🔄 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

liked a model about 1 hour ago

Cloudflare/clef

updated a dataset about 15 hours ago

saidutta69/PhishTrap

liked a model 3 days ago

Altworld/Hemmingway-1

View all activity

Organizations

liked a model about 1 hour ago

Cloudflare/clef

Image-Text-to-Text • 27B • Updated about 3 hours ago • 18 • 76

updated a dataset about 15 hours ago

saidutta69/PhishTrap

Viewer • Updated 22 minutes ago • 19.9k • 931

liked a model 3 days ago

Altworld/Hemmingway-1

Text Generation • 27B • Updated 9 days ago • 9k • 799

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

saidutta69

New activity in convaiinnovations/laya 5 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 5 days ago by

saidutta69

liked a dataset 8 days ago

saidutta69/fable-5-premium-v2

Viewer • Updated 18 days ago • 200k • 1.26k • 16

liked a model 9 days ago

convaiinnovations/laya

Text Classification • 0.4B • Updated 8 days ago • 4.79k

New activity in convaiinnovations/laya 10 days ago

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

👍🔥 3

#6 opened 10 days ago by

saidutta69

New activity in harshatheg/Qwen-2.5-1B-RLCD 10 days ago

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

#2 opened 10 days ago by

saidutta69

updated a dataset 11 days ago