🔄 In a Training Loop

RACER IS OP

saidutta69

5 4 24

https://sdad.pro

instax-dutta

AI & ML interests

On-device ML · Abliteration · Distillation · Odia NLP · Security models · Running everything locally on TFLOPS and vibes

Recent Activity

updated a model about 14 hours ago

saidutta69/granite-4.2-3b-heretic

published a model about 14 hours ago

saidutta69/granite-4.2-3b-heretic

updated a dataset about 15 hours ago

saidutta69/PhishTrap

View all activity

Organizations

updated a model about 14 hours ago

saidutta69/granite-4.2-3b-heretic

Text Generation • 4B • Updated about 14 hours ago • 51

published a model about 14 hours ago

saidutta69/granite-4.2-3b-heretic

Text Generation • 4B • Updated about 14 hours ago • 51

updated a dataset about 15 hours ago

saidutta69/PhishTrap

Viewer • Updated about 2 hours ago • 19.9k • 943

liked a model 1 day ago

Cloudflare/clef

Image-Text-to-Text • 27B • Updated 1 day ago • 824 • 690

liked a model 4 days ago

Altworld/Hemmingway-1

Text Generation • 27B • Updated about 21 hours ago • 9.57k • 817

New activity in Qwen/Qwen2.5-1.5B-Instruct 6 days ago

Qwen2.5-1.5B-Instruct under parallel constrained decoding: 0.605 over 1,240 typed decisions, with the cost that implies on CPU

#29 opened 6 days ago by

saidutta69

New activity in convaiinnovations/laya 6 days ago

Independent head-to-head on a sealed 1,190-case manifest: laya 0.686 vs Jev 1.13.0 0.907 vs Qwen2.5-1.5B PCD 0.605, with paired intervals, plus three adapter findings

🔥 2

#20 opened 6 days ago by

saidutta69

liked a dataset 9 days ago

saidutta69/fable-5-premium-v2

Viewer • Updated 19 days ago • 200k • 1.29k • 16

liked a model 10 days ago

convaiinnovations/laya

Text Classification • 0.4B • Updated 9 days ago • 4.95k

New activity in convaiinnovations/laya 11 days ago

Independent Laya vs Jev head-to-head on identical inputs

👍🔥 3

#6 opened 11 days ago by

saidutta69

New activity in harshatheg/Qwen-2.5-1B-RLCD 11 days ago

Independent 4-way benchmark incl. this engine (751 identical states)

#2 opened 11 days ago by

saidutta69

updated a dataset 12 days ago

saidutta69/RedTeam-Premium

Viewer • Updated 12 days ago • 38.1k • 94

published a dataset 12 days ago

saidutta69/RedTeam-Premium

Viewer • Updated 12 days ago • 38.1k • 94

updated a dataset 12 days ago

saidutta69/Qwen3.8-Agent-Premium

Viewer • Updated 12 days ago • 26.1k • 158

published a dataset 12 days ago

saidutta69/Qwen3.8-Agent-Premium

Viewer • Updated 12 days ago • 26.1k • 158

updated a dataset 12 days ago

saidutta69/Kimi-K3-Premium

Viewer • Updated 12 days ago • 5.05k • 156

published a dataset 12 days ago

saidutta69/Kimi-K3-Premium

Viewer • Updated 12 days ago • 5.05k • 156

updated a dataset 12 days ago

saidutta69/CyberSec-Reasoning-Premium

Viewer • Updated 12 days ago • 6.13k • 164

published a dataset 12 days ago

saidutta69/CyberSec-Reasoning-Premium

Viewer • Updated 12 days ago • 6.13k • 164

updated a dataset 12 days ago

saidutta69/fable-5.1-premium

Viewer • Updated 12 days ago • 9.99k • 561 • 2

RACER IS OP

AI & ML interests

Recent Activity

Organizations

saidutta69's activity

Qwen2.5-1.5B-Instruct under parallel constrained decoding: 0.605 over 1,240 typed decisions, with the cost that implies on CPU

Independent head-to-head on a sealed 1,190-case manifest: laya 0.686 vs Jev 1.13.0 0.907 vs Qwen2.5-1.5B PCD 0.605, with paired intervals, plus three adapter findings

Independent Laya vs Jev head-to-head on identical inputs

Independent 4-way benchmark incl. this engine (751 identical states)