Upload spatial_nvs checkpoints (part 2)

.gitattributes

@@ -267,3 +267,234 @@ s1_lnmse_1img/nvs_vis/step_0010000_rank_06_idx_007900_cos_0.8111_ln_mse_target_g
 s1_lnmse_1img/nvs_vis/step_0010000_rank_06_idx_007900_cos_0.8118_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
 s1_lnmse_1img/nvs_vis/step_0010000_rank_07_idx_007950_cos_0.8526_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
 s1_lnmse_1img/nvs_vis/step_0010000_rank_07_idx_007950_cos_0.8539_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s1_lnmse_1img/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_00_idx_003200_cos_0.7537_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_01_idx_003250_cos_0.8754_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_02_idx_003300_cos_0.8453_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_03_idx_003350_cos_0.8293_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_04_idx_003400_cos_0.8343_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_05_idx_003450_cos_0.8059_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_06_idx_003500_cos_0.8032_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_07_idx_003550_cos_0.8233_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_08_idx_003600_cos_0.7884_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_09_idx_003650_cos_0.8245_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_10_idx_003700_cos_0.7863_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_11_idx_003750_cos_0.8070_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_12_idx_003800_cos_0.7938_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_13_idx_003850_cos_0.8365_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_14_idx_003900_cos_0.7825_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_15_idx_003950_cos_0.7955_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_16_idx_004000_cos_0.8023_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_17_idx_004050_cos_0.7883_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_18_idx_004100_cos_0.7887_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_19_idx_004150_cos_0.7935_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_20_idx_004200_cos_0.8316_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_21_idx_004250_cos_0.7940_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_22_idx_004300_cos_0.7689_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_23_idx_004350_cos_0.7954_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_24_idx_004400_cos_0.7979_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_25_idx_004450_cos_0.7942_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_26_idx_004500_cos_0.8142_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_27_idx_004550_cos_0.7913_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_28_idx_004600_cos_0.8509_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_29_idx_004650_cos_0.8118_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_30_idx_004700_cos_0.8187_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_31_idx_004750_cos_0.7651_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_32_idx_004800_cos_0.7854_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_33_idx_004850_cos_0.8484_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_34_idx_004900_cos_0.8467_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_35_idx_004950_cos_0.7232_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_36_idx_005000_cos_0.8017_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_37_idx_005050_cos_0.8069_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_38_idx_005100_cos_0.8226_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_39_idx_005150_cos_0.8204_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_40_idx_005200_cos_0.7720_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_41_idx_005250_cos_0.8068_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_42_idx_005300_cos_0.8041_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_43_idx_005350_cos_0.8148_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_44_idx_005400_cos_0.8478_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_45_idx_005450_cos_0.8601_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_46_idx_005500_cos_0.8081_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_47_idx_005550_cos_0.8075_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_48_idx_005600_cos_0.7729_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_50_idx_005700_cos_0.7732_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_51_idx_005750_cos_0.8392_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_52_idx_005800_cos_0.8092_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_53_idx_005850_cos_0.8278_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_54_idx_005900_cos_0.7523_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_55_idx_005950_cos_0.7867_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_56_idx_006000_cos_0.7542_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_57_idx_006050_cos_0.7869_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_58_idx_006100_cos_0.8141_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_59_idx_006150_cos_0.7723_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_60_idx_006200_cos_0.8131_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_61_idx_006250_cos_0.8106_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_62_idx_006300_cos_0.8047_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001000_rank_63_idx_006350_cos_0.8600_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_00_idx_006400_cos_0.8089_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_01_idx_006450_cos_0.7889_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_02_idx_006500_cos_0.8013_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_03_idx_006550_cos_0.8180_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_04_idx_006600_cos_0.7513_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_05_idx_006650_cos_0.8288_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_06_idx_006700_cos_0.8071_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_07_idx_006750_cos_0.7896_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_08_idx_006800_cos_0.8340_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_09_idx_006850_cos_0.8174_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_10_idx_006900_cos_0.8373_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_11_idx_006950_cos_0.7945_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_12_idx_007000_cos_0.8579_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_13_idx_007050_cos_0.8069_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_14_idx_007100_cos_0.7524_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_15_idx_007150_cos_0.8360_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_16_idx_007200_cos_0.8031_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_17_idx_007250_cos_0.7784_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_18_idx_007300_cos_0.8428_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_19_idx_007350_cos_0.8093_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_20_idx_007400_cos_0.7551_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_21_idx_007450_cos_0.7856_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_22_idx_007500_cos_0.8873_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_23_idx_007550_cos_0.8633_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_24_idx_007600_cos_0.7613_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_25_idx_007650_cos_0.8043_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_26_idx_007700_cos_0.7968_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_27_idx_007750_cos_0.7585_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_28_idx_007800_cos_0.7785_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_29_idx_007850_cos_0.7950_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_30_idx_007900_cos_0.7964_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_31_idx_007950_cos_0.8443_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_32_idx_008000_cos_0.8619_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_33_idx_008050_cos_0.8051_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_34_idx_008100_cos_0.8084_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_35_idx_008150_cos_0.7589_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_36_idx_008200_cos_0.7978_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_37_idx_008250_cos_0.7965_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_38_idx_008300_cos_0.8191_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_39_idx_008350_cos_0.8450_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_40_idx_008400_cos_0.8012_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_41_idx_008450_cos_0.7543_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_42_idx_008500_cos_0.7899_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_44_idx_008600_cos_0.8162_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_45_idx_008650_cos_0.8359_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_46_idx_008700_cos_0.8267_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_47_idx_008750_cos_0.8143_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_48_idx_008800_cos_0.8242_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_49_idx_008850_cos_0.7899_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_50_idx_008900_cos_0.8222_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_51_idx_008950_cos_0.7927_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_52_idx_009000_cos_0.8304_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_53_idx_009050_cos_0.7378_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_54_idx_009100_cos_0.7831_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_55_idx_009150_cos_0.8071_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_56_idx_009200_cos_0.7832_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_57_idx_009250_cos_0.8190_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_58_idx_009300_cos_0.7825_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_59_idx_009350_cos_0.8200_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_60_idx_009400_cos_0.7820_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_61_idx_009450_cos_0.7960_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_62_idx_009500_cos_0.8088_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0001500_rank_63_idx_009550_cos_0.8301_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_00_idx_009600_cos_0.7874_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_01_idx_009650_cos_0.8003_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_02_idx_009700_cos_0.7765_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_03_idx_009750_cos_0.7798_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_04_idx_009800_cos_0.8168_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_05_idx_009850_cos_0.8135_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_06_idx_009900_cos_0.8022_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_07_idx_009950_cos_0.8063_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_08_idx_010000_cos_0.7285_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_09_idx_010050_cos_0.7737_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_10_idx_010100_cos_0.7799_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_11_idx_010150_cos_0.8455_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_12_idx_010200_cos_0.8102_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_13_idx_010250_cos_0.8133_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_14_idx_010300_cos_0.7906_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_15_idx_010350_cos_0.7920_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_16_idx_010400_cos_0.8125_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_17_idx_010450_cos_0.8290_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_18_idx_010500_cos_0.8370_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_19_idx_010550_cos_0.8694_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_20_idx_010600_cos_0.7647_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_21_idx_010650_cos_0.8332_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_22_idx_010700_cos_0.8470_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_23_idx_010750_cos_0.7808_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_24_idx_010800_cos_0.7992_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_25_idx_010850_cos_0.7885_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_26_idx_010900_cos_0.7841_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_27_idx_010950_cos_0.7961_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_28_idx_011000_cos_0.8333_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_29_idx_011050_cos_0.8162_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_30_idx_011100_cos_0.8579_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_31_idx_011150_cos_0.7764_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_32_idx_011200_cos_0.8007_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_33_idx_011250_cos_0.8382_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_34_idx_011300_cos_0.7952_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_35_idx_011350_cos_0.8064_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_36_idx_011400_cos_0.8061_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_37_idx_011450_cos_0.8300_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_38_idx_011500_cos_0.7805_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_39_idx_011550_cos_0.8245_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_40_idx_011600_cos_0.7876_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_41_idx_011650_cos_0.8221_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_42_idx_011700_cos_0.7873_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_43_idx_011750_cos_0.7586_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_44_idx_011800_cos_0.8059_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_45_idx_011850_cos_0.8261_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_46_idx_011900_cos_0.8549_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_47_idx_011950_cos_0.8363_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_49_idx_012050_cos_0.8396_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_50_idx_012100_cos_0.8161_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_51_idx_012150_cos_0.7582_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_52_idx_012200_cos_0.8182_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_53_idx_012250_cos_0.7820_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_54_idx_012300_cos_0.8371_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_55_idx_012350_cos_0.8303_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_56_idx_012400_cos_0.8210_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_57_idx_012450_cos_0.8260_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_58_idx_012500_cos_0.7831_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_59_idx_012550_cos_0.7613_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_60_idx_012600_cos_0.7591_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_61_idx_012650_cos_0.7741_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_62_idx_012700_cos_0.8290_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002000_rank_63_idx_012750_cos_0.7824_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002500_rank_00_idx_012800_cos_0.8244_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002500_rank_01_idx_012850_cos_0.7702_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002500_rank_02_idx_012900_cos_0.8035_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002500_rank_03_idx_012950_cos_0.8083_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002500_rank_04_idx_013000_cos_0.8050_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002500_rank_05_idx_013050_cos_0.7735_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002500_rank_06_idx_013100_cos_0.7836_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002500_rank_07_idx_013150_cos_0.8224_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002500_rank_08_idx_013200_cos_0.8139_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002500_rank_09_idx_013250_cos_0.8709_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002500_rank_10_idx_013300_cos_0.8096_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002500_rank_11_idx_013350_cos_0.7924_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002500_rank_12_idx_013400_cos_0.7728_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002500_rank_13_idx_013450_cos_0.8365_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002500_rank_14_idx_013500_cos_0.8310_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002500_rank_15_idx_013550_cos_0.8093_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002500_rank_16_idx_013600_cos_0.7885_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002500_rank_17_idx_013650_cos_0.8421_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002500_rank_18_idx_013700_cos_0.8807_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002500_rank_20_idx_013800_cos_0.8770_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002500_rank_21_idx_013850_cos_0.8065_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002500_rank_22_idx_013900_cos_0.8520_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002500_rank_23_idx_013950_cos_0.7915_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002500_rank_24_idx_014000_cos_0.7798_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002500_rank_25_idx_014050_cos_0.8564_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002500_rank_26_idx_014100_cos_0.7812_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002500_rank_27_idx_014150_cos_0.7968_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002500_rank_28_idx_014200_cos_0.7799_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002500_rank_29_idx_014250_cos_0.7703_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002500_rank_30_idx_014300_cos_0.8276_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002500_rank_31_idx_014350_cos_0.8606_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002500_rank_32_idx_014400_cos_0.8030_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002500_rank_33_idx_014450_cos_0.8251_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002500_rank_34_idx_014500_cos_0.8425_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002500_rank_35_idx_014550_cos_0.8082_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002500_rank_36_idx_014600_cos_0.8366_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002500_rank_37_idx_014650_cos_0.8334_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002500_rank_38_idx_014700_cos_0.8152_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002500_rank_39_idx_014750_cos_0.7722_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002500_rank_40_idx_014800_cos_0.8301_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text
+s2_lnmse_1img_query5e6_wm/nvs_vis/step_0002500_rank_41_idx_014850_cos_0.7519_ln_mse_target_gtfeat_predfeat.png filter=lfs diff=lfs merge=lfs -text

s1_lnmse_1img/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b761ebf769798fb2cd694cb6178bfbbb6a96b49ccce60dda3e2c09bd3508103c
+size 11422838

s1_lnmse_1img/tokenizer_config.json

@@ -0,0 +1,249 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151669": {
+      "content": "<world>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>",
+    "<world>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 12800,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

s1_lnmse_1img/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0050fd4f68cb856b7bf5d9e48f0ff51c6df002f3ebba1b39060454b9f83f9504
+size 7224

s1_lnmse_1img/video_preprocessor_config.json

@@ -0,0 +1,41 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_sample_frames": true,
+  "fps": 2,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "input_data_format": null,
+  "max_frames": 8,
+  "merge_size": 2,
+  "min_frames": 4,
+  "num_frames": null,
+  "pad_size": null,
+  "patch_size": 16,
+  "processor_class": "Qwen3VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_metadata": false,
+  "size": {
+    "longest_edge": 802816,
+    "shortest_edge": 200704
+  },
+  "temporal_patch_size": 2,
+  "video_metadata": null,
+  "video_processor_type": "Qwen3VLVideoProcessor"
+}

s2_lnmse_1img_query5e6_wm/added_tokens.json

@@ -0,0 +1,29 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<world>": 151669,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

s2_lnmse_1img_query5e6_wm/chat_template.jinja

@@ -0,0 +1,120 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' }}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+    {%- if message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content_item in message.content %}
+                {%- if 'text' in content_item %}
+                    {{- content_item.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and message.content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

s2_lnmse_1img_query5e6_wm/config.json

@@ -0,0 +1,104 @@
+{
+  "architectures": [
+    "Qwen3VLNVSForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "image_token_id": 151655,
+  "model_type": "qwen3_vl",
+  "nvs_decoder_dim": 512,
+  "nvs_decoder_dropout": 0.0,
+  "nvs_decoder_heads": 8,
+  "nvs_decoder_layers": 8,
+  "nvs_decoder_mlp_ratio": 4.0,
+  "nvs_depth_loss_type": "log_l1",
+  "nvs_depth_loss_weight": 0.0,
+  "nvs_dino_image_size": -1,
+  "nvs_dino_model_name": "vit_base_patch14_reg4_dinov2.lvd142m",
+  "nvs_dino_num_prefix_tokens": 5,
+  "nvs_dino_patch_size": -1,
+  "nvs_dino_pretrained": true,
+  "nvs_feature_loss_type": "ln_mse",
+  "nvs_future_condition_dim": 32,
+  "nvs_future_condition_dino_path": "/mnt/petrelfs/zhangsiqi1/efm_data/huggingface/vit_large_patch14_reg4_dinov2.lvd142m",
+  "nvs_future_condition_image_size": 224,
+  "nvs_future_condition_num_queries": 16,
+  "nvs_future_condition_pool_size": 8,
+  "nvs_future_condition_vae_path": "/mnt/petrelfs/zhangsiqi1/efm_data/huggingface/Wan2.1-VACE-14B/Wan2.1_VAE.pth",
+  "nvs_loss_weight": 0.5,
+  "nvs_num_scene_queries": 128,
+  "nvs_perceptual_loss_weight": 0.0,
+  "nvs_pose_loss_weight": 0.0,
+  "nvs_render_patch_size": 16,
+  "nvs_target_feature_dim": 2048,
+  "nvs_target_feature_type": "qwen_visual_merger",
+  "nvs_target_patch_size": 16,
+  "nvs_target_spatial_merge_size": 2,
+  "nvs_use_world_adapter": false,
+  "nvs_vae_image_size": 512,
+  "nvs_vae_model_path": "/mnt/inspurfs/efm_t/zhangsiqi/huggingface/sdxl-vae",
+  "nvs_vae_scaling_factor": 0.18215,
+  "nvs_world_adapter_dim": 512,
+  "nvs_world_adapter_gate_init_bias": -4.0,
+  "nvs_world_token": "<world>",
+  "nvs_world_token_id": 151669,
+  "pad_token_id": 151643,
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "dtype": "bfloat16",
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 2048,
+    "initializer_range": 0.02,
+    "intermediate_size": 6144,
+    "max_position_embeddings": 262144,
+    "model_type": "qwen3_vl_text",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 28,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        24,
+        20,
+        20
+      ],
+      "rope_type": "default"
+    },
+    "rope_theta": 5000000,
+    "tie_word_embeddings": true,
+    "use_cache": true,
+    "vocab_size": 151936
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.1",
+  "use_cache": true,
+  "video_token_id": 151656,
+  "vision_config": {
+    "deepstack_visual_indexes": [
+      5,
+      11,
+      17
+    ],
+    "depth": 24,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1024,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "model_type": "qwen3_vl",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 2048,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652
+}

s2_lnmse_1img_query5e6_wm/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.57.1"
+}

s2_lnmse_1img_query5e6_wm/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f3d8894b55e67974f968f2aa93712af071fddaffdfdd5383e6720da69d5675e
+size 4995043040

s2_lnmse_1img_query5e6_wm/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b74910d6e4612c94d2db4c646e97c614fed2de267257c665d056827c64868f61
+size 753168586

s2_lnmse_1img_query5e6_wm/model.safetensors.index.json

@@ -0,0 +1,1066 @@
+{
+  "metadata": {
+    "total_parameters": 2562876929,
+    "total_size": 5748083714
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.21.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.21.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.22.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.22.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.24.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.24.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.25.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.25.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.26.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.26.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.norm.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00002.safetensors",
+    "model.visual.merger.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.merger.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.merger.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.merger.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.merger.norm.bias": "model-00001-of-00002.safetensors",
+    "model.visual.merger.norm.weight": "model-00001-of-00002.safetensors",
+    "model.visual.patch_embed.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.pos_embed.weight": "model-00001-of-00002.safetensors",
+    "nvs_decoder.camera_tokenizer.proj.0.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.camera_tokenizer.proj.0.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.camera_tokenizer.proj.2.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.camera_tokenizer.proj.2.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.0.linear1.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.0.linear1.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.0.linear2.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.0.linear2.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.0.norm1.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.0.norm1.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.0.norm2.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.0.norm2.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.0.self_attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.0.self_attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.0.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.1.linear1.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.1.linear1.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.1.linear2.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.1.linear2.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.1.norm1.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.1.norm1.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.1.norm2.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.1.norm2.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.1.self_attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.1.self_attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.1.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.2.linear1.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.2.linear1.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.2.linear2.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.2.linear2.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.2.norm1.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.2.norm1.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.2.norm2.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.2.norm2.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.2.self_attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.2.self_attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.2.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.2.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.3.linear1.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.3.linear1.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.3.linear2.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.3.linear2.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.3.norm1.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.3.norm1.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.3.norm2.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.3.norm2.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.3.self_attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.3.self_attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.3.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.3.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.4.linear1.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.4.linear1.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.4.linear2.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.4.linear2.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.4.norm1.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.4.norm1.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.4.norm2.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.4.norm2.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.4.self_attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.4.self_attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.4.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.4.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.5.linear1.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.5.linear1.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.5.linear2.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.5.linear2.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.5.norm1.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.5.norm1.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.5.norm2.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.5.norm2.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.5.self_attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.5.self_attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.5.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.5.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.6.linear1.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.6.linear1.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.6.linear2.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.6.linear2.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.6.norm1.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.6.norm1.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.6.norm2.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.6.norm2.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.6.self_attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.6.self_attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.6.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.6.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.7.linear1.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.7.linear1.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.7.linear2.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.7.linear2.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.7.norm1.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.7.norm1.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.7.norm2.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.7.norm2.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.7.self_attn.in_proj_bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.7.self_attn.in_proj_weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.7.self_attn.out_proj.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.decoder.layers.7.self_attn.out_proj.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.depth_head.0.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.depth_head.0.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.depth_head.1.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.depth_head.1.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.depth_head.3.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.depth_head.3.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.feature_head.0.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.feature_head.0.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.feature_head.1.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.feature_head.1.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.sampled_ray_embedder.0.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.sampled_ray_embedder.0.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.sampled_ray_embedder.2.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.sampled_ray_embedder.2.weight": "model-00002-of-00002.safetensors",
+    "nvs_decoder.scene_proj.bias": "model-00002-of-00002.safetensors",
+    "nvs_decoder.scene_proj.weight": "model-00002-of-00002.safetensors",
+    "scene_query_tokens": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.1.norm2.bias": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.10.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.10.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.10.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.10.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.10.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.10.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.10.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.10.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.10.norm1.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.10.norm1.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.10.norm2.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.10.norm2.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.11.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.11.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.11.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.11.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.11.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.11.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.11.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.11.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.11.norm1.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.11.norm1.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.11.norm2.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.11.norm2.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.12.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.12.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.12.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.12.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.12.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.12.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.12.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.12.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.12.norm1.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.12.norm1.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.12.norm2.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.12.norm2.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.13.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.13.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.13.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.13.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.13.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.13.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.13.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.13.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.13.norm1.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.13.norm1.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.13.norm2.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.13.norm2.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.14.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.14.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.14.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.14.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.14.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.14.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.14.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.14.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.14.norm1.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.14.norm1.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.14.norm2.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.14.norm2.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.15.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.15.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.15.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.15.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.15.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.15.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.15.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.15.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.15.norm1.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.15.norm1.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.15.norm2.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.15.norm2.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.16.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.16.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.16.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.16.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.16.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.16.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.16.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.16.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.16.norm1.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.16.norm1.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.16.norm2.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.16.norm2.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.17.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.17.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.17.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.17.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.17.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.17.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.17.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.17.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.17.norm1.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.17.norm1.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.17.norm2.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.17.norm2.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.18.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.18.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.18.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.18.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.18.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.18.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.18.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.18.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.18.norm1.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.18.norm1.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.18.norm2.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.18.norm2.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.19.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.19.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.19.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.19.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.19.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.19.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.19.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.19.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.19.norm1.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.19.norm1.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.19.norm2.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.19.norm2.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.20.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.20.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.20.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.20.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.20.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.20.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.20.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.20.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.20.norm1.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.20.norm1.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.20.norm2.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.20.norm2.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.21.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.21.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.21.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.21.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.21.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.21.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.21.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.21.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.21.norm1.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.21.norm1.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.21.norm2.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.21.norm2.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.22.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.22.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.22.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.22.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.22.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.22.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.22.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.22.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.22.norm1.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.22.norm1.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.22.norm2.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.22.norm2.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.23.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.23.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.23.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.23.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.23.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.23.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.23.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.23.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.23.norm1.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.23.norm1.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.23.norm2.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.23.norm2.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.4.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.4.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.4.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.4.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.4.norm1.bias": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.blocks.5.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.5.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.5.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.5.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.5.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.5.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.5.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.5.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.5.norm1.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.5.norm1.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.5.norm2.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.5.norm2.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.6.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.6.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.6.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.6.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.6.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.6.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.6.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.6.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.6.norm1.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.6.norm1.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.6.norm2.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.6.norm2.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.7.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.7.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.7.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.7.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.7.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.7.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.7.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.7.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.7.norm1.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.7.norm1.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.7.norm2.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.7.norm2.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.8.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.8.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.8.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.8.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.8.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.8.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.8.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.8.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.8.norm1.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.8.norm1.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.8.norm2.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.8.norm2.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.9.attn.proj.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.9.attn.proj.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.9.attn.qkv.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.9.attn.qkv.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.9.mlp.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.9.mlp.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.9.mlp.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.9.mlp.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.9.norm1.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.9.norm1.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.9.norm2.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.blocks.9.norm2.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.deepstack_merger_list.0.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.deepstack_merger_list.0.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.deepstack_merger_list.0.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.deepstack_merger_list.0.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.deepstack_merger_list.0.norm.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.deepstack_merger_list.0.norm.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.deepstack_merger_list.1.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.deepstack_merger_list.1.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.deepstack_merger_list.1.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.deepstack_merger_list.1.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.deepstack_merger_list.1.norm.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.deepstack_merger_list.1.norm.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.deepstack_merger_list.2.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.deepstack_merger_list.2.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.deepstack_merger_list.2.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.deepstack_merger_list.2.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.deepstack_merger_list.2.norm.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.deepstack_merger_list.2.norm.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.merger.linear_fc1.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.merger.linear_fc1.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.merger.linear_fc2.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.merger.linear_fc2.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.merger.norm.bias": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.merger.norm.weight": "model-00002-of-00002.safetensors",
+    "target_visual_encoder.patch_embed.proj.bias": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
+    "target_visual_encoder.pos_embed.weight": "model-00001-of-00002.safetensors"
+  }
+}