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.
rl_warmup_rlve_offline_20K-parquet_qwen3-1.7b_epoch_1_maskrecipe-llm-ggufQwen3-4B_ds-parquet-programs-c24Qwen3-4B_ds-parquet-programs-c1403Qwen3-4B_ds-parquet-programs-c12mixed_sft_kukurasu_20K_qwen3_4b_thinking-parquet_nemotron-cascade-8b_epoch_3opd_rlve_rose_20K-parquet_qwen3-1.7b_epoch_1_mask_qwen3-4b-think_resp16384-T1.0-n8-topk16Qwen3-4B_ds-parquet-programs-c2806Qwen3-4B_ds-parquet-programs_test-c4Qwen3-4B_ds-parquet-programs_test-c8sft_training_sudoku_level_3_stitch_train_half_mask-parquet_nemotron-cascade-8b-mathrl_epoch_3combine_parquet_r1gui_org_grpo_qwen2_5_vl_3b_h20_step_250roofline_kukurasu_9K_qwen3_4b_thinking-parquet_nemotron-cascade-8b_epoch_3rlve_sft_Qwen3_1-7B_continual_Qwen3_4B_Thinking-parquet_qwen3-1.7b_epoch_3teacher_prefix_sudoku_10K_qwen3_4b_thinking_continual_qwen3-1-7b-parquet_qwen3-1.7b_epoch_3rl_warm_up_code_full_sft_hard_25K-parquet_qwen3-1.7b_epoch_1_maskrl_warm_up_code_rose_sft_25K_1_7B_SFT-parquet_qwen3-1.7b-base-code-10k-sft_epoch_1_mask_lr1e-5combine_parquet_r1gui_org_grpo_qwen2_5_vl_3b_h20_step_350combine_parquet_r1gui_org_grpo_qwen2_5_vl_3b_h20_step_400combine_parquet_r1gui_org_grpo_qwen2_5_vl_3b_h20_step_450mixed_sft_minesweeper_14K_kukurasu_20K_qwen3_4b_thinking-parquet_nemotron-cascade-8b_epoch_3rl_warm_up_stitch_survo-parquet_qwen3-1.7b_epoch_3_maskpolaris_warmup_polaris_warmup_40K-parquet_qwen3-4b_epoch_1_masktinyllama-recipes-mergedpolaris_warmup_polaris_ROSE_warmup_Qwen3_1_7B_40K-parquet_qwen3-1.7b_epoch_1_masksft_warmup_OpenCodeReasoning_10K-parquet_qwen3-1.7b-base_epoch_1_mask_lr1e-5grpo_code_hard_code_rose_sft_25K_warmup-parquet_qwen3-1.7b_epoch_1_mask_resp16384-T1.0-n8combine_parquet_r1gui_org_grpo_qwen2_5_vl_3b_h20_step_300rl_warm_up_mixed_minesweeper_correct-parquet_qwen3-1.7b_epoch_1_maskrl_warm_up_mixed_survo_correct-parquet_qwen3-1.7b_epoch_3_mask
