·
AI & ML interests
None yet
Organizations
None yet
realtreetune/r1d-1.5b_deepscaler_dlThnk_hpBase_clip0.25_lssAgg_ace-length_fxdOptStps_2_fltBchCorr
Updated
realtreetune/r1d-1.5b_deepscaler_delethink_hpBase_lossAgg_ace-length_fixedOptSteps_1_fltBchCorr__ckpt-000800
2B • Updated realtreetune/r1d-1.5b_deepscaler_grpo_24k_clip0.272_v2
realtreetune/r1d-1.5b_deepscaler_dlThnk_hpBase_clip0.26_lssAgg_ace-length_fxdOptStps_2_fltBchCorr
Updated
realtreetune/r1d-1.5b_deepscaler_dlThnk_clip0.26_lssAgg_ace-length_fxdOptStps_2_fltBchCorr_v2
Updated
realtreetune/r1d-1.5b_deepscaler_delethink_hpBase_lossAgg_ace-length_fixedOptSteps_1_fltBchCorr
Updated
realtreetune/r1d-1.5b_deepscaler_delethink_hpBase_lossAgg_ace-length_fixedOptSteps_1
Updated
realtreetune/r1d-1.5b_deepscaler_delethink_hpBase_dthTrim_annot_lossAgg_ace-length_fixedOptSteps_1
Updated
realtreetune/r1d-1.5b_deepscaler_grpo_24k_clip0.26
Updated
realtreetune/r1d-1.5b_deepscaler_dlThnk_hpBase_lssAgg_ace-length_fxdOptStps_1_temp_1.0
Updated
realtreetune/polIter_r1d-1.5b_deepscaler_delethink_tis_clip0.24_dthTrim_annot
Updated
realtreetune/polIter_r1d-1.5b_deepscaler_grpo_24k
Updated
realtreetune/polIter_r1d-1.5b_deepscaler_delethink_tis_clip0.24_True
Updated
realtreetune/polIter_r1d-1.5b_deepscaler_delethink_v2
Updated
realtreetune/test_upload_ckpt_22
Updated
realtreetune/test_model_upload222
Updated
realtreetune/test_upload_ckpt_2
Updated
realtreetune/test_model_upload
Updated
realtreetune/test_push_to_hub
Updated
realtreetune/r1d-deepscalerR-iter975-vppo
Text Generation
• 2B • Updated • 6
realtreetune/r1d-1b-deepmath-rspLen3500-iter0040
Text Generation
• 2B • Updated • 3
realtreetune/r1d-1b-deepmath-rspLen3500-iter120
Text Generation
• 2B • Updated • 7
realtreetune/rho-1b-sft-MATH-chat
Text Generation
• 1B • Updated • 2
• • 1
realtreetune/rho-1b-sft-MATH
Text Generation
• 1B • Updated • 164
• realtreetune/deepseekmath-7b-sft-GSM8K
Text Generation
• 7B • Updated • 1.62k
realtreetune/deepseekmath-7b-sft-MATH-v2
Text Generation
• 7B • Updated • 1.34k
realtreetune/rho-1b-sft-GSM8K
Text Generation
• 1B • Updated • 425
• realtreetune/rho-interpreter-1b-sft-MATH
Text Generation
• 1B • Updated • 6