LegendaryDawn on Hugging Face: model downloads
LegendaryDawn has 118 tracked models, downloaded 987 times in the last 30 days and 24,195 times in total. LegendaryDawn Wrapped: the last 12 months.
Models by downloads in the last 30 days
- LegendaryDawn/self-debate-exp-Qwen2.5-3B-majority_fix_n4_l2048-DAPO_n8_bs256_long8-step200 19 downloads, model
- LegendaryDawn/mbpo-adv_8_64-w0001-qwen2_5_vl_3b-step302 18 downloads, model
- LegendaryDawn/mbpo-adv_8_64-w001-qwen2_5_vl_3b-step302 18 downloads, model
- LegendaryDawn/self-debate-baseline-Qwen3-1.7B-Base-DAPO-n8-bs256-long8-step200 17 downloads, model
- LegendaryDawn/self-debate-exp-Qwen3-4B-Base-majority_n4_l2048-DAPO_n8_bs256_long8-run2-step200 16 downloads, model
- LegendaryDawn/self-debate-exp-Qwen2.5-3B-grpo-diff_sol2048-n8-bs256-long8-DAPO-step200 15 downloads, model
- LegendaryDawn/erpo-iclr-ours-Qwen2.5-7b-corr_gen_s005_max14 14 downloads, model
- LegendaryDawn/self-debate-exp-Qwen3-4B-Base-majority_n4_l2048-DAPO_n8_bs256_long8-step200 13 downloads, model
- LegendaryDawn/self-debate-exp-Qwen2.3-3B-balance-diff_sol2048-n8-bs256-long8-DAPO-step200 13 downloads, model
- LegendaryDawn/mbpo-adv_group_append_clean_abs1-adv_8_64_rankmix20-dapo-n8-qwen2_5_vl_3b-step300 13 downloads, model
- LegendaryDawn/mbpo-adv_8_64-scaled-w001-qwen2_5_vl_3b-step302 12 downloads, model
- LegendaryDawn/mbpo-ablation-append_clean_abs05-filter-adv_patch_zero50_rankmix-global20-3b-step300 12 downloads, model
- LegendaryDawn/erpo-Qwen2.5-3B-s003_max11-step180 12 downloads, model
- LegendaryDawn/WaitList-Qwen2-VL-7B-G16-R-multiyn-Rmmseed-GPT4o-adv-multiyn-12k-beta05 12 downloads, model
- LegendaryDawn/mbpo-iclr-Qwen2_vl_7b_instruct-R_multiyn1-lr5e-7-beta01-Rmmseed-GPT4o-adv-multiyn-12k 12 downloads, model
- LegendaryDawn/mbpo-clean_negative_reweight-resrl_quantile-adv_8_64-qwen2_5_vl_3b-step302 12 downloads, model
- LegendaryDawn/mbpo-adv_dpo001-shard-adv_8_64_rankmix20-dapo-n8-qwen2_5_vl_3b-step300 12 downloads, model
- LegendaryDawn/mbpo-adv_masked_grpo-balanced-adv_8_64-qwen2_5_vl_3b-step302 12 downloads, model
- LegendaryDawn/ablation-Qwen2-VL-7B-G16-R-multiyn1-r1-multiyn-2k 11 downloads, model
- LegendaryDawn/Qwen2-VL-7b-G0-povid-12k 11 downloads, model
- LegendaryDawn/Qwen2-VL-7b-G0-rlaifv-12k 11 downloads, model
- LegendaryDawn/baseline-LlavaOneVision-G0-bpo-12k 11 downloads, image text to text
- LegendaryDawn/SDRL-baseline-Qwen3-8B-Base-DAPO-n8-bs256-long12-yarn2-step200 11 downloads, model
- LegendaryDawn/erpo-Qwen2.5-7B-s005_max12-step180 11 downloads, model
- LegendaryDawn/erpo-iclr-baseline-Qwen2.5-7b-DAPO-step180 11 downloads, model
- LegendaryDawn/erpo-iclr-ours-Qwen2.5-3b-corr_gen_s002_max12 11 downloads, model
- LegendaryDawn/mbpo-iclr-Qwen2_5_vl_7b_instruct-R_multiyn1-beta02-lr2e-7-mixed-10-8-64-12k 11 downloads, model
- LegendaryDawn/mbpo-adv_dpo001-shard2-adv_8_64_rankmix20-dapo-n8-qwen2_5_vl_3b-step300 11 downloads, model
- LegendaryDawn/ablation-Qwen2_5-G0-Rmmseed-GPT4o-rand01-12k 10 downloads, model
- LegendaryDawn/mbpo-adv_group_append_clean_abs05-clip02-filter-entropy-0p001-adv_8_64_rankmix20-7b-step250 10 downloads, model
- LegendaryDawn/mbpo-clean_negative_reweight-budget_exp-adv_8_64-qwen2_5_vl_3b-step302 10 downloads, model
- LegendaryDawn/baseline-RLAIF-V-llava-7B 10 downloads, model
- LegendaryDawn/mbpo-ablation-append_clean_abs05-filter-adv_patch_zero50_rankmix30-3b-step300 10 downloads, model
- LegendaryDawn/SDRL-freq-Qwen3-8B-Base-majority_n8_l4096-DAPO_n8_bs256_long12-yarn2-step125 10 downloads, model
- LegendaryDawn/SDRL-baseline-DAPO-Qwen3-4B-Base-icml-self-debate-baseline-DAPO-n8-bs256-long8-step200 10 downloads, model
- LegendaryDawn/Qwen2-VL-7b-G0-bpo-12k 10 downloads, model
- LegendaryDawn/mbpo-balanced-adv_8_64-w001-qwen2_5_vl_3b-step302 10 downloads, model
- LegendaryDawn/ablation-Qwen2-VL-7B-G0-adv20-2-12k 10 downloads, model
- LegendaryDawn/ean-nips-append_clean-n4_abs05-filter-adv_patch_zero50_rankmix20-dapo-n8-qwen2_5_vl_7b-step300 10 downloads, model
- LegendaryDawn/erpo-iclr-ablation-Qwen2.5-3b-corr_gen_s005_max12 10 downloads, model
- LegendaryDawn/ours_optune_iter0 10 downloads, feature extraction
- LegendaryDawn/Qwen2-VL-7b-G0-csr-iter0-12k 10 downloads, model
- LegendaryDawn/erpo-iclr-rebuttal-Qwen2.5-3B-corr_gen_s002_max12-step270-step270 9 downloads, model
- LegendaryDawn/erpo-Qwen2.5-3B-s002_max11-step180 9 downloads, model
- LegendaryDawn/mbpo-adv_dpo001-shard-adv_8_64_rankmix20-grpo-n5-qwen2_5_vl_3b-step300 9 downloads, model
- LegendaryDawn/erpo-iclr-baseline-Qwen2.5-3B-dapo 9 downloads, model
- LegendaryDawn/erpo-iclr-ablation-Qwen2.5-3b-corr_gen_s005_max14 9 downloads, model
- LegendaryDawn/mbpo-adv_neg_replace-adv_8_64_rankmix20-dapo-n8-qwen2_5_vl_3b-step300 9 downloads, model
- LegendaryDawn/ours_sft_iter0 9 downloads, feature extraction
- LegendaryDawn/erpo-iclr-Qwen2.5-7B-RA-step180 9 downloads, model
- LegendaryDawn/self-debate-exp-Qwen2.5-3B-diff_sol2048-overall_debate_grpo_loss-n8-bs256-long8-DAPO-step200 9 downloads, model
- LegendaryDawn/SDRL-freq-ablation-step125-Qwen3-4B-Base-icml-self-debate-majority_n8_l2048-DAPO_n8_bs256_long8 9 downloads, model
- LegendaryDawn/SDRL-rand-Qwen2.5-3B-icml-self-debate-ablation-random_n4_l2048-DAPO_n8_bs256_long8-step200 9 downloads, model
- LegendaryDawn/mbpo-adv_group_append_clean_abs05-adv_8_64_rankmix10-dapo-n8-qwen2_5_vl_3b-step300 8 downloads, model
- LegendaryDawn/mbpo-ablation-append_clean_abs05-filter-adv_patch_zero50_random20-3b-step300 8 downloads, model
- LegendaryDawn/ean-ablation-append_clean_abs05-filter-random_patch-rankmix20-3b-step300 8 downloads, model
- LegendaryDawn/erpo-iclr-Qwen2.5-3b-RA-reactivate_all_correct 8 downloads, model
- LegendaryDawn/SDRL-icml_rebuttal-freq-Qwen2.5-3B-majority_n8_l2048-DAPO_n8_bs256_long8-step200 8 downloads, model
- LegendaryDawn/SDRL-icml_rebuttal-2turn-freq-Qwen2.5-3B-majority_n4_l2048-DAPO_n8_bs256_long8-step200 8 downloads, model
- LegendaryDawn/mbpo-ablation-append_clean_abs05-filter-adv_patch_zero50_rankmix10-3b-step300 8 downloads, model
- LegendaryDawn/erpo-iclr-rebuttal-llama3.2-3B-Instruct-corr_gen_s002_max12-step180-step180 8 downloads, model
- LegendaryDawn/mbpo-adv_group_append_clean_abs01-adv_8_64_rankmix20-dapo-n8-qwen2_5_vl_3b-step300 8 downloads, model
- LegendaryDawn/mbpo-adv_group_append_clean_abs05-adv_8_64_rankmix30-dapo-n8-qwen2_5_vl_3b-step300 8 downloads, model
- LegendaryDawn/mbpo-baseline-dapo-qwen2_5_vl_3b-step300 8 downloads, model
- LegendaryDawn/self-debate-baseline-DAPO-Qwen2.5-3B-Instruct-n8-bs256-long8-step200 8 downloads, model
- LegendaryDawn/SDRL-baseline-Qwen3-4B-Base-GRPO-n8-bs256-long8-2-step200 8 downloads, model
- LegendaryDawn/mbpo-adv_group_append_clean_abs05-clip001-adv_8_64_rankmix20-dapo-n8-qwen2_5_vl_3b-step300 7 downloads, model
- LegendaryDawn/mbpo-baseline-dapo-n8-qwen2_5_vl_7b-step200 7 downloads, model
- LegendaryDawn/erpo-iclr-rebuttal-Qwen2.5-3B-baseline-dapo-step180-270-step90 7 downloads, model
- LegendaryDawn/baseline-LlavaOneVision-G0-povid-12k 7 downloads, model
- LegendaryDawn/ean-n4-abs05-filter-adv_patch_zero50_rankmix20-dapo-n8-qwen3_vl_8b-step150 7 downloads, model
- LegendaryDawn/mbpo-adv_group_append_clean_abs05-adv_8_64_rankmix20-dapo-n8-qwen2_5_vl_3b-step300 7 downloads, model
- LegendaryDawn/mbpo-append_clean_n2_abs05-filter-adv_patch_zero50_rankmix20-dapo-n8-qwen2_5_vl_7b-step300 7 downloads, model
- LegendaryDawn/mbpo-ablation-adv_group_append_clean_abs05-adv_8_64_rankmix20-dapo-n8-qwen2_5_vl_3b-step300 7 downloads, model
- LegendaryDawn/SDRL-freq-Qwen2.5-3B-icml-self-debate-exp-majority_n4_l2048-DAPO_n8_bs256_long8-step200 7 downloads, model
- LegendaryDawn/SDRL-freq-Qwen3-4B-Base-icml-self-debate-exp-majority_n8_l2048-DAPO_n8_bs256_long8-run2-step200 7 downloads, model
- LegendaryDawn/baseline-LlavaOneVision-G0-rlaifv-12k 7 downloads, model
- LegendaryDawn/SDRL-rand-Qwen3-4B-Base-icml-self-debate-random_n8_l2048-DAPO_n8_bs256_long8-step200 7 downloads, model
- LegendaryDawn/ean-baseline-dapo-n8-qwen3_vl_8b-step300 7 downloads, model
- LegendaryDawn/mbpo-baseline-dapo-n8-qwen2_5_vl_7b-step300 7 downloads, model
- LegendaryDawn/mbpo-baseline-grpo-qwen2_5_vl_3b-step302 7 downloads, model
- LegendaryDawn/mbpo-clean_negative_reweight-rank_power-adv_8_64-qwen2_5_vl_3b-step302 7 downloads, model
- LegendaryDawn/ablation-Qwen2_5-G0-Rmmseed-GPT4o-rand-12k 6 downloads, model
- LegendaryDawn/mbpo-adv_group_append_clean_abs05-clip02-filter-adv_8_64_rankmix10-dapo-n8-qwen2_5_vl_7b-step300 6 downloads, model
- LegendaryDawn/mbpo-adv_group_append_clean_abs05-clip02-filter-adv_8_64_rankmix30-7b-step300 6 downloads, model
- LegendaryDawn/mbpo-ablation-append_clean_abs05-filter-adv_patch_zero50_rankmix-category_20-3b-step300 6 downloads, model
- LegendaryDawn/mbpo-adv_group_append_clean_abs05-filter-adv_8_64_rankmix10-dapo-n8-qwen2_5_vl_3b-step300 6 downloads, model
- LegendaryDawn/mbpo-adv_group_append_clean_abs05-kl001-adv_8_64_rankmix20-dapo-n8-qwen2_5_vl_3b-step300 6 downloads, model
- LegendaryDawn/mbpo-adv_group_append_clean_abs05-clip01-adv_8_64_rankmix20-dapo-n8-qwen2_5_vl_3b-step300 6 downloads, model
- LegendaryDawn/self-debate-baseline-Qwen3-0.6B-Base-DAPO-n8_bs256_long8-mini32-step200 6 downloads, model
- LegendaryDawn/erpo-baseline-Qwen2.5-3B-grpo-step180 6 downloads, model
- LegendaryDawn/SDRL-rand-Qwen3-8B-Base-random_n8_l4096-DAPO_n8_bs256_long12-yarn2-step200 6 downloads, model
- LegendaryDawn/SDRL-baseline-Qwen3-8B-Base-DAPO-n8-bs256-long8-step200 5 downloads, model
- LegendaryDawn/ean-n4-abs05-filter-adv_patch_zero50_rankmix20-dapo-n8-qwen3_vl_8b-step300 5 downloads, model
- LegendaryDawn/mbpo-ablation-append_clean_abs05-filter-adv_patch_zero50_rankmix-bottom20-3b-step300 5 downloads, model
- LegendaryDawn/mbpo-append_clean_abs05-filter-adv_binary_patch50_rankmix20-3b-step300 5 downloads, model
- LegendaryDawn/mbpo-ablation-adv_group_append_clean_random_patch-filter-abs05-adv_8_64_rankmix20-3b-step300 5 downloads, model
- LegendaryDawn/ean-ablation-append_clean_abs05-filter-random_patch-rankmix20-7b-step300 5 downloads, model
- LegendaryDawn/mbpo-adv_group_append_clean_abs05-clip02-filter-entropy-0p001-adv_8_64_rankmix20-7b-step300 5 downloads, model
- LegendaryDawn/mbpo-adv_group_append_clean_abs05-n3-clip02-filter-adv_8_64_rankmix20-7b-step300 5 downloads, model