Dev

Devistro

·

AI & ML interests

None yet

Recent Activity

liked a model about 11 hours ago

jialinyyzz/humanizer

liked a model about 11 hours ago

DavidAU/Qwen3.8-Flash-Next-Abliterated-Uncensored-Turbo-Brilliance-50x-Reasoning-Instruct-GSQ-RCO-GGUF

liked a model about 11 hours ago

nerkyor/Qwen3.8-27B-Coder390-EfficientThink-Opus5.5-GPT6Astra-Grok4.7-DSV4Pro-K3-SFT-RLOO-MTP-DFlash2

View all activity

Organizations

upvoted a collection 8 days ago

Swift 1.5 27B

Swift 1.5 on Qwen3.8-27B: stronger than Swift 1.0 on agentic and coding tasks, with fewer thinking tokens. BF16 weights and every quant. • 11 items • Updated 9 days ago • 23

upvoted an article 25 days ago

Article

tokenizers v1: encode, decode and scaling, measured

+2

ArthurZ, sbrandeis, mcpotato, lysandre

•

26 days ago

• 91

upvoted a collection about 1 month 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. • 133 items • Updated about 20 hours ago • 177