rrvaswin on Hugging Face: downloads and rankings
rrvaswin has 127 tracked models, downloaded 955 times in the last 30 days and 15,641 times in total; 31 datasets, downloaded 3,548 times in the last 30 days. rrvaswin Wrapped: the last 12 months.
Models by downloads in the last 30 days
- rrvaswin/64b_SFT 19 downloads, model
- rrvaswin/1b_SFT 18 downloads, model
- rrvaswin/64b_RL_DAPO 18 downloads, model
- rrvaswin/32b_SFT 18 downloads, model
- rrvaswin/2b_SFT 18 downloads, model
- rrvaswin/qwen3_4b_rldecomp 17 downloads, text generation
- rrvaswin/64b_RL_DAPO_step250 17 downloads, model
- rrvaswin/64_v1_scalable 16 downloads, model
- rrvaswin/STaR_SFT 16 downloads, model
- rrvaswin/qwen_STaR_RL 15 downloads, model
- rrvaswin/64_v2_scalable 15 downloads, model
- rrvaswin/8b_SFT 15 downloads, model
- rrvaswin/2b_SFT_NEW 15 downloads, model
- rrvaswin/16b_RL_DAPO 14 downloads, model
- rrvaswin/64b_RL 14 downloads, model
- rrvaswin/4b_SFT_NEW 14 downloads, model
- rrvaswin/trl_SFT_32b_epoch2 14 downloads, model
- rrvaswin/qwen3_4b_rldecomp1 14 downloads, text generation
- rrvaswin/4b_SFT 13 downloads, model
- rrvaswin/32b_RL_DAPO 13 downloads, model
- rrvaswin/16b_RL 12 downloads, model
- rrvaswin/1b_RL_DAPO 12 downloads, model
- rrvaswin/32b_RL 12 downloads, model
- rrvaswin/llama3_2_3b_entropy_klcov0.002_b32_mb8_klp0_gsm8k_data 12 downloads, model
- rrvaswin/trl_SFT_66b_epoch1 11 downloads, model
- rrvaswin/2b_RL_DAPO 11 downloads, model
- rrvaswin/16b_SFT 11 downloads, model
- rrvaswin/trl_SFT_4b_epoch2 10 downloads, model
- rrvaswin/4b_RL_DAPO 10 downloads, model
- rrvaswin/llama3_2_3b_dapo_b16_mb4_klp0_gsm8k_data 10 downloads, model
- rrvaswin/trl_SFT_32b_epoch1 10 downloads, model
- rrvaswin/llama3_2_3b_grpo_b128_mb32_klp0.001_deep_math6.5d_data 10 downloads, model
- rrvaswin/PrayToGod6_k2_KL_adaptive_controller 10 downloads, model
- rrvaswin/trl_SFT_8b_epoch3 10 downloads, model
- rrvaswin/8b_SFT_NEW 10 downloads, model
- rrvaswin/llama3_2_3b_entropy_klcov0.002_b128_mb32_klp0_gsm8k_data 10 downloads, model
- rrvaswin/8b_RL_DAPO 10 downloads, model
- rrvaswin/Vanilla_RL_NEW 9 downloads, model
- rrvaswin/DAPO_GRPO_16b_incorrect_bs_32_mb_8_n16_cliphigh 9 downloads, model
- rrvaswin/llama3_2_3b_grpo_b16_mb4_klp0.001_7k_dapo_data 9 downloads, model
- rrvaswin/qwen_coder_3b_e2 9 downloads, model
- rrvaswin/llama3_2_3b_grpo_b64_mb16_klp0.001_gsm8k_data 9 downloads, model
- rrvaswin/Vanilla_RL 9 downloads, model
- rrvaswin/MT_1_to_16_step200 8 downloads, model
- rrvaswin/64b_RL_DAPO_v2 8 downloads, model
- rrvaswin/trl_SFT_16b_epoch2 8 downloads, model
- rrvaswin/llama3_2_3b_grpo_b32_mb8_klp0.001_gsm8k_data 8 downloads, model
- rrvaswin/llama3_2_3b_dapo_b128_mb32_klp0_gsm8k_data 8 downloads, model
- rrvaswin/llama3_2_3b_entropy_klcov0.002_b16_mb4_klp0_gsm8k_data 8 downloads, model
- rrvaswin/trl_SFT_16b_epoch1 8 downloads, model
- rrvaswin/llama3_2_3b_dapo_b64_mb16_klp0_gsm8k_data 8 downloads, model
- rrvaswin/DAPO_Llama_3.2_3B_InT_bs_32_mb_8_n16 8 downloads, model
- rrvaswin/trl_SFT_2b_epoch3 8 downloads, model
- rrvaswin/sefcom_judge_v2 8 downloads, model
- rrvaswin/llama3_2_3b_grpo_b16_mb4_klp0.001_gsm8k_data 8 downloads, model
- rrvaswin/qwen_star_baseline 8 downloads, model
- rrvaswin/trl_SFT_4b_epoch3 8 downloads, model
- rrvaswin/qwen_coder_3b_e3 8 downloads, model
- rrvaswin/4b_RL 8 downloads, model
- rrvaswin/llama3_2_3b_grpo_b128_mb32_klp0.001_gsm8k_data 8 downloads, model
- rrvaswin/trl_SFT_16b_epoch3 8 downloads, model
- rrvaswin/trl_SFT_8b_epoch1 8 downloads, model
- rrvaswin/llama-3.2-3b-grpo 8 downloads, model
- rrvaswin/trl_SFT_2b_epoch2 8 downloads, model
- rrvaswin/STaR_RL_DAPO 8 downloads, model
- rrvaswin/trl_SFT_8b_epoch2 8 downloads, model
- rrvaswin/llama3_2_3b_entropy_klcov0.002_b64_mb16_klp0_gsm8k_data 7 downloads, model
- rrvaswin/DAPO_GRPO_8b_incorrect_bs_32_mb_8_n16_cliphigh 7 downloads, model
- rrvaswin/trl_SFT_4b_epoch1 7 downloads, model
- rrvaswin/16b_RL_NEW 7 downloads, model
- rrvaswin/trl_SFT_2b_epoch1 7 downloads, model
- rrvaswin/1_to_1_analysis 7 downloads, model
- rrvaswin/qwen2p5_test_sft_vfree 6 downloads, model
- rrvaswin/llama3_2_3b_dapo_wo_ds_b16_mb4_klp0_7k_dapo_data 6 downloads, model
- rrvaswin/llama3_2_3b_grpo_b64_mb16_klp0.001_7k_dapo_data 6 downloads, model
- rrvaswin/DAPO_GRPO_2b_incorrect_bs_32_mb_8_n16_cliphigh 5 downloads, model
- rrvaswin/Llama_SFT_8behaviors_445steps_lr5e-6_epoch1 5 downloads, model
- rrvaswin/sefcom_llmjudge1 5 downloads, model
- rrvaswin/DAPO_Llama_3.2_3B_base_VanillaRL_bs_32_mb_8_n16 5 downloads, model
- rrvaswin/2b_RL 5 downloads, model
- rrvaswin/qwen_32b_RL 5 downloads, model
- rrvaswin/qwen_8b_RL 5 downloads, model
- rrvaswin/qwen_1b_SFT 5 downloads, model
- rrvaswin/DAPO_Llama_3.2_3B_16b_bs_32_mb_8_n16 5 downloads, model
- rrvaswin/DAPO_GRPO_4b_incorrect_bs_32_mb_8_n16_cliphigh 5 downloads, model
- rrvaswin/Llama_SFT_4behaviors_445steps_lr5e-6_epoch1 4 downloads, model
- rrvaswin/llama3_2_3b_grpo_b32_mb8_klp0.001_7k_dapo_data 4 downloads, model
- rrvaswin/16b_SFT_NEW 4 downloads, model
- rrvaswin/grpo_dapo_math_7k_data_b128_mb32 4 downloads, model
- rrvaswin/Llama_SFT_65behaviors_452steps_lr5e-6_epoch1 4 downloads, model
- rrvaswin/llama3_2_3b_dapo_b32_mb8_klp0_gsm8k_data 4 downloads, model
- rrvaswin/Llama_SFT_1behaviors_445steps_lr5e-6_epoch1 4 downloads, model
- rrvaswin/Llama-3.2-3B-Instruct_adv_b16_mb4_dm_6.5d_klbc_0.0009_entbc_0.001_tlr5e-7_slr1e-6 4 downloads, model
- rrvaswin/RL4DecompLMjudge2 4 downloads, model
- rrvaswin/Llama_SFT_16behaviors_445steps_lr5e-6_epoch1 4 downloads, model
- rrvaswin/1_to_16_analysis 4 downloads, model
- rrvaswin/qwen_coder_3b_e1 4 downloads, model
- rrvaswin/llama-3.2-3b-SFT 4 downloads, model
- rrvaswin/llama-3.2-3b-STaR 4 downloads, model
- rrvaswin/b128_advthinking_klp_sig_14times8xminus1_t32mb_s4mb_highent_detach_grad 4 downloads, model
Datasets by downloads in the last 30 days
- rrvaswin/hle-math 2.4K downloads
- rrvaswin/qwen_2.5_behaviors_5k 322 downloads
- rrvaswin/qwen_2.5_behaviors 228 downloads
- rrvaswin/deepmath_advthinking 120 downloads
- rrvaswin/behaviors_65_5.2k 52 downloads
- rrvaswin/analysis_1_to_16 47 downloads
- rrvaswin/behaviors_66_7k_llamagen 44 downloads
- rrvaswin/65b_rewarded_top16 37 downloads
- rrvaswin/65b_rewarded 36 downloads
- rrvaswin/behaviors_66_7k_llamagen_diverse 36 downloads
- rrvaswin/behaviors_66_4.81k 35 downloads
- rrvaswin/16b_diverse_gm 28 downloads
- rrvaswin/16b_math_openr1 25 downloads
- rrvaswin/analysis_1_to_1 14 downloads
- rrvaswin/rewarded_16b_gsm8k_incorrect 13 downloads
- rrvaswin/qwq32b_distill_data 13 downloads
- rrvaswin/dapo_qwen3_inst_stats 11 downloads
- rrvaswin/16b_diverse_m 9 downloads
- rrvaswin/16b_diverse 9 downloads
- rrvaswin/qwen2.5_star 8 downloads
- rrvaswin/hmmt-25 7 downloads
- rrvaswin/llama_star_messages 6 downloads
- rrvaswin/QwQ_64b_Distill 6 downloads
- rrvaswin/_5_turns_only_ckp_2 5 downloads
- rrvaswin/cog_behaviors 5 downloads
- rrvaswin/_5_turns_only_ckp_1 5 downloads
- rrvaswin/_5_turns_only_ckp_0 5 downloads
- rrvaswin/openr1-verifiable_8k 4 downloads
- rrvaswin/llama_star 3 downloads
- rrvaswin/polaris_10k 2 downloads
- rrvaswin/qwq32b_distill_data_1 2 downloads
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.