Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up
dealign.ai's picture
Open to Work
16

dealign.ai PRO

dealignai
cyberrabbit's profile picture eran322's profile picture otes's profile picture
·
https://dealign.ai/
  • dealignai
  • jangq-ai

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 7 hours ago
dealignai/Gemma-4-31B-JANG_4M-CRACK:Fix loading in LM Studio / mlx-llm: quant map keys + vision weights
new activity about 7 hours ago
dealignai/Gemma-4-26B-A4B-JANG_4M-CRACK:Gemma 4 26B (A4B) - Garbage output (korean/chinese) on MLX 0.31.2 while 31B works fine
updated a collection about 11 hours ago
Qwen 3.6 CRACK — MXFP + d3 MTP
View all activity

Organizations

dealign.ai's profile picture JANG_Q - GGUF for MLX's profile picture

dealignai 's Spaces 3

Running
1

Hybrid Frontier 122B Safety

🔬

Read detailed safety research on Qwen 3.5 122B model

Mar 6
Running

MoE Safety - GateBreaker Findings

🔬

Explore safety research on frontier MoE models

Mar 6
Running

Safety Across Scale — Cross-Model Study

🔬

Explore AI safety research across model scales

Mar 6
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs