Open to Work

dealign.ai PRO

dealignai

AI & ML interests

ML Researcher - No fine tuning, no lora, no template bs, pure real ablation. - I have an obsession with making high quality red teaming LLM’s

Recent Activity

new activity about 1 hour ago

OsaurusAI/MiniMax-M2.7-JANGTQ_K:Add MMLU-200 (93.5%), speed/memory benchmarks, fix variants table sizes (47→56 GB), expand topic tags

updated a model 3 days ago

dealignai/Ling-2.6-flash-JANGTQ2-CRACK

updated a model 3 days ago

dealignai/Ling-2.6-flash-MXFP4-CRACK

View all activity

Organizations

New activity in OsaurusAI/MiniMax-M2.7-JANGTQ_K about 1 hour ago

Add MMLU-200 (93.5%), speed/memory benchmarks, fix variants table sizes (47→56 GB), expand topic tags

#1 opened about 1 hour ago by

dealignai

New activity in dealignai/Gemma-4-31B-JANG_4M-CRACK about 1 month ago

gemma4-crack

#8 opened about 1 month ago by

Adam666Eves

Bug

#3 opened about 1 month ago by

Zayaan

New activity in dealignai/Nemotron-Cascade-2-30B-A3B-JANG_2L-CRACK about 1 month ago

non-mac

#1 opened about 1 month ago by

pirola

New activity in dealignai/Gemma-4-26B-A4B-JANG_2L-CRACK about 1 month ago

lm-studio

#2 opened about 1 month ago by

hady20100

turboquant module?

#1 opened about 1 month ago by

abbuu

New activity in dealignai/Gemma-4-31B-JANG_4M-CRACK about 1 month ago

Can you please release GGUF versions ?

#1 opened about 1 month ago by

PaPaai99

Refusal rate very high on questions beyond cybersecurity

#4 opened about 1 month ago by

Zayaan

New activity in dealignai/GPT-OSS-120B-MLX-CRACK about 1 month ago

Performance Test on MacBook Max – 77 tokens/s for a 1k‑token Task

#1 opened about 1 month ago by

cutiedeng

New activity in dealignai/Qwen3.5-VL-9B-4bit-MLX-CRACK about 1 month ago

Better than Huihui-Qwen3.5-9B-abliterated-mlx-4bit ?

#1 opened about 1 month ago by