violetxi/sft_tir_rl_prep_Llama_lr0.0001_bs64_wd0.0_wp0.1_checkpoint-epoch1 Text Generation • 1B • Updated Feb 20 • 9
violetxi/sft_tir_rl_prep_Llama_lr0.0001_bs64_wd0.0_wp0.1_checkpoint-epoch0 Text Generation • 1B • Updated Feb 20 • 10
violetxi/sft_tir_rl_prep_Llama_lr1e-05_bs32_wd0.0_wp0.1_checkpoint-epoch2 Text Generation • 8B • Updated Feb 20 • 8
violetxi/sft_tir_rl_prep_Llama_lr1e-05_bs32_wd0.0_wp0.1_checkpoint-epoch0 Text Generation • 8B • Updated Feb 20 • 8
violetxi/sft_tir_3e-5_b32_warmup0.1_checkpoint-epoch2 Text Generation • 8B • Updated Dec 9, 2024 • 19 •
violetxi/ak-prm-full_sft-steptok_lr1e-5_wa0.03_wd0.01_epoch0 Text Generation • 8B • Updated Dec 8, 2024 • 14
violetxi/ak-prm-full_sft-steptok_lr1e-5_wa0.03_wd0.01_checkpoint12000 Text Generation • 8B • Updated Dec 8, 2024 • 58
violetxi/ak-prm-full_sft-steptok_lr1e-5_wa0.03_wd0.01_checkpoint6000 Text Generation • 8B • Updated Dec 8, 2024 • 40
violetxi/ak-prm-full_sft-steptok_lr1e-5_wa0.03_epoch0 Text Generation • 8B • Updated Dec 7, 2024 • 72
violetxi/ak-prm-full_sft-steptok_lr1e-5_wa0.03_checkpoint12000 Text Generation • 8B • Updated Dec 7, 2024 • 14