| *.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 |
| backbone/prompt_model_mt160_5M_iter_400000 filter=lfs diff=lfs merge=lfs -text |
| gradient_16experts+moe/expert_0_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_16experts+moe/expert_1_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_16experts+moe/expert_10_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_16experts+moe/expert_11_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_16experts+moe/expert_12_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_16experts+moe/expert_13_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_16experts+moe/expert_14_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_16experts+moe/expert_15_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_16experts+moe/expert_2_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_16experts+moe/expert_3_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_16experts+moe/expert_4_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_16experts+moe/expert_5_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_16experts+moe/expert_6_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_16experts+moe/expert_7_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_16experts+moe/expert_8_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_16experts+moe/expert_9_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_16experts+moe/moe__iter_400000 filter=lfs diff=lfs merge=lfs -text |
| gradient_24experts+moe/expert_0_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_24experts+moe/expert_1_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_24experts+moe/expert_10_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_24experts+moe/expert_11_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_24experts+moe/expert_12_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_24experts+moe/expert_13_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_24experts+moe/expert_14_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_24experts+moe/expert_15_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_24experts+moe/expert_16_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_24experts+moe/expert_17_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_24experts+moe/expert_18_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_24experts+moe/expert_19_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_24experts+moe/expert_2_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_24experts+moe/expert_20_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_24experts+moe/expert_21_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_24experts+moe/expert_22_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_24experts+moe/expert_23_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_24experts+moe/expert_3_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_24experts+moe/expert_4_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_24experts+moe/expert_5_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_24experts+moe/expert_6_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_24experts+moe/expert_7_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_24experts+moe/expert_8_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_24experts+moe/expert_9_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_24experts+moe/moe__iter_400000 filter=lfs diff=lfs merge=lfs -text |
| gradient_32experts+moe/expert_0_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_32experts+moe/expert_1_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_32experts+moe/expert_10_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_32experts+moe/expert_11_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_32experts+moe/expert_12_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_32experts+moe/expert_13_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_32experts+moe/expert_14_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_32experts+moe/expert_15_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_32experts+moe/expert_16_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_32experts+moe/expert_17_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_32experts+moe/expert_18_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_32experts+moe/expert_19_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_32experts+moe/expert_2_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_32experts+moe/expert_20_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_32experts+moe/expert_21_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_32experts+moe/expert_22_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_32experts+moe/expert_23_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_32experts+moe/expert_24_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_32experts+moe/expert_25_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_32experts+moe/expert_26_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_32experts+moe/expert_27_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_32experts+moe/expert_28_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_32experts+moe/expert_29_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_32experts+moe/expert_3_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_32experts+moe/expert_30_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_32experts+moe/expert_31_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_32experts+moe/expert_4_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_32experts+moe/expert_5_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_32experts+moe/expert_6_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_32experts+moe/expert_7_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_32experts+moe/expert_8_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_32experts+moe/expert_9_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_32experts+moe/moe__iter_400000 filter=lfs diff=lfs merge=lfs -text |
| gradient_40experts+moe/expert_0_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_40experts+moe/expert_1_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_40experts+moe/expert_10_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_40experts+moe/expert_11_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_40experts+moe/expert_12_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_40experts+moe/expert_13_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_40experts+moe/expert_14_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_40experts+moe/expert_15_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_40experts+moe/expert_16_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_40experts+moe/expert_17_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_40experts+moe/expert_18_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_40experts+moe/expert_19_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_40experts+moe/expert_2_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_40experts+moe/expert_20_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_40experts+moe/expert_21_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_40experts+moe/expert_22_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_40experts+moe/expert_23_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_40experts+moe/expert_24_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_40experts+moe/expert_25_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_40experts+moe/expert_26_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_40experts+moe/expert_27_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_40experts+moe/expert_28_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_40experts+moe/expert_29_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_40experts+moe/expert_3_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_40experts+moe/expert_30_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_40experts+moe/expert_31_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_40experts+moe/expert_32_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_40experts+moe/expert_33_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_40experts+moe/expert_34_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_40experts+moe/expert_35_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_40experts+moe/expert_36_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_40experts+moe/expert_37_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_40experts+moe/expert_38_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_40experts+moe/expert_39_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_40experts+moe/expert_4_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_40experts+moe/expert_5_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_40experts+moe/expert_6_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_40experts+moe/expert_7_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_40experts+moe/expert_8_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_40experts+moe/expert_9_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_40experts+moe/moe__iter_400000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_0_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_1_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_10_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_11_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_12_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_13_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_14_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_15_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_16_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_17_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_18_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_19_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_2_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_20_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_21_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_22_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_23_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_24_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_25_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_26_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_27_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_28_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_29_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_3_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_30_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_31_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_32_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_33_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_34_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_35_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_36_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_37_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_38_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_39_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_4_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_40_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_41_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_42_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_43_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_44_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_45_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_46_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_47_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_5_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_6_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_7_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_8_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/expert_9_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_48experts+moe/moe__iter_400000 filter=lfs diff=lfs merge=lfs -text |
| gradient_8experts+moe/expert_0_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_8experts+moe/expert_1_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_8experts+moe/expert_2_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_8experts+moe/expert_3_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_8experts+moe/expert_4_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_8experts+moe/expert_5_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_8experts+moe/expert_6_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_8experts+moe/expert_7_iter_200000 filter=lfs diff=lfs merge=lfs -text |
| gradient_8experts+moe/moe__iter_400000 filter=lfs diff=lfs merge=lfs -text |
|
|