pixillated

pixillated's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

updated a model 4 days ago

cyberneurova/CyberNeurova-Kimi-K2.7-Code-GGUF

1T • Updated 4 days ago • 1

published a model 4 days ago

cyberneurova/CyberNeurova-Kimi-K2.7-Code-GGUF

1T • Updated 4 days ago • 1

updated a model 23 days ago

cyberneurova/CyberNeurova-Gemma-4-12B-it-abliterated

Text Generation • 12B • Updated 23 days ago • 2.25k • 1

published a model 23 days ago

cyberneurova/CyberNeurova-Gemma-4-12B-it-abliterated

Text Generation • 12B • Updated 23 days ago • 2.25k • 1

New activity in cyberneurova/CyberNeurova-DeepSeek-V4-Flash-abliterated-GGUF 29 days ago

Q8_0 version 404-ed?

2

#6 opened 29 days ago by

joesixpaq

updated 2 collections about 1 month ago

CyberNeurova × Qwen Family

Collection

Abliterations based on the Qwen model family. Includes vision-language variants and future Qwen2/Qwen3 text-only releases. • 2 items • Updated May 20 • 1

CyberNeurova Abliterations

Collection

Refusal-direction ablation across model families: text LLMs, VLMs, and unified multimodal generation. Full benchmarks + methodology per release. • 4 items • Updated May 20 • 2

updated a model about 1 month ago

cyberneurova/CyberNeurova-Qwen3.6-35B-A3B-abliterated

Text Generation • 35B • Updated May 20 • 328 • 7

published a model about 1 month ago

cyberneurova/CyberNeurova-Qwen3.6-35B-A3B-abliterated

Text Generation • 35B • Updated May 20 • 328 • 7

updated 4 collections about 1 month ago

CyberNeurova × ByteDance Family

Collection

Research artifacts derived from ByteDance multimodal models. Lance-3B with refusal-direction transfer from Qwen2.5-VL-3B-Instruct. • 1 item • Updated May 20

CyberNeurova × DeepSeek Family

Collection

Abliterations based on DeepSeek. V4-Flash (284B MoE) with three-direction multi-turn-aware ablation, as Q2_K and Q8_0 GGUFs. • 1 item • Updated May 20

CyberNeurova × Qwen Family

Collection

Abliterations based on the Qwen model family. Includes vision-language variants and future Qwen2/Qwen3 text-only releases. • 2 items • Updated May 20 • 1

CyberNeurova Abliterations

Collection

Refusal-direction ablation across model families: text LLMs, VLMs, and unified multimodal generation. Full benchmarks + methodology per release. • 4 items • Updated May 20 • 2

updated a model about 1 month ago

cyberneurova/CyberNeurova-Lance-3B-abliterated

Any-to-Any • Updated May 20 • 9

published a model about 1 month ago

cyberneurova/CyberNeurova-Lance-3B-abliterated

Any-to-Any • Updated May 20 • 9

updated a model about 1 month ago

cyberneurova/CyberNeurova-Qwen2.5-VL-3B-Instruct-abliterated

Image-Text-to-Text • 4B • Updated May 20 • 106 • 4

published a model about 1 month ago

cyberneurova/CyberNeurova-Qwen2.5-VL-3B-Instruct-abliterated

Image-Text-to-Text • 4B • Updated May 20 • 106 • 4

New activity in cyberneurova/CyberNeurova-DeepSeek-V4-Flash-abliterated-GGUF about 2 months ago

The model is working okay! (Temporary fix for stop token being ignored)

5

#1 opened about 2 months ago by

phakio