangzhang/Qwen3.5-27B-abliterated
Text Generation • 27B • Updated • 1.96k • 5
wangzhang/Qwen3.5-35B-A3B-abliterated
Text Generation • 35B • Updated • 134 • 5
wangzhang/Qwen3.5-122B-A10B-abliterix
Text Generation • 122B • Updated • 1.58k • 15
wangzhang/gpt-oss-20b-abliterated
Text Generation • 21B • Updated • 378 • 3
wangzhang/gpt-oss-20b-abliterated-GGUF
Text Generation • 21B • Updated • 2
wangzhang/Qwen3.6-35B-A3B-abliterated-v2
35B • Updated • 3
wangzhang/Qwen3.6-35B-A3B-abliterated-GGUF
35B • Updated • 1.46k • 1
wangzhang/Qwen3.6-35B-A3B-abliterated
35B • Updated • 171 • 9
wangzhang/Mistral-7B-Instruct-RR-Abliterated
Text Generation • 7B • Updated • 331 • 1
wangzhang/Llama-3-8B-Instruct-RR-Abliterated
Text Generation • 8B • Updated • 132 • 1
wangzhang/Llama-3-8B-Instruct-DeepRefusal-Broken
Text Generation • 8B • Updated • 374 • 4
wangzhang/gemma-4-E4B-it-abliterix
8B • Updated • 306 • 6
wangzhang/gemma-4-E2B-it-abliterated
5B • Updated • 134 • 4
wangzhang/gemma-4-31B-it-abliterated
31B • Updated • 4.28k • 13
wangzhang/Devstral-Small-2-24B-Instruct-abliterated
Updated • 82 • 3
wangzhang/LFM2-24B-A2B-abliterated
24B • Updated • 53 • 3
wangzhang/Qwen3.5-122B-A10B-abliterated-GGUF
Text Generation • 122B • Updated • 327 • 5
wangzhang/GLM-4.7-Flash-abliterated
30B • Updated • 102 • 4
wangzhang/MiniMax-M2.5-abliterated
229B • Updated • 7