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-4bgpt-oss-20b-format-loraatomicvision-format-submit-merged-loraqwen3-8b-oracle-sft-formatTinyLlama-1B-Sonar-formattingft-phone-formatqwen3-4b-structured-output-slack-recovery-phase1-format-guard-t002for_matsuolab_lecturee5_format_reward_0.4_rain_rl_langSkeptiSTEM-4B-v2-stageR2-format-loraldif-comment-formattergpt-oss-120b-transcript-formatter-loraSkeptiSTEM-4B-stageR2-format-loraqwen3-4b-structured-output-slack-recovery-phase1-format-guard-t006qwen3-4b-structured-output-slack-recovery-phase1-format-guard-t007e5_format_reward_0.2_rain_rl_langnarraflow-formatter-enqwen3-4b-structured-output-slack-recovery-phase1-format-guard-t001gpt-oss-20b-transcript-formatter-loraqwen3.5-4b-transcript-formatter-lorae5_format_reward_0.6_rain_rl_langAffine-5czsc2fc98-r223-thought-format-loranarraflow-formatter-loraqwen14b-dpo-format-s42agentbench-qwen3-4b-v02-fixed-formatllm2025-adv-exp007-format-fixFormatMatch_v1FormatALFOnly_v1llm2025-adv-exp016b-fix-formatQwen2.5-3B-Instruct_Address_Formatter
