parkjo/Qwen2.5-Math-1.5B_grpo_ppl_adv_entropy_rollout_8_KL_0.001_ent_0.001_USE_KL__step580 2B • Updated May 22 • 2 • 1
inference-optimization/gpt-oss-120b-from-qwen235b-then-self-ckpt4-speculator.eagle3 0.9B • Updated Apr 1 • 3 • 1