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.
JustRL-DeepSeek-1.5BJustRL-Qwen3-1p7b-Selective-Top20pctJustRL-Distilled-DeepSeek-7b-DirectOPDJustRL-Qwen3-1p7b-Selective-Top15pctJustRL-Qwen3-8b-RKLSelective-Top10pctJustRL-Qwen3-8b-FKLSelective-Top10pctJustRL-Qwen3-1p7b-FKLSelective-Top10pctJustRL-Qwen3-4b-DirectOPDJustRL-Qwen3-8b-Selective-Top10pctJustRL-Qwen3-1p7b-Selective-Top10pctJustRL-Qwen3-4b-RKLSelective-Top10pctJustRL-Qwen3-1p7b-RKLSelective-Top10pctJustRL-Qwen3-4b-FKLSelective-Top10pctJustRL-II-base-modelJustRL-Nemotron-1.5BJustRL-Qwen3-8b-DirectOPDJustRL-Distilled-DeepSeek-7b-Selective-Top10pctJustRL-Qwen3-1p7b-DirectOPDJustRL-Qwen3-1p7b-Random10pct-seed42JustRL-Qwen3-4b-Selective-Top10pctJustRL-Qwen3-1p7b-BatchSelective-Top10pctJustRL-Qwen3-1p7b-Selective-Top5pctJustRL-Qwen3-4BJustRL-Qwen3-1.7BJustRL-R1-7BQwen3-1.7B-DirectOPD-JustRLShift-100