agurung/cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp5-nb21iid16 Text Generation • 4B • Updated 26 days ago • 461 • 1
agurung/cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp5-base-b21 Text Generation • 4B • Updated 26 days ago • 444
agurung/cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp5-nb21vs16 Text Generation • 4B • Updated 26 days ago • 448
agurung/cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp10-iid30 Text Generation • 4B • Updated 26 days ago • 150
agurung/cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp10-base Text Generation • 4B • Updated 26 days ago • 407
agurung/cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp20-base Text Generation • 4B • Updated 26 days ago • 147
agurung/flawed-fictions-qwen3-4b-lengthpenalty-litereason Reinforcement Learning • 4B • Updated 26 days ago • 13
agurung/lcb-ft-v2-qwen3-4b-rft-iid-24-lora-r128-a32-lr2p5e-4-const-lr2p5e-4-qps8-gpuauto-ep4 Updated 26 days ago • 15
agurung/cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp5-base-q4v2 Text Generation • 4B • Updated 26 days ago • 452
agurung/cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp5-q4v2-vs16 Text Generation • 4B • Updated 26 days ago • 504
agurung/cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp5-q4v2-iid16 Text Generation • 4B • Updated 26 days ago • 444
agurung/cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp10-q4v3-groot16 Text Generation • 4B • Updated 26 days ago • 523
agurung/cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp10-q4v3-iid16 Text Generation • 4B • Updated 26 days ago • 513
agurung/cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp10-base-q4v3 Text Generation • 4B • Updated 26 days ago • 514
agurung/cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp5-base-q4v3 Text Generation • 4B • Updated 26 days ago • 501
agurung/v1ff_savebestearly_sft_qwen7B_25percent_lr_1e4_bptt_offset Text Generation • 8B • Updated 26 days ago • 237
agurung/cobalt-seeded-rl-base-ramp25-stoppen-gen4k-ep2-ncp5-q4v2-groot16 Text Generation • 4B • Updated 26 days ago • 446
agurung/Qwen2.5-7B-Instruct-1M-NRL-NCP-GRPO-NLL-PIECEWISE-REWARD Text Generation • 8B • Updated 26 days ago • 114