| *.7z filter=lfs diff=lfs merge=lfs -text | |
| *.arrow filter=lfs diff=lfs merge=lfs -text | |
| *.bin filter=lfs diff=lfs merge=lfs -text | |
| *.bz2 filter=lfs diff=lfs merge=lfs -text | |
| *.ckpt filter=lfs diff=lfs merge=lfs -text | |
| *.ftz filter=lfs diff=lfs merge=lfs -text | |
| *.gz filter=lfs diff=lfs merge=lfs -text | |
| *.h5 filter=lfs diff=lfs merge=lfs -text | |
| *.joblib filter=lfs diff=lfs merge=lfs -text | |
| *.lfs.* filter=lfs diff=lfs merge=lfs -text | |
| *.mlmodel filter=lfs diff=lfs merge=lfs -text | |
| *.model filter=lfs diff=lfs merge=lfs -text | |
| *.msgpack filter=lfs diff=lfs merge=lfs -text | |
| *.npy filter=lfs diff=lfs merge=lfs -text | |
| *.npz filter=lfs diff=lfs merge=lfs -text | |
| *.onnx filter=lfs diff=lfs merge=lfs -text | |
| *.ot filter=lfs diff=lfs merge=lfs -text | |
| *.parquet filter=lfs diff=lfs merge=lfs -text | |
| *.pb filter=lfs diff=lfs merge=lfs -text | |
| *.pickle filter=lfs diff=lfs merge=lfs -text | |
| *.pkl filter=lfs diff=lfs merge=lfs -text | |
| *.pt filter=lfs diff=lfs merge=lfs -text | |
| *.pth filter=lfs diff=lfs merge=lfs -text | |
| *.rar filter=lfs diff=lfs merge=lfs -text | |
| *.safetensors filter=lfs diff=lfs merge=lfs -text | |
| saved_model/**/* filter=lfs diff=lfs merge=lfs -text | |
| *.tar.* filter=lfs diff=lfs merge=lfs -text | |
| *.tar filter=lfs diff=lfs merge=lfs -text | |
| *.tflite filter=lfs diff=lfs merge=lfs -text | |
| *.tgz filter=lfs diff=lfs merge=lfs -text | |
| *.wasm filter=lfs diff=lfs merge=lfs -text | |
| *.xz filter=lfs diff=lfs merge=lfs -text | |
| *.zip filter=lfs diff=lfs merge=lfs -text | |
| *.zst filter=lfs diff=lfs merge=lfs -text | |
| *tfevents* filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/optim/__8_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/optim/__15_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_YAM_post-train_5k/optim/.metadata filter=lfs diff=lfs merge=lfs -text | |
| 2B_YAM_post-train_5k/model/.metadata filter=lfs diff=lfs merge=lfs -text | |
| 2B_YAM_post-train_5k/optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_YAM_post-train_5k/optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_YAM_post-train_5k/optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_YAM_post-train_5k/optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_YAM_post-train_5k/optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_YAM_post-train_5k/optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_YAM_post-train_5k/optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_YAM_post-train_5k/optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_YAM_post-train_5k/model/__7_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_YAM_post-train_5k/model/__2_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/optim/.metadata filter=lfs diff=lfs merge=lfs -text | |
| 2B_YAM_post-train_5k/model/__1_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_YAM_post-train_5k/model/__6_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_YAM_post-train_5k/model/__3_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_YAM_post-train_5k/model/__5_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_YAM_post-train_5k/model/__0_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_YAM_post-train_5k/model/__4_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/optim/__17_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/optim/__28_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/optim/__18_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/optim/__10_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/optim/__21_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/optim/__14_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/optim/__19_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/optim/__13_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/optim/__11_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/optim/__25_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/optim/__12_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/optim/__9_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/optim/__26_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/optim/__29_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/optim/__20_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/optim/__16_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/optim/__23_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/optim/__27_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/optim/__15_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/model/.metadata filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/optim/__22_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/optim/__8_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/optim/__30_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/optim/__24_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/optim/__31_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/model/__17_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/model/__18_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/model/__7_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/model/__21_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/model/__10_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/model/__28_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/model/__19_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/model/__14_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/optim/__17_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/model/__26_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/optim/__18_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/model/__12_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/optim/__21_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/optim/__10_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/optim/__28_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/optim/.metadata filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/model/__13_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/model/__2_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/model/__11_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/model/__4_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/optim/__19_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/optim/__14_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/model/__5_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/model/__16_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/optim/__26_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/model/__0_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/model/__6_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/model/__22_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/model/__29_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/model/__3_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/model/__1_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/model/__27_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/model/__20_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/model/__8_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/model/__24_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/model/__25_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/model/__9_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/model/__23_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/model/__15_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/model/__30_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain_140k/model/__31_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/optim/__12_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/optim/__13_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/optim/__11_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/optim/__29_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/optim/__20_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/optim/__25_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/optim/__16_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/model/.metadata filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/optim/__9_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/optim/__22_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/optim/__27_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/optim/__23_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/optim/__8_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/optim/__15_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/optim/__31_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/optim/__24_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/optim/__30_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/model/__18_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/model/__7_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/model/__17_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/model/__21_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/model/__28_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/model/__26_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/model/__19_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/model/__2_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/model/__13_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/model/__11_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/model/__10_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/model/__12_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/model/__14_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/model/__4_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/model/__5_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/model/__0_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/model/__20_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/model/__29_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/optim/.metadata filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/model/__16_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/model/__25_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/model/__9_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/model/__1_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/model/__23_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/model/__6_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/optim/__17_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/model/__27_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/optim/__10_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/model/__22_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/optim/__18_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/optim/__21_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/optim/__28_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/optim/__14_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/model/__3_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/optim/__19_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/optim/__26_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/model/__8_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/optim/__12_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/model/__31_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/model/__15_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/model/__30_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train_5k/model/__24_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/optim/__13_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/optim/__11_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/optim/__25_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/optim/__29_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/optim/__20_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/optim/__16_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/optim/__9_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/model/.metadata filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/optim/__22_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/optim/__23_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/optim/__27_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/optim/__8_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/optim/__15_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/optim/__31_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/optim/__24_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/optim/__30_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_G1_post-train_5k/optim/.metadata filter=lfs diff=lfs merge=lfs -text | |
| 2B_G1_post-train_5k/optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_G1_post-train_5k/optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_G1_post-train_5k/optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_G1_post-train_5k/optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_G1_post-train_5k/optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_G1_post-train_5k/optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_G1_post-train_5k/optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_G1_post-train_5k/optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_G1_post-train_5k/model/.metadata filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/model/__17_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/model/__10_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/model/__21_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/model/__18_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/model/__26_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/model/__7_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/model/__28_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/model/__12_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/model/__19_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/model/__13_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/model/__2_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/model/__14_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/model/__11_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/model/__4_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/model/__5_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/model/__0_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/model/__25_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/model/__20_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/model/__29_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/model/__16_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/model/__9_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/model/__1_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/model/__23_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/model/__27_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/model/__3_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/model/__15_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/model/__22_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/model/__6_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/model/__31_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/optim/.metadata filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/model/__30_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/model/__8_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train_5k/model/__24_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_G1_post-train_5k/model/__7_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_G1_post-train_5k/model/__5_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_G1_post-train_5k/model/__2_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_G1_post-train_5k/model/__0_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_G1_post-train_5k/model/__4_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_G1_post-train_5k/model/__6_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_G1_post-train_5k/model/__1_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_G1_post-train_5k/model/__3_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/optim/__17_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/optim/__10_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/optim/__18_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/optim/__28_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/optim/__21_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/optim/__19_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/optim/__11_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/optim/__12_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/optim/__14_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/optim/__26_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/optim/__13_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/optim/__29_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/optim/__20_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/optim/__25_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/model/.metadata filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/optim/__31_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_pretrain_140k/model/__7_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_pretrain_140k/model/__2_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_pretrain_140k/model/__5_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_pretrain_140k/model/__0_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_pretrain_140k/model/__4_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_pretrain_140k/model/__1_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_pretrain_140k/model/__3_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_pretrain_140k/model/__6_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/optim/.metadata filter=lfs diff=lfs merge=lfs -text | |
| 2B_GR1_post-train_5k/model/__2_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_GR1_post-train_5k/model/__7_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_GR1_post-train_5k/model/__4_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/optim/__24_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/optim/__30_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_GR1_post-train_5k/model/__0_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_GR1_post-train_5k/model/__1_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_GR1_post-train_5k/model/__3_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_GR1_post-train_5k/model/__6_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_GR1_post-train_5k/model/__5_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/optim/__16_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/optim/__9_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/optim/__23_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/optim/__22_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/optim/__27_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/optim/__8_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/optim/__15_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/optim/__24_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/optim/__30_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/optim/__31_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_AgiBot_post-train_5k/optim/.metadata filter=lfs diff=lfs merge=lfs -text | |
| 2B_AgiBot_post-train_5k/optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_AgiBot_post-train_5k/optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_AgiBot_post-train_5k/optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_AgiBot_post-train_5k/optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_AgiBot_post-train_5k/optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_AgiBot_post-train_5k/optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_AgiBot_post-train_5k/optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_AgiBot_post-train_5k/optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_AgiBot_post-train_5k/model/.metadata filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/model/__10_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/model/__17_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/model/__18_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/model/__7_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/model/__21_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/model/__28_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/model/__26_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/model/__19_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/model/__14_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/model/__12_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/model/__13_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/model/__2_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/model/__11_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/model/__5_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/model/__0_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/model/__29_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/model/__9_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/model/__16_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/model/__4_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/model/__20_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/model/__25_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/model/__1_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/model/__23_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/model/__6_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/model/__27_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/model/__22_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/model/__3_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_pretrain_140k/optim/.metadata filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/model/__8_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/model/__31_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/model/__15_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/model/__24_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train_5k/model/__30_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_pretrain_140k/model/.metadata filter=lfs diff=lfs merge=lfs -text | |
| 2B_AgiBot_post-train_5k/model/__7_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_AgiBot_post-train_5k/model/__2_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_AgiBot_post-train_5k/model/__0_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_AgiBot_post-train_5k/model/__5_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_AgiBot_post-train_5k/model/__4_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_AgiBot_post-train_5k/model/__1_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_AgiBot_post-train_5k/model/__6_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_AgiBot_post-train_5k/model/__3_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_GR1_post-train_5k/optim/.metadata filter=lfs diff=lfs merge=lfs -text | |
| 2B_pretrain_140k/optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_pretrain_140k/optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_pretrain_140k/optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_pretrain_140k/optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_pretrain_140k/optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_pretrain_140k/optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_pretrain_140k/optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_pretrain_140k/optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_GR1_post-train_5k/model/.metadata filter=lfs diff=lfs merge=lfs -text | |
| 2B_GR1_post-train_5k/optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_GR1_post-train_5k/optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_GR1_post-train_5k/optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_GR1_post-train_5k/optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_GR1_post-train_5k/optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_GR1_post-train_5k/optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_GR1_post-train_5k/optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_GR1_post-train_5k/optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/optim/__17_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/optim/__18_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/optim/__10_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/optim/__21_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/optim/__28_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/optim/__26_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/optim/__19_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/optim/__12_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/optim/__11_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/optim/__13_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/optim/__14_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/optim/__29_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/optim/__20_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/optim/__16_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/optim/__25_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/optim/__9_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/optim/__23_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/model/.metadata filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/optim/__22_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/optim/__27_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/model/__17_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/model/__21_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/model/__7_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/model/__18_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/model/__10_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/model/__28_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/model/__19_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/model/__12_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/model/__14_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/model/__26_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/model/__2_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/model/__11_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/model/__13_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/model/__4_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/model/__5_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/model/__0_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/model/__20_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/model/__9_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/model/__29_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/model/__25_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/model/__23_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/model/__1_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/model/__27_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/model/__6_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/model/__16_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/model/__3_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/model/__8_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/model/__30_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/model/__31_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/model/__24_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/model/__22_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train_5k/model/__15_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/optim/__16_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_YAM_post-train/iter_000050000/optim/.metadata filter=lfs diff=lfs merge=lfs -text | |
| 2B_YAM_post-train/iter_000050000/model/.metadata filter=lfs diff=lfs merge=lfs -text | |
| 2B_AgiBot_post-train/iter_000050000/optim/.metadata filter=lfs diff=lfs merge=lfs -text | |
| 2B_YAM_post-train/iter_000050000/optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_YAM_post-train/iter_000050000/optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_YAM_post-train/iter_000050000/optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_YAM_post-train/iter_000050000/optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_YAM_post-train/iter_000050000/optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_YAM_post-train/iter_000050000/optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_YAM_post-train/iter_000050000/optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_YAM_post-train/iter_000050000/optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_AgiBot_post-train/iter_000050000/model/.metadata filter=lfs diff=lfs merge=lfs -text | |
| 2B_AgiBot_post-train/iter_000050000/optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_AgiBot_post-train/iter_000050000/optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_AgiBot_post-train/iter_000050000/optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_AgiBot_post-train/iter_000050000/optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_AgiBot_post-train/iter_000050000/optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_AgiBot_post-train/iter_000050000/optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_AgiBot_post-train/iter_000050000/optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_AgiBot_post-train/iter_000050000/optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_YAM_post-train/iter_000050000/model/__2_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_YAM_post-train/iter_000050000/model/__3_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_YAM_post-train/iter_000050000/model/__5_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_YAM_post-train/iter_000050000/model/__4_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/optim/.metadata filter=lfs diff=lfs merge=lfs -text | |
| 2B_YAM_post-train/iter_000050000/model/__7_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_YAM_post-train/iter_000050000/model/__0_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_YAM_post-train/iter_000050000/model/__6_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_YAM_post-train/iter_000050000/model/__1_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_AgiBot_post-train/iter_000050000/model/__2_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_AgiBot_post-train/iter_000050000/model/__3_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_AgiBot_post-train/iter_000050000/model/__4_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_AgiBot_post-train/iter_000050000/model/__5_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_AgiBot_post-train/iter_000050000/model/__0_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_AgiBot_post-train/iter_000050000/model/__1_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_AgiBot_post-train/iter_000050000/model/__6_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_AgiBot_post-train/iter_000050000/model/__7_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/optim/__29_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/optim/__30_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/optim/__24_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/optim/__11_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/optim/__28_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/optim/__31_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/optim/__12_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/optim/__27_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/optim/__17_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/optim/__18_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/optim/__13_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/optim/__8_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/optim/__14_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/optim/__25_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/optim/__20_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/optim/__9_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/optim/__15_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/optim/__10_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/optim/__21_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/optim/__19_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/optim/__23_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/model/.metadata filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/optim/__22_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/optim/__26_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/optim/__16_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/optim/__29_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/optim/__30_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/optim/__11_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/model/__30_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/model/__2_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/model/__31_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/model/__11_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/model/__24_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/model/__18_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/model/__12_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/model/__28_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/model/__3_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/model/__29_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/model/__27_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/model/__17_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/optim/__28_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/model/__5_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/model/__4_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/model/__8_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/optim/.metadata filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/model/__20_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/model/__25_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/model/__1_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/model/__13_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/model/__19_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/model/__14_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/model/__10_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/model/__6_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/model/__21_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/model/__9_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/model/__15_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/model/__7_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/optim/__24_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/model/__26_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/model/__23_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/model/__22_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/model/__16_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_GR1_post-train/iter_000050000/model/__0_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/optim/__31_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/optim/__17_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/optim/__12_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/optim/__27_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/optim/__18_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/optim/__8_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/optim/__13_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/optim/__25_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/optim/__14_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/optim/__15_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/optim/__20_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/optim/__9_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/model/.metadata filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/optim/__10_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/optim/__23_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/optim/__21_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/optim/__19_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/optim/__22_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/optim/__26_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/optim/__16_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_GR1_post-train/iter_000050000/optim/.metadata filter=lfs diff=lfs merge=lfs -text | |
| 2B_GR1_post-train/iter_000050000/optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_GR1_post-train/iter_000050000/optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_GR1_post-train/iter_000050000/optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_GR1_post-train/iter_000050000/optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/model/__2_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/model/__29_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/model/__30_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/model/__28_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/model/__11_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/model/__31_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/model/__24_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/model/__17_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_GR1_post-train/iter_000050000/optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/model/__12_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/model/__27_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/model/__3_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_GR1_post-train/iter_000050000/optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/model/__4_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/model/__18_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_GR1_post-train/iter_000050000/optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_GR1_post-train/iter_000050000/model/.metadata filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/model/__13_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/model/__8_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/model/__5_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_GR1_post-train/iter_000050000/optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/model/__14_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/model/__25_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/model/__15_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/model/__1_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/model/__20_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/model/__6_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_pretrain/iter_000140000/optim/.metadata filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/model/__23_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/model/__10_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/model/__9_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/model/__0_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/model/__21_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/model/__19_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/model/__7_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/model/__22_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/model/__26_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_G1_post-train/iter_000050000/model/__16_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_pretrain/iter_000140000/optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_pretrain/iter_000140000/optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_pretrain/iter_000140000/optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_pretrain/iter_000140000/optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_GR1_post-train/iter_000050000/model/__2_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_pretrain/iter_000140000/optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_pretrain/iter_000140000/model/.metadata filter=lfs diff=lfs merge=lfs -text | |
| 2B_GR1_post-train/iter_000050000/model/__4_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_pretrain/iter_000140000/optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_GR1_post-train/iter_000050000/model/__3_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_GR1_post-train/iter_000050000/model/__5_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_pretrain/iter_000140000/optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_GR1_post-train/iter_000050000/model/__1_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_pretrain/iter_000140000/optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_GR1_post-train/iter_000050000/model/__6_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_GR1_post-train/iter_000050000/model/__7_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_GR1_post-train/iter_000050000/model/__0_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/optim/.metadata filter=lfs diff=lfs merge=lfs -text | |
| 2B_pretrain/iter_000140000/model/__2_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_pretrain/iter_000140000/model/__4_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_pretrain/iter_000140000/model/__3_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_pretrain/iter_000140000/model/__5_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_pretrain/iter_000140000/model/__1_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_pretrain/iter_000140000/model/__6_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_pretrain/iter_000140000/model/__0_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_pretrain/iter_000140000/model/__7_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/optim/__29_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/optim/__24_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/optim/__11_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/optim/__30_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/optim/__17_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/optim/__28_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/optim/__31_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/optim/__12_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/optim/__18_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/optim/__27_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/optim/__13_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/optim/__8_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/optim/__14_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/optim/__25_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/optim/__15_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/optim/__20_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/optim/__9_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/optim/__10_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/optim/__19_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/optim/__21_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/optim/__23_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/model/.metadata filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/optim/__22_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/optim/__26_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/optim/__16_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/optim/__30_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/optim/__29_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/optim/__11_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/model/__2_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/model/__29_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/model/__11_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/optim/__28_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/model/__24_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/model/__18_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/model/__30_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/model/__31_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/model/__12_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/model/__28_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/model/__4_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/model/__3_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/model/__27_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/model/__17_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/optim/.metadata filter=lfs diff=lfs merge=lfs -text | |
| 2B_G1_post-train/iter_000050000/model/__2_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_G1_post-train/iter_000050000/model/__4_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_G1_post-train/iter_000050000/model/__3_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_G1_post-train/iter_000050000/model/__5_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_G1_post-train/iter_000050000/model/__6_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_G1_post-train/iter_000050000/model/__1_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_G1_post-train/iter_000050000/model/__7_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_G1_post-train/iter_000050000/model/__0_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/model/__13_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/model/__27_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/model/__10_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/model/__7_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/model/__20_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/model/__15_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/model/__3_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/model/__5_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/model/__14_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/model/__17_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/model/__28_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/model/__21_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/model/__11_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/model/__6_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/model/__29_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/model/__22_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/model/__30_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/model/__8_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/model/__0_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/optim/__26_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/model/__2_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/model/__4_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/model/__23_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/model/__9_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/model/__12_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/model/__25_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/model/__24_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/model/__18_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/model/__19_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/model/__31_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/model/__26_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/model/__1_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/model/__16_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/model/.metadata filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/optim/__17_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/optim/__27_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/optim/__12_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/optim/__18_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/optim/__13_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/optim/__14_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/optim/__8_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/optim/__25_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/optim/__30_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/optim/__29_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/optim/__24_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/optim/__11_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/optim/__28_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/optim/__31_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/model/__1_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/model/__13_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/model/__5_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/model/__8_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/model/__14_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/optim/.metadata filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/model/__20_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/model/__19_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/model/__10_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/optim/__24_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/model/__6_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/model/__15_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/model/__25_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/model/__7_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/model/__9_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/model/__21_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/model/__22_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/model/__23_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/model/__0_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/model/__26_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_YAM_post-train/iter_000050000/model/__16_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/optim/__31_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/optim/__12_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/optim/__27_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/optim/__17_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/optim/__18_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/optim/__13_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/optim/__8_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/optim/__14_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/optim/__25_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/optim/__15_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/optim/__10_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/optim/__19_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/optim/__20_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/optim/__9_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/model/.metadata filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/optim/__23_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/optim/__22_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/optim/__26_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/optim/__16_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/optim/__21_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_G1_post-train/iter_000050000/optim/.metadata filter=lfs diff=lfs merge=lfs -text | |
| 2B_G1_post-train/iter_000050000/optim/__2_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_G1_post-train/iter_000050000/optim/__3_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_G1_post-train/iter_000050000/optim/__4_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_G1_post-train/iter_000050000/optim/__5_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/model/__30_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/model/__29_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/model/__11_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/model/__28_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/model/__2_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/model/__24_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/model/__31_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/model/__12_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/model/__27_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/model/__17_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/model/__18_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_G1_post-train/iter_000050000/optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/model/__3_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/model/__4_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_G1_post-train/iter_000050000/optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/model/__13_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/model/__5_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/model/__8_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_G1_post-train/iter_000050000/model/.metadata filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/model/__14_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_G1_post-train/iter_000050000/optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 2B_G1_post-train/iter_000050000/optim/__0_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/model/__25_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/model/__15_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/model/__1_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/model/__20_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/model/__9_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/model/__10_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/model/__19_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/model/__6_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/model/__16_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/model/__22_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/model/__23_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/model/__26_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/model/__21_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/model/__7_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_pretrain/iter_000140000/model/__0_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/optim/__9_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/optim/__20_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/optim/__1_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/optim/__19_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/optim/__15_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/optim/__21_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/optim/__10_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/optim/__6_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/optim/__23_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/optim/__22_0.distcp filter=lfs diff=lfs merge=lfs -text | |
| 14B_AgiBot_post-train/iter_000050000/optim/__7_0.distcp filter=lfs diff=lfs merge=lfs -text | |