🔄 In a Training Loop
RACER IS OP
saidutta69
AI & ML interests
On-device ML · Abliteration · Distillation · Odia NLP · Security models · Running everything locally on TFLOPS and vibes
Recent Activity
new activity about 1 hour ago
interfaze-ai/lev:Independent run: Banking77 12-way 0.7292 against your 77-intent 0.980 new activity about 2 hours ago
wayfind/metask-jev-4b-policy-mix:Independent run: our MNLI 0.6333 against your published 90.3% new activity about 2 hours ago
Mapika/decider-4b:Independent run: our MNLI 0.7667 against your published 0.926Organizations
Independent run: Banking77 12-way 0.7292 against your 77-intent 0.980
2
#1 opened about 2 hours ago
by saidutta69
Independent run: our MNLI 0.6333 against your published 90.3%
1
#1 opened about 2 hours ago
by saidutta69
Independent run: our MNLI 0.7667 against your published 0.926
1
#3 opened about 2 hours ago
by saidutta69
Independent run on typed decisions: ours 0.4815 overall - what does your harness give?
1
#5 opened about 2 hours ago
by saidutta69
Independent run: Banking77 12-way 0.9062 against your 77-option 0.690
#1 opened about 2 hours ago
by saidutta69
Independent run: our MNLI 0.7417 against your published 0.856 - which is right?
#4 opened about 2 hours ago
by saidutta69
Independent run: our SST-5 (0.4667) is below your published 0.603 - which harness is right?
1
#1 opened about 2 hours ago
by saidutta69
Independent Laya vs Jev head-to-head on identical inputs
👍🔥 3
5
#6 opened 13 days ago
by saidutta69
Independent 4-way benchmark incl. this engine (751 identical states)
#2 opened 13 days ago
by saidutta69
saidutta69/Qwen2.5-Coder-3B-Instruct-heretic
🤗 1
#10810 opened 3 months ago
by saidutta69