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-flash-reinforce-1.5bqwen25-1.5b-gsm8k-reinforce-step425verilog-qwen3.5-9b-v33-thinking-reinforced-loraMATH_ALL_REINFORCE_Q2.5-3BMATH_ALL_REINFORCE_MOD_Q2.5-3BOPENR1_REINFORCE_MOD_Q2.5-3B_NEW_TEMPLATEreinforce_v3MATH_ALL_REINFORCE_MOD_L3.2-3BMATH_REINFORCE_MOD_Q2.5-3BI_r16Affine-5czsc2fc98-r225-reinforce-loramafia_self-play_REINFORCE_v0MATH_REINFORCE_MOD_L3.2-3BI_r16_fullOPENR1_REINFORCE_MOD_Q2.5-3BOPENR1_REINFORCE_MOD_Q2.5-7Bqwen25-1.5b-gsm8k-reinforce-step300cloudsre-reinforce-checkpointMATH_ALL_REINFORCE_L3.2-3Bbig5-reinforce-v1