JackHsieh/Qwen3-4B-Base-thoughtless.statml-arxiv-40M-20M.best Text Generation • 4B • Updated Aug 10 • 102
JackHsieh/prestar-4B-reason-only-k8-r_train0.125-lr1e-05-replay0.75-epochs2-bs32-step2432 Text Generation • 4B • Updated Jul 31 • 13
JackHsieh/prestar-4B-reason-only-k8-lr1e-05-replay0.75-epochs2-bs32-step2432 Text Generation • 4B • Updated Jul 31 • 6
JackHsieh/sft_with_kl_qwen-4B_NR-short-32k-16-1k-8_lr-3e-06-constant-bs-512_steps-128 4B • Updated Apr 22 • 5
JackHsieh/sft_on_offline_thoughts_qwen-4B_NR-short-32k-16-1k-8_lr-1e-06-constant-bs-512_steps-296 4B • Updated Apr 20 • 6
JackHsieh/jepo_frozen_rewarder_qwen-4B_NR-short-32k-4k_lr-1e-06-bs-64-kl-0.001_steps-768 4B • Updated Apr 18 • 2