Vikarti Anatra

vikarti-anatra's activity

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

upvoted a collection 7 days ago

Qwen 3.5 CRACK Abliterated Series

Collection

Full Qwen 3.5 CRACK family (0.8B-397B). Dense + MoE VL models, 4/6/8-bit MLX. Pure surgical abliteration, zero fine-tuning. • 32 items • Updated 3 days ago • 1

upvoted a collection 4 months ago

The Bestiary

Collection

Decensored language models made using Heretic (https://github.com/p-e-w/heretic) • 6 items • Updated Nov 16, 2025 • 103

upvoted a paper 11 months ago

PRIMA.CPP: Speeding Up 70B-Scale LLM Inference on Low-Resource Everyday Home Clusters

Paper • 2504.08791 • Published Apr 7, 2025 • 139

upvoted a collection 11 months ago

RpR Models

Collection

RpR (RolePlay with Reasoning) models which are built on RPMax datasets with properly trained multi-turn reasoning. • 8 items • Updated Jun 25, 2025 • 20

upvoted a collection over 2 years ago

Saiga

Collection

Russian fine-tunes of different base LLMs • 12 items • Updated Apr 25, 2025 • 45