is-sft-271828/grpo-is-qwen3-0.6b-base-beh-qwen3-8b-lr-3e-5-logspace-dm-0.3-ncoeff-1.0-nmode-flip 0.6B • Updated 5 days ago • 12
is-sft-271828/grpo-is-qwen3-0.6b-base-beh-qwen3-8b-lr-3e-5-logspace-dm-0.3-ncoeff-1.0-nmode-flip 0.6B • Updated 5 days ago • 12