backup_checkpoints_libmoe / .gitattributes
DavidNguyen's picture
378b467984f9e13f61aa6d0197a32071ade4c24db8af8ec26c2bed842275178e
e750c5e verified
raw
history blame
16.7 kB
*.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
sft/smoe_refine_665k_llava/checkpoint-16632/logs/0409_1803_llava..._pope_llava_model_args_7bd459/mmerealworld_lite.json filter=lfs diff=lfs merge=lfs -text
sft/smoe_refine_665k_llava/checkpoint-16632/logs/0409_1803_llava..._pope_llava_model_args_7bd459/pope.json filter=lfs diff=lfs merge=lfs -text
sft/smoe_refine_665k_llava/checkpoint-16632/logs/0409_1803_llava..._pope_llava_model_args_7bd459/textvqa_val.json filter=lfs diff=lfs merge=lfs -text
sft/smoe_refine_665k_llava/checkpoint-16632/logs/0409_1833_llava...mstar_llava_model_args_7bd459/mmbench_en_dev.json filter=lfs diff=lfs merge=lfs -text
sft/smoe_refine_665k_llava/checkpoint-16632/logs/0409_1833_llava...mstar_llava_model_args_7bd459/submissions/mmbench_en_dev_results.xlsx filter=lfs diff=lfs merge=lfs -text
sft/smoe_refine_665k_llava/checkpoint-3328/logs/0409_1820_llava...mstar_llava_model_args_b94fe7/mmbench_en_dev.json filter=lfs diff=lfs merge=lfs -text
sft/smoe_refine_665k_llava/checkpoint-3328/logs/0409_1820_llava...mstar_llava_model_args_b94fe7/submissions/mmbench_en_dev_results.xlsx filter=lfs diff=lfs merge=lfs -text
sft/smoe_refine_665k_llava/logs/ai2d,mmbench_en_dev,mmmu_val,mmstar/0412_1911_llava...mstar_llava_model_args_4172a9/mmbench_en_dev.json filter=lfs diff=lfs merge=lfs -text
sft/smoe_refine_665k_llava/logs/ai2d,mmbench_en_dev,mmmu_val,mmstar/0412_1911_llava...mstar_llava_model_args_4172a9/submissions/mmbench_en_dev_results.xlsx filter=lfs diff=lfs merge=lfs -text
sft/smoe_refine_665k_llava/logs/gqa/0412_1934_llava_v1.5_gqa_llava_model_args_4172a9/gqa.json filter=lfs diff=lfs merge=lfs -text
sft/smoe_refine_665k_llava/logs/ocrbench,textvqa_val,mmerealworld_lite,pope/0412_1933_llava..._pope_llava_model_args_4172a9/mmerealworld_lite.json filter=lfs diff=lfs merge=lfs -text
sft/smoe_refine_665k_llava/logs/ocrbench,textvqa_val,mmerealworld_lite,pope/0412_1933_llava..._pope_llava_model_args_4172a9/pope.json filter=lfs diff=lfs merge=lfs -text
sft/smoe_refine_665k_llava/logs/ocrbench,textvqa_val,mmerealworld_lite,pope/0412_1933_llava..._pope_llava_model_args_4172a9/textvqa_val.json filter=lfs diff=lfs merge=lfs -text
sft/smoe_refinev2_665k_llava/checkpoint-16632/logs/0409_1803_llava..._pope_llava_model_args_7bd459/mmerealworld_lite.json filter=lfs diff=lfs merge=lfs -text
sft/smoe_refinev2_665k_llava/checkpoint-16632/logs/0409_1803_llava..._pope_llava_model_args_7bd459/pope.json filter=lfs diff=lfs merge=lfs -text
sft/smoe_refinev2_665k_llava/checkpoint-16632/logs/0409_1803_llava..._pope_llava_model_args_7bd459/textvqa_val.json filter=lfs diff=lfs merge=lfs -text
sft/smoe_refinev2_665k_llava/checkpoint-16632/logs/0409_1833_llava...mstar_llava_model_args_7bd459/mmbench_en_dev.json filter=lfs diff=lfs merge=lfs -text
sft/smoe_refinev2_665k_llava/checkpoint-16632/logs/0409_1833_llava...mstar_llava_model_args_7bd459/submissions/mmbench_en_dev_results.xlsx filter=lfs diff=lfs merge=lfs -text
sft/smoe_refinev2_665k_llava/checkpoint-3328/logs/0409_1820_llava...mstar_llava_model_args_b94fe7/mmbench_en_dev.json filter=lfs diff=lfs merge=lfs -text
sft/smoe_refinev2_665k_llava/checkpoint-3328/logs/0409_1820_llava...mstar_llava_model_args_b94fe7/submissions/mmbench_en_dev_results.xlsx filter=lfs diff=lfs merge=lfs -text
sft/smoe_refinev3_665k_llava/checkpoint-13312/logs/0418_1835_llava...u_val_llava_model_args_8261c1/mmmu_val.json filter=lfs diff=lfs merge=lfs -text
sft/smoe_refinev3_665k_llava/checkpoint-6656/logs/0418_1819_llava...u_val_llava_model_args_473fc1/mmmu_val.json filter=lfs diff=lfs merge=lfs -text
sft/smoe_refinev3_665k_llava/checkpoint-9984/logs/0418_1827_llava...u_val_llava_model_args_af441b/mmmu_val.json filter=lfs diff=lfs merge=lfs -text
sft/smoe_refinev3_665k_llava/logs/0418_1707_llava...mstar_llava_model_args_9259d6/mmbench_en_dev.json filter=lfs diff=lfs merge=lfs -text
sft/smoe_refinev3_665k_llava/logs/0418_1707_llava...mstar_llava_model_args_9259d6/submissions/mmbench_en_dev_results.xlsx filter=lfs diff=lfs merge=lfs -text
sft/smoe_refinev3_665k_llava/logs/0418_1721_llava..._pope_llava_model_args_9259d6/mmerealworld_lite.json filter=lfs diff=lfs merge=lfs -text
sft/smoe_refinev3_665k_llava/logs/0418_1721_llava..._pope_llava_model_args_9259d6/pope.json filter=lfs diff=lfs merge=lfs -text
sft/smoe_refinev3_665k_llava/logs/0418_1721_llava..._pope_llava_model_args_9259d6/textvqa_val.json filter=lfs diff=lfs merge=lfs -text
sft/smoe_refinev3_665k_llava/logs/0418_1748_llava_v1.5_gqa_llava_model_args_9259d6/gqa.json filter=lfs diff=lfs merge=lfs -text
sft_pretrain/Full_competesmoev30/checkpoint-1040/logs/0512_0233_llava...a_val_llava_model_args_f58958/textvqa_val.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/0.02_moce/trainer_state.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/act/moce_norm/logs/0418_1103_llava...mstar_llava_model_args_16dc6f/mmbench_en_dev.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/act/moce_norm/logs/0418_1103_llava...mstar_llava_model_args_16dc6f/submissions/mmbench_en_dev_results.xlsx filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/act/moce_norm/logs/0418_1110_llava..._pope_llava_model_args_16dc6f/mmerealworld_lite.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/act/moce_norm/logs/0418_1110_llava..._pope_llava_model_args_16dc6f/pope.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/act/moce_norm/logs/0418_1110_llava..._pope_llava_model_args_16dc6f/textvqa_val.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/act/moce_norm/logs/0418_1130_llava_v1.5_gqa_llava_model_args_16dc6f/gqa.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/act/moce_norm/trainer_state.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/act/moce_relu/logs/0417_0450_llava...mstar_llava_model_args_696dbd/mmbench_en_dev.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/act/moce_relu/logs/0417_0450_llava...mstar_llava_model_args_696dbd/submissions/mmbench_en_dev_results.xlsx filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/act/moce_relu/logs/0417_0459_llava..._pope_llava_model_args_696dbd/mmerealworld_lite.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/act/moce_relu/logs/0417_0459_llava..._pope_llava_model_args_696dbd/pope.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/act/moce_relu/logs/0417_0459_llava..._pope_llava_model_args_696dbd/textvqa_val.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/act/moce_relu/logs/0417_0514_llava_v1.5_gqa_llava_model_args_696dbd/gqa.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/act/moce_relu/trainer_state.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/act/moce_sigmoid/logs/0417_0523_llava...mstar_llava_model_args_2153fb/mmbench_en_dev.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/act/moce_sigmoid/logs/0417_0523_llava...mstar_llava_model_args_2153fb/submissions/mmbench_en_dev_results.xlsx filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/act/moce_sigmoid/logs/0417_0532_llava..._pope_llava_model_args_2153fb/mmerealworld_lite.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/act/moce_sigmoid/logs/0417_0532_llava..._pope_llava_model_args_2153fb/pope.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/act/moce_sigmoid/logs/0417_0532_llava..._pope_llava_model_args_2153fb/textvqa_val.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/act/moce_sigmoid/logs/0417_0547_llava_v1.5_gqa_llava_model_args_2153fb/gqa.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/act/moce_sigmoid/trainer_state.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/act/moce_silu/logs/0416_2257_llava...mstar_llava_model_args_a34f80/mmbench_en_dev.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/act/moce_silu/logs/0416_2257_llava...mstar_llava_model_args_a34f80/submissions/mmbench_en_dev_results.xlsx filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/act/moce_silu/logs/0417_0411_llava...mstar_llava_model_args_a34f80/mmbench_en_dev.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/act/moce_silu/logs/0417_0411_llava...mstar_llava_model_args_a34f80/submissions/mmbench_en_dev_results.xlsx filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/act/moce_silu/logs/0417_0418_llava..._pope_llava_model_args_a34f80/mmerealworld_lite.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/act/moce_silu/logs/0417_0418_llava..._pope_llava_model_args_a34f80/pope.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/act/moce_silu/logs/0417_0418_llava..._pope_llava_model_args_a34f80/textvqa_val.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/act/moce_silu/logs/0417_0441_llava_v1.5_gqa_llava_model_args_a34f80/gqa.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/act/moce_silu/trainer_state.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/hrloss/0.03_moce/logs/gqa/0404_0654_llava_v1.5_gqa_llava_model_args_b4e935/gqa.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/hrloss/0.03_moce/trainer_state.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/remove_competition/logs/ai2d,mmbench_en_dev,mmmu_val,mmstar/0404_2022_llava...mstar_llava_model_args_c2354b/mmbench_en_dev.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/remove_competition/logs/ai2d,mmbench_en_dev,mmmu_val,mmstar/0404_2022_llava...mstar_llava_model_args_c2354b/submissions/mmbench_en_dev_results.xlsx filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/remove_competition/logs/gqa/0405_2347_llava_v1.5_gqa_llava_model_args_c2354b/gqa.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/remove_competition/logs/ocrbench,textvqa_val,mmerealworld_lite,pope/0404_2045_llava..._pope_llava_model_args_c2354b/mmerealworld_lite.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/remove_competition/logs/ocrbench,textvqa_val,mmerealworld_lite,pope/0404_2045_llava..._pope_llava_model_args_c2354b/pope.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/remove_competition/logs/ocrbench,textvqa_val,mmerealworld_lite,pope/0404_2045_llava..._pope_llava_model_args_c2354b/textvqa_val.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/remove_diversity/logs/ai2d,mmbench_en_dev,mmmu_val,mmstar/0405_2242_llava...mstar_llava_model_args_6f8127/mmbench_en_dev.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/remove_diversity/logs/ai2d,mmbench_en_dev,mmmu_val,mmstar/0405_2242_llava...mstar_llava_model_args_6f8127/submissions/mmbench_en_dev_results.xlsx filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/remove_diversity/logs/gqa/0405_2242_llava_v1.5_gqa_llava_model_args_6f8127/gqa.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/remove_diversity/logs/ocrbench,textvqa_val,mmerealworld_lite,pope/0405_2253_llava..._pope_llava_model_args_6f8127/mmerealworld_lite.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/remove_diversity/logs/ocrbench,textvqa_val,mmerealworld_lite,pope/0405_2253_llava..._pope_llava_model_args_6f8127/pope.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/remove_diversity/logs/ocrbench,textvqa_val,mmerealworld_lite,pope/0405_2253_llava..._pope_llava_model_args_6f8127/textvqa_val.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/remove_diversity/trainer_state.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/scheduler/0.03_moce/logs/gqa/0404_0741_llava_v1.5_gqa_llava_model_args_42bfb8/gqa.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/scheduler/0.03_moce/trainer_state.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/scheduler/0.05_moce/logs/gqa/0404_0709_llava_v1.5_gqa_llava_model_args_b48daf/gqa.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/scheduler/0.05_moce/trainer_state.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/scheduler/0.09_moce/logs/gqa/0404_0610_llava_v1.5_gqa_llava_model_args_84bad3/gqa.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/scheduler/0.09_moce/trainer_state.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/theta/0.2_moce/logs/gqa/0404_0504_llava_v1.5_gqa_llava_model_args_34716b/gqa.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/theta/0.2_moce/logs/mmerealworld_lite,ocrbench/0404_0452_llava...bench_llava_model_args_34716b/mmerealworld_lite.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/theta/0.3_moce/logs/ai2d,mmbench_en_dev,mmmu_val,mmstar/0404_0418_llava...mstar_llava_model_args_99e268/mmbench_en_dev.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/theta/0.3_moce/logs/ai2d,mmbench_en_dev,mmmu_val,mmstar/0404_0418_llava...mstar_llava_model_args_99e268/submissions/mmbench_en_dev_results.xlsx filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/theta/0.3_moce/logs/gqa/0404_1451_llava_v1.5_gqa_llava_model_args_99e268/gqa.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/theta/0.3_moce/logs/ocrbench,textvqa_val,mmerealworld_lite,pope/0404_0428_llava..._pope_llava_model_args_99e268/mmerealworld_lite.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/theta/0.3_moce/logs/ocrbench,textvqa_val,mmerealworld_lite,pope/0404_0428_llava..._pope_llava_model_args_99e268/pope.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/theta/0.3_moce/logs/ocrbench,textvqa_val,mmerealworld_lite,pope/0404_0428_llava..._pope_llava_model_args_99e268/textvqa_val.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/ablation_moce/theta/0.3_moce/trainer_state.json filter=lfs diff=lfs merge=lfs -text
CompeteSMoE/competesmoe_versions/Full_CS_BS_theta0.2_RL0.01_softmax_competesmoev30/trainer_state.json filter=lfs diff=lfs merge=lfs -text
sft/1M3/Full_smoe/logs/0613_0224_llava..._pope_llava_model_args_bc59f1/mmbench_en_dev.json filter=lfs diff=lfs merge=lfs -text
sft/1M3/Full_smoe/logs/0613_0224_llava..._pope_llava_model_args_bc59f1/mmerealworld_lite.json filter=lfs diff=lfs merge=lfs -text
sft/1M3/Full_smoe/logs/0613_0224_llava..._pope_llava_model_args_bc59f1/pope.json filter=lfs diff=lfs merge=lfs -text
sft/1M3/Full_smoe/logs/0613_0224_llava..._pope_llava_model_args_bc59f1/submissions/mmbench_en_dev_results.xlsx filter=lfs diff=lfs merge=lfs -text
sft/1M3/Full_smoe/logs/0613_0224_llava..._pope_llava_model_args_bc59f1/textvqa_val.json filter=lfs diff=lfs merge=lfs -text
sft/1M3/Full_smoe/logs/0613_0343_llava_v1.5_gqa_llava_model_args_bc59f1/gqa.json filter=lfs diff=lfs merge=lfs -text
sft/1M3/Full_smoe/logs/0617_0402_llava...a_val_llava_model_args_bc59f1/infovqa_val.json filter=lfs diff=lfs merge=lfs -text
sft/1M3/Full_smoe/logs/0626_0643_llava_v1.5_pope_llava_model_args_bc59f1/pope.json filter=lfs diff=lfs merge=lfs -text
sft/1M3/Full_smoe/checkpoint-27572/trainer_state.json filter=lfs diff=lfs merge=lfs -text