YYYYYYibo on Hugging Face: downloads and rankings
YYYYYYibo has 93 tracked models, downloaded 1,006 times in the last 30 days and 3,691 times in total; 353 datasets, downloaded 5,770 times in the last 30 days. YYYYYYibo Wrapped: the last 12 months.
Models by downloads in the last 30 days
- YYYYYYibo/qwen3-4b-questa-nonmcq-estep-pos20-neg20-truncneg20-step50 169 downloads, text generation
- YYYYYYibo/qwen3-4b-dapo-estep-pos5-neg5-truncneg5-b256-step50 40 downloads, model
- YYYYYYibo/zephyr-7b-dpo-qlora-min-pi-part-0 30 downloads, model
- YYYYYYibo/imp_sam_iter_2 20 downloads, model
- YYYYYYibo/full_vanilla_dpo_iter_1 18 downloads, text generation
- YYYYYYibo/gshf_iter_3 17 downloads, text generation
- YYYYYYibo/approx_nash_3temp_iter_2 16 downloads, text generation
- YYYYYYibo/two_agent_1_epoch_2_dpo_iter_6 15 downloads, model
- YYYYYYibo/nash_dpo_merge_iter_real_plus_3 15 downloads, model
- YYYYYYibo/two_agent_dpo_iter_2 14 downloads, text generation
- YYYYYYibo/zephyr-7b-dpo-qlora-training-on-full-binary 14 downloads, model
- YYYYYYibo/nash_real_rank4_all_iter_2 14 downloads, model
- YYYYYYibo/nash_dpo_doff_no_golden_iter_3 13 downloads, model
- YYYYYYibo/Qwen3-4B-Teacher-Penalty-PPO-Step25 13 downloads, model
- YYYYYYibo/two_agent_rdpo_iter_2 13 downloads, text generation
- YYYYYYibo/nash_dpo_merge_iter_2 13 downloads, model
- YYYYYYibo/approx_nash_rdpo_iter_2 13 downloads, model
- YYYYYYibo/full_vanilla_dpo_iter_2 12 downloads, text generation
- YYYYYYibo/imp_sam_1_iter_2 12 downloads, model
- YYYYYYibo/approx_nash_maxmin_iter_3 11 downloads, text generation
- YYYYYYibo/nash_dpo_rank4_on_vanilla_iter_3 11 downloads, model
- YYYYYYibo/nash_dpo_merge_iter_6 11 downloads, model
- YYYYYYibo/full_vanilla_doff_dpo_iter_2 11 downloads, text generation
- YYYYYYibo/gshf_iter_2 11 downloads, text generation
- YYYYYYibo/vanilla_dpo_iter_2 11 downloads, model
- YYYYYYibo/vanilla_dpo_iter_3 11 downloads, model
- YYYYYYibo/nash_dpo_rank4_on_vanilla_iter_1 10 downloads, model
- YYYYYYibo/vanilla_dpo_iter_1 10 downloads, model
- YYYYYYibo/approx_nash_1_iter_3 10 downloads, text generation
- YYYYYYibo/gshf_lora_iter_1 10 downloads, model
- YYYYYYibo/zephyr-7b-lora-64-no-quant-2k 10 downloads, model
- YYYYYYibo/gshf_ours_1_iter_2 10 downloads, model
- YYYYYYibo/approx_nash_3temp_iter_3 10 downloads, text generation
- YYYYYYibo/nash_dpo_rank4_iter_3 10 downloads, model
- YYYYYYibo/nash_ave_pi_iter_1 10 downloads, model
- YYYYYYibo/full_vanilla_doff_dpo_iter_1 10 downloads, text generation
- YYYYYYibo/full_simple_online_iter_3 10 downloads, text generation
- YYYYYYibo/nash_dpo_doff_real_no_golden_iter_3 10 downloads, model
- YYYYYYibo/full_vanilla_dpo_iter_3 10 downloads, text generation
- YYYYYYibo/approx_nash_maxmin_iter_2 10 downloads, text generation
- YYYYYYibo/nash_dpo_doff_real_no_golden_iter_1 10 downloads, model
- YYYYYYibo/nash_dpo_rank4_iter_real_plus_3 10 downloads, model
- YYYYYYibo/full_vanilla_doff_dpo_iter_3 9 downloads, text generation
- YYYYYYibo/imp_sam_1_iter_1 9 downloads, model
- YYYYYYibo/approx_nash_1_iter_2 9 downloads, text generation
- YYYYYYibo/two_agent_dpo_iter_3 9 downloads, text generation
- YYYYYYibo/nash_dpo_doff_no_golden_iter_1 9 downloads, model
- YYYYYYibo/nash_dpo_merge_iter_3 8 downloads, model
- YYYYYYibo/gshf_lora_iter_2 8 downloads, model
- YYYYYYibo/vanilla_doff_dpo_iter_1 8 downloads, model
- YYYYYYibo/nash_dpo_rank4_iter_2 8 downloads, model
- YYYYYYibo/nash_dpo_merge_iter_4 8 downloads, model
- YYYYYYibo/selm_ours_iter_2 8 downloads, model
- YYYYYYibo/zephyr-7b-lora-64-no-quant-all 8 downloads, model
- YYYYYYibo/vanilla_doff_dpo_iter_2 8 downloads, model
- YYYYYYibo/nash_rank4_all_iter_3 8 downloads, model
- YYYYYYibo/two_agent_iter_1 8 downloads, text generation
- YYYYYYibo/nash_rank4_all_iter_2 8 downloads, model
- YYYYYYibo/nash_dpo_iter_1 8 downloads, model
- YYYYYYibo/approx_nash_again_iter_2 7 downloads, model
- YYYYYYibo/selm_ours_1_iter_2 7 downloads, model
- YYYYYYibo/nash_simple_online_iter_1 7 downloads, model
- YYYYYYibo/vanilla_doff_iter_3 7 downloads, model
- YYYYYYibo/two_agent_1_rdpo_iter_3 7 downloads, model
- YYYYYYibo/nash_ave_pi_with_golden_iter_3 7 downloads, model
- YYYYYYibo/gshf_ours_iter_2 6 downloads, model
- YYYYYYibo/nash_simple_online_iter_3 6 downloads, model
- YYYYYYibo/imp_sam_iter_1 6 downloads, model
- YYYYYYibo/nash_ave_pi_with_golden_iter_1 6 downloads, model
- YYYYYYibo/imp_sam_1_iter_3 6 downloads, model
- YYYYYYibo/imp_sam_iter_3 6 downloads, model
- YYYYYYibo/simple_online_epoch_2_dpo_iter_4 6 downloads, model
- YYYYYYibo/two_agent_1_epoch_2_dpo_iter_5 6 downloads, model
- YYYYYYibo/two_agent_2_rdpo_iter_3 6 downloads, model
- YYYYYYibo/simple_online_epoch_2_dpo_iter_6 5 downloads, model
- YYYYYYibo/olmo3-7b-openthoughts-estep-pos5-neg5 5 downloads, model
- YYYYYYibo/two_agent_2_dpo_iter_2 5 downloads, model
- YYYYYYibo/two_agent_1_epoch_2_rdpo_iter_5 5 downloads, model
- YYYYYYibo/qwen2-7b-grpo-replay-hard-25percent-0326 3 downloads, model
- YYYYYYibo/two_agent_1_epoch_2_rdpo_iter_6 3 downloads, model
- YYYYYYibo/two_agent_rdpo_iter_3 3 downloads, model
- YYYYYYibo/simple_online_epoch_2_dpo_iter_5 3 downloads, model
- YYYYYYibo/qwen2_7b_grpo_replay_hard_40percent_0326_0024 3 downloads, model
- YYYYYYibo/two_agent_1_epoch_2_rdpo_iter_4 3 downloads, model
- YYYYYYibo/approx_nash_rdpo_iter_3 3 downloads, model
- YYYYYYibo/selm_ours_1_iter_3 3 downloads, model
- YYYYYYibo/qwen2_7b_grpo_vanilla_0325_1257 3 downloads, model
- YYYYYYibo/gshf_ours_1_iter_3 3 downloads, model
- YYYYYYibo/two_agent_1_dpo_iter_3 3 downloads, model
- YYYYYYibo/approx_nash_again_1_iter_2 2 downloads, model
- YYYYYYibo/approx_nash_again_iter_3 2 downloads, model
- YYYYYYibo/approx_nash_again_1_iter_3 2 downloads, model
- YYYYYYibo/qwen2_5_7b_sft_baseline 2 downloads, model
Datasets by downloads in the last 30 days
- YYYYYYibo/DAPO-Math-17k-Qwen3-235B-A22B-Thinking-2507-non-thinking-dedup 190 downloads
- YYYYYYibo/qwen3-8b-base-deepscaler-rollouts 58 downloads
- YYYYYYibo/ultrafeedback_binarized_with_response_full_labeled_part_5 55 downloads
- YYYYYYibo/VSR-MATH500-Qwen2.5-7B-Rollouts 54 downloads
- YYYYYYibo/alfworld-experimenter-gpt5mini-sft-1k 54 downloads
- YYYYYYibo/QuestA-OpenR1-Math-220k-Joined 47 downloads
- YYYYYYibo/alfworld-expert-prefix-rollouts 45 downloads
- YYYYYYibo/openr1-math-220k-length-filtered-4k 45 downloads
- YYYYYYibo/full_simple_online_vllm_part_3 43 downloads
- YYYYYYibo/ultrafeedback_binarized_train_part_2 42 downloads
- YYYYYYibo/ultrafeedback_binarized_simple_online_train_part_1 42 downloads
- YYYYYYibo/ultrafeedback_binarized_train_part_3 36 downloads
- YYYYYYibo/full_simple_online_vllm_part_3_mini_3 36 downloads
- YYYYYYibo/openr1_math_train_with_qwen_evals 35 downloads
- YYYYYYibo/ultrafeedback_binarized_epoch_2_vllm_part_3 35 downloads
- YYYYYYibo/ultrafeedback_binarized_gshf_lora_train_part_3 33 downloads
- YYYYYYibo/ultrafeedback_binarized_epoch_2_train_part_3 33 downloads
- YYYYYYibo/ultrafeedback_binarized_dataset_offline_part0 33 downloads
- YYYYYYibo/ultrafeedback_binarized_with_response_full_part2 32 downloads
- YYYYYYibo/ultrafeedback_binarized_new_gen_part_3 32 downloads
- YYYYYYibo/ultrafeedback_binarized_ave_pi_with_golden_train_part_3_mini_0 32 downloads
- YYYYYYibo/ultrafeedback_binarized_dataset_offline_pairrm_part1 31 downloads
- YYYYYYibo/ultrafeedback_binarized_with_response_full_labeled_part_0 31 downloads
- YYYYYYibo/ultrafeedback_binarized_real_rank4_all_train_part_2 30 downloads
- YYYYYYibo/ultrafeedback_binarized_minpi_part_3 30 downloads
- YYYYYYibo/ultrafeedback_binarized_dataset_offline_part2 29 downloads
- YYYYYYibo/ultrafeedback_binarized_plus_left_part_3 29 downloads
- YYYYYYibo/ultrafeedback_binarized_with_response_full_labeled_part_4 28 downloads
- YYYYYYibo/ultrafeedback_binarized_with_response_full_labeled_part_1 28 downloads
- YYYYYYibo/ultrafeedback_binarized_epoch_2_left_part_1 28 downloads
- YYYYYYibo/qwen3-4b-nonthinking-skywork-rollouts-verified 28 downloads
- YYYYYYibo/ultrafeedback_binarized_dataset_offline_pairrm_part2 27 downloads
- YYYYYYibo/ultrafeedback_binarized_simple_online_vllm_part_3 27 downloads
- YYYYYYibo/ultrafeedback_binarized_ave_pi_with_golden_train_part_2 27 downloads
- YYYYYYibo/ultrafeedback_binarized_left_part_3 27 downloads
- YYYYYYibo/ultrafeedback_binarized_dataset_offline_pairrm_part0 26 downloads
- YYYYYYibo/ultrafeedback_binarized_simple_online_vllm_part_3_mini_2 26 downloads
- YYYYYYibo/gshf_train_part_2_mini_0 26 downloads
- YYYYYYibo/full_simple_online_train_part_3 26 downloads
- YYYYYYibo/ultrafeedback_binarized_epoch_2_train_part_1 26 downloads
- YYYYYYibo/ultrafeedback_binarized_with_response_full_part1 26 downloads
- YYYYYYibo/ultrafeedback_binarized_epoch_2_left_part_3 26 downloads
- YYYYYYibo/ultrafeedback_binarized_imp_sam_minpi_2_part_2 25 downloads
- YYYYYYibo/ultrafeedback_binarized_real_rank4_all_train_part_3 25 downloads
- YYYYYYibo/ultrafeedback_binarized_imp_sam_minpi_1_part_3 25 downloads
- YYYYYYibo/ultrafeedback_binarized_doff_no_golden_train_part_2_mini_2 24 downloads
- YYYYYYibo/ultrafeedback_binarized_gshf_lora_train_part_2 24 downloads
- YYYYYYibo/full_simple_online_vllm_part_3_mini_5 24 downloads
- YYYYYYibo/ultrafeedback_binarized_dataset_offline_pairrm_part1_mini_2 24 downloads
- YYYYYYibo/full_simple_online_train_part_2 24 downloads
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.