xiaoyuanliu on Hugging Face: downloads and rankings
xiaoyuanliu has 74 tracked models, downloaded 922 times in the last 30 days and 3,441 times in total; 72 datasets, downloaded 1,767 times in the last 30 days. xiaoyuanliu Wrapped: the last 12 months.
Models by downloads in the last 30 days
- xiaoyuanliu/Qwen2.5-3B-simplerl-ppo-6k-bs012 21 downloads, text generation
- xiaoyuanliu/Qwen2.5-3B-simplerl-ppo-verifier 20 downloads, text generation
- xiaoyuanliu/Qwen3-8B-SFT-V2.1-ml.16K-lr.1e-5-ep.3 19 downloads, text generation
- xiaoyuanliu/Qwen2.5-7B-simplerl-ppo-online.critique-012-6k-es 17 downloads, text generation
- xiaoyuanliu/Qwen2.5-1.5B-simplerl-ppo-offline.critique-012-bs012 16 downloads, text generation
- xiaoyuanliu/Qwen2.5-3B-BBH-PPO-RISE-Step60 16 downloads, text generation
- xiaoyuanliu/Qwen2.5-3B-simplerl-ppo-offline.critique-012-6k 16 downloads, text generation
- xiaoyuanliu/Qwen2.5-1.5B-simplerl-ppo 15 downloads, text generation
- xiaoyuanliu/StateLM-8B-SFT 15 downloads, text generation
- xiaoyuanliu/StateLM-8B-RL-0123-CKPT32 15 downloads, text generation
- xiaoyuanliu/Qwen2.5-3B-simplerl-ppo-online.critique-012-1k 15 downloads, text generation
- xiaoyuanliu/Qwen3-30B-A3B-SFT-V4_OPT 15 downloads, text generation
- xiaoyuanliu/Qwen2.5-3B-simplerl-ppo-critique-100 15 downloads, text generation
- xiaoyuanliu/Qwen2.5-7B-simplerl-ppo-online.critique-012-6k 15 downloads, text generation
- xiaoyuanliu/Qwen2.5-7B-simplerl-ppo-offline.critique-012-bs012 15 downloads, text generation
- xiaoyuanliu/Qwen2.5-1.5B-simplerl-ppo-online.critique-012-1k 15 downloads, text generation
- xiaoyuanliu/Qwen2.5-7B-simplerl-ppo-offline.critique-100 14 downloads, text generation
- xiaoyuanliu/Qwen2.5-7B-simplerl-ppo-online.critique-025 14 downloads, text generation
- xiaoyuanliu/Qwen2.5-3B-simplerl-ppo-critique-012 14 downloads, text generation
- xiaoyuanliu/Qwen3-4B-SFT-V2.1-ml.16K-lr.1e-5-ep.3 14 downloads, text generation
- xiaoyuanliu/Qwen2.5-3B-simplerl-ppo-online.critique-012-ver.len-p3 14 downloads, text generation
- xiaoyuanliu/Qwen2.5-7B-Instruct-DeepMath10K-PPO 14 downloads, text generation
- xiaoyuanliu/Qwen2.5-1.5B-simplerl-ppo-verifier 14 downloads, text generation
- xiaoyuanliu/Qwen2.5-7B-simplerl-ppo-bs012 14 downloads, text generation
- xiaoyuanliu/StateLM-4B-SFT 14 downloads, text generation
- xiaoyuanliu/Qwen2.5-1.5B-simplerl-ppo-online.critique-025-3k 14 downloads, text generation
- xiaoyuanliu/Qwen2.5-3B-BBH-PPO-RISE 13 downloads, text generation
- xiaoyuanliu/Qwen2.5-3B-LogiQA-PPO-Step84 13 downloads, text generation
- xiaoyuanliu/Qwen2.5-7B-simplerl-ppo-online.critique-012-ec003 13 downloads, text generation
- xiaoyuanliu/Qwen2.5-7B-simplerl-ppo-online.critique-012-mini256 13 downloads, text generation
- xiaoyuanliu/Qwen2.5-7B-Instruct-MathHard-PPO-012 13 downloads, text generation
- xiaoyuanliu/Qwen2.5-3B-simplerl-ppo-online.critique-012-p2 13 downloads, text generation
- xiaoyuanliu/Qwen2.5-1.5B-simplerl-ppo-3k-bs012 13 downloads, text generation
- xiaoyuanliu/StateLM-14B-SFT 13 downloads, text generation
- xiaoyuanliu/Qwen2.5-7B-simplerl-ppo-verifier 13 downloads, text generation
- xiaoyuanliu/Qwen2.5-3B-simplerl-grpo 12 downloads, text generation
- xiaoyuanliu/Qwen2.5-3B-simplerl-grpo-online.critique-025 12 downloads, text generation
- xiaoyuanliu/Qwen2.5-7B-simplerl-ppo 12 downloads, text generation
- xiaoyuanliu/Qwen2.5-7B-simplerl-ppo-online.critique-100-6k 12 downloads, text generation
- xiaoyuanliu/Qwen2.5-7B-simplerl-ppo-critique-050 12 downloads, text generation
- xiaoyuanliu/Qwen2.5-3B-simplerl-ppo-offline.critique-012-bs012 12 downloads, text generation
- xiaoyuanliu/Qwen2.5-1.5B-simplerl-ppo-online.critique-012-2k 12 downloads, text generation
- xiaoyuanliu/Qwen2.5-3B-simplerl-ppo-6k 12 downloads, text generation
- xiaoyuanliu/Qwen2.5-7B-simplerl-ppo-critique-025 12 downloads, text generation
- xiaoyuanliu/Qwen2.5-7B-simplerl-ppo-critique-012 12 downloads, text generation
- xiaoyuanliu/Qwen2.5-7B-BBH-PPO-RISE 12 downloads, text generation
- xiaoyuanliu/Qwen2.5-3B-simplerl-ppo-online.critique-012-ver.len 12 downloads, text generation
- xiaoyuanliu/Qwen2.5-1.5B-simplerl-ppo-online.critique-100-3k 12 downloads, text generation
- xiaoyuanliu/Qwen2.5-3B-simplerl-ppo-online.critique-025 12 downloads, text generation
- xiaoyuanliu/Qwen2.5-3B-simplerl-ppo-critique-025 12 downloads, text generation
- xiaoyuanliu/Qwen2.5-3B-simplerl-ppo-offline.critique-100-6k 12 downloads, text generation
- xiaoyuanliu/Qwen2.5-7B-simplerl-ppo-online.critique-012-p2 12 downloads, text generation
- xiaoyuanliu/Qwen2.5-3B-simplerl-ppo-offline.critique-050-6k 11 downloads, text generation
- xiaoyuanliu/Qwen2.5-7B-simplerl-ppo-baseline-3.0k 11 downloads, text generation
- xiaoyuanliu/StateLM-14B-RL-0124-CKPT32 11 downloads, text generation
- xiaoyuanliu/Qwen2.5-1.5B-simplerl-ppo-offline.critique-012 11 downloads, text generation
- xiaoyuanliu/Qwen2.5-7B-simplerl-ppo-online.critique-100 11 downloads, text generation
- xiaoyuanliu/Qwen2.5-3B-LogiQA-PPO-RISE 11 downloads, text generation
- xiaoyuanliu/Qwen2.5-3B-LogiQA-PPO-RISE-Step84 11 downloads, text generation
- xiaoyuanliu/Qwen2.5-7B-simplerl-ppo-online.critique-050 11 downloads, text generation
- xiaoyuanliu/Qwen2.5-3B-simplerl-ppo-online.critique-012-3k 11 downloads, text generation
- xiaoyuanliu/Qwen2.5-3B-BBH-PPO-Step60 11 downloads, text generation
- xiaoyuanliu/Qwen2.5-3B-simplerl-ppo-critique-050 10 downloads, text generation
- xiaoyuanliu/Qwen2.5-3B-BBH-PPO 10 downloads, text generation
- xiaoyuanliu/Qwen2.5-7B-Instruct-MathHard-PPO-RISE012 9 downloads, text generation
- xiaoyuanliu/Qwen2.5-3B-LogiQA-PPO 9 downloads, text generation
- xiaoyuanliu/Qwen2.5-1.5B-simplerl-ppo-online.critique-012 8 downloads, text generation
- xiaoyuanliu/Qwen3-4B-Base-DeepMath10K-PPO-SV 8 downloads, model
- xiaoyuanliu/Qwen2.5-1.5B-simplerl-ppo-online.critique-012-3k 8 downloads, text generation
- xiaoyuanliu/Qwen2.5-7B-BBH-PPO 7 downloads, text generation
- xiaoyuanliu/Qwen2.5-7B-simplerl-ppo-online.critique-012-3k 7 downloads, text generation
- xiaoyuanliu/Qwen2.5-3B-simplerl-ppo-critique-025-longp 6 downloads, text generation
- xiaoyuanliu/Qwen2.5-3B-simplerl-ppo 5 downloads, model
- xiaoyuanliu/Qwen3-4B-Base-DeepMath10K-PPO 4 downloads, model
Datasets by downloads in the last 30 days
- xiaoyuanliu/logiqa 541 downloads
- xiaoyuanliu/ruler-niah 69 downloads
- xiaoyuanliu/memantine_sep 67 downloads
- xiaoyuanliu/math-gen-critique 67 downloads
- xiaoyuanliu/claude4-agentic-samples-V3 62 downloads
- xiaoyuanliu/conflict_vis 58 downloads
- xiaoyuanliu/AIME90 55 downloads
- xiaoyuanliu/bbh_rl 35 downloads
- xiaoyuanliu/memantine_train 33 downloads
- xiaoyuanliu/claude4-agentic-samples-V3-ds 31 downloads
- xiaoyuanliu/MATH 23 downloads
- xiaoyuanliu/claude4_agentic_samples 23 downloads
- xiaoyuanliu/ruler-niah-single 22 downloads
- xiaoyuanliu/olympiadbench 20 downloads
- xiaoyuanliu/HELMET_alce_qampari_700_qampari_eval_gtr_top2000_eval 20 downloads
- xiaoyuanliu/claude4-agentic-samples-V4-opt 20 downloads
- xiaoyuanliu/claude4-agentic-samples-V4-mix 19 downloads
- xiaoyuanliu/OMI2_augmented_math20K 19 downloads
- xiaoyuanliu/DeepMath-10K 19 downloads
- xiaoyuanliu/HELMET_kilt_popqa_3_popqa_test_1000_k1000_dep6_eval 18 downloads
- xiaoyuanliu/HELMET_kilt_triviaqa_triviaqa-dev-multikilt_1000_k1000_dep6_eval 18 downloads
- xiaoyuanliu/claude4-agentic-samples-V4-Balanced 18 downloads
- xiaoyuanliu/HELMET_alce_asqa_700_asqa_eval_gtr_top2000_eval 17 downloads
- xiaoyuanliu/claude4-agentic-samples-V4-sm 17 downloads
- xiaoyuanliu/claude4-agentic-samples-V4-1K 17 downloads
- xiaoyuanliu/longmemeval-s-50 16 downloads
- xiaoyuanliu/gsm8k 16 downloads
- xiaoyuanliu/InfiniteBench_QA 16 downloads
- xiaoyuanliu/HELMET_kilt_nq_nq-dev-multikilt_1000_k1000_dep6_eval 16 downloads
- xiaoyuanliu/claude4-agentic-samples-V4-add 16 downloads
- xiaoyuanliu/MMLU-Pro 16 downloads
- xiaoyuanliu/LongBench-v2-verified 15 downloads
- xiaoyuanliu/simplerl-critique-offline 13 downloads
- xiaoyuanliu/claude4-agentic-samples-V4-opt-swift-format 13 downloads
- xiaoyuanliu/lca_trajectories_32k 13 downloads
- xiaoyuanliu/AIME_2024 13 downloads
- xiaoyuanliu/HELMET_kilt_hotpotqa_hotpotqa-dev-multikilt_1000_k1000_dep3_eval 13 downloads
- xiaoyuanliu/HELMET_icl_banking77_5900shot_balance__eval 12 downloads
- xiaoyuanliu/LongBench-v2-rlvr 12 downloads
- xiaoyuanliu/HELMET_icl_clinic150_7050shot_balance__eval 12 downloads
- xiaoyuanliu/HELMET_ruler_niah_mv_validation_131072_eval 11 downloads
- xiaoyuanliu/claude4-agentic-samples-V4-opt-swift-format-500 10 downloads
- xiaoyuanliu/HELMET_ruler_niah_mk_3_validation_131072_eval 10 downloads
- xiaoyuanliu/claude4-agentic-samples-V3-200 10 downloads
- xiaoyuanliu/AIME_2025 10 downloads
- xiaoyuanliu/amc23 10 downloads
- xiaoyuanliu/longmemeval-s 10 downloads
- xiaoyuanliu/agentic_samples 10 downloads
- xiaoyuanliu/V4-BAScan-Warmup360 10 downloads
- xiaoyuanliu/LongBench-v2-small 10 downloads