models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
paper-zero-rl-format-reward-4bpapersignal-hype-detectorpaper-flash-reinforce-1.5bcot-oracle-paper-ablation-ours-3layerspaper-bpco-bounded-critic-1.5bpaper-filter-metric-1.5bcot-oracle-paper-ablation-ours-12layerscot-oracle-paper-3layers-r1024-a128paper-gmts-token-select-1.5bcot-oracle-paper-ablation-adam-recipe-1layercot-oracle-paper-ablation-ours-3layers-onpolicy-lens-onlycot-oracle-paper-ablation-ours-1layer-lastcot-oracle-paper-ablation-ours-12layers-r512-a1024paper-adaptive-clip-1.5bpaper-endpoint-sft-1.5bcot-oracle-paper-ablation-ours-1layer-75pctpaper-sao-single-rollout-1.5bcot-oracle-paper-ablation-ours-1layerFine-tuning_Qwen3-14B_for_fine-grained_paperscot-oracle-paper-ablation-ours-6layers-deltascot-oracle-paper-12layers-stage2-convqa-lr1e5cot-oracle-paper-3layers-r1024-a32-lowalpha-fixed50cot-oracle-paper-12layers-r1024-a256-bigrun-bs8paper-harness-and-weights-1.5bcot-oracle-paper-12layers-scaled-r1024-a1024-lr3e5-100m-pastonlycot-oracle-paper-12layers-stage2-convqa-bs4cot-oracle-paper-3layers-r1024-a16-exact-matchgemma_2_ipg_util_paper_readyjembut-paper-knock-Hermes3-3B-step825SmolLM-135M-paper-instructions-lora
