🇨🇳 Focusing

Palind

Palind

·

Palind-Rome

AI & ML interests

Post-Training

Recent Activity

upvoted a paper 1 day ago

P^2-MOPD: Accelerating Multi-Teacher On-Policy Distillation via Parameter Priors

liked a dataset 1 day ago

open-thoughts/OpenThoughts-TBLite

liked a dataset 1 day ago

harborframework/terminal-bench-2.1

View all activity

Organizations

None yet

Collections 1

models 11

Palind/Qwen3-4B-SC-CodeAgent-500Steps

Text Generation • 4B • Updated Oct 11 • 20

Palind/Qwen3-4B-SC-CodeAgent-200Steps

Text Generation • 4B • Updated Oct 10 • 17

Palind/Qwen3-4B-SC-TIS-repro-best

Text Generation • 4B • Updated Oct 7 • 68

Palind/Qwen3-4B-PG-repro-best

Text Generation • 4B • Updated Oct 7 • 90

Palind/Qwen3-4B-PG-repro-final

Text Generation • 4B • Updated Oct 7 • 24

Palind/Qwen3-4B-TIS-repro-best

Text Generation • 4B • Updated Oct 7 • 18

Palind/Qwen3-4B-SC-TIS-repro-final

Text Generation • 4B • Updated Oct 7 • 20

Palind/Qwen3-4B-TIS-repro-final

Text Generation • 4B • Updated Oct 7 • 23

Palind/Qwen3-4B-SC-repro-best

Text Generation • 4B • Updated Oct 7 • 24

Palind/Qwen3-4B-SC-repro-final

Text Generation • 4B • Updated Oct 7 • 20

datasets 0

None public yet