Upload CycleGRPO-OPSD step 195

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,542 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|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,
+  "<|mt_0000|>": 151670,
+  "<|mt_0001|>": 151671,
+  "<|mt_0002|>": 151672,
+  "<|mt_0003|>": 151673,
+  "<|mt_0004|>": 151674,
+  "<|mt_0005|>": 151675,
+  "<|mt_0006|>": 151676,
+  "<|mt_0007|>": 151677,
+  "<|mt_0008|>": 151678,
+  "<|mt_0009|>": 151679,
+  "<|mt_0010|>": 151680,
+  "<|mt_0011|>": 151681,
+  "<|mt_0012|>": 151682,
+  "<|mt_0013|>": 151683,
+  "<|mt_0014|>": 151684,
+  "<|mt_0015|>": 151685,
+  "<|mt_0016|>": 151686,
+  "<|mt_0017|>": 151687,
+  "<|mt_0018|>": 151688,
+  "<|mt_0019|>": 151689,
+  "<|mt_0020|>": 151690,
+  "<|mt_0021|>": 151691,
+  "<|mt_0022|>": 151692,
+  "<|mt_0023|>": 151693,
+  "<|mt_0024|>": 151694,
+  "<|mt_0025|>": 151695,
+  "<|mt_0026|>": 151696,
+  "<|mt_0027|>": 151697,
+  "<|mt_0028|>": 151698,
+  "<|mt_0029|>": 151699,
+  "<|mt_0030|>": 151700,
+  "<|mt_0031|>": 151701,
+  "<|mt_0032|>": 151702,
+  "<|mt_0033|>": 151703,
+  "<|mt_0034|>": 151704,
+  "<|mt_0035|>": 151705,
+  "<|mt_0036|>": 151706,
+  "<|mt_0037|>": 151707,
+  "<|mt_0038|>": 151708,
+  "<|mt_0039|>": 151709,
+  "<|mt_0040|>": 151710,
+  "<|mt_0041|>": 151711,
+  "<|mt_0042|>": 151712,
+  "<|mt_0043|>": 151713,
+  "<|mt_0044|>": 151714,
+  "<|mt_0045|>": 151715,
+  "<|mt_0046|>": 151716,
+  "<|mt_0047|>": 151717,
+  "<|mt_0048|>": 151718,
+  "<|mt_0049|>": 151719,
+  "<|mt_0050|>": 151720,
+  "<|mt_0051|>": 151721,
+  "<|mt_0052|>": 151722,
+  "<|mt_0053|>": 151723,
+  "<|mt_0054|>": 151724,
+  "<|mt_0055|>": 151725,
+  "<|mt_0056|>": 151726,
+  "<|mt_0057|>": 151727,
+  "<|mt_0058|>": 151728,
+  "<|mt_0059|>": 151729,
+  "<|mt_0060|>": 151730,
+  "<|mt_0061|>": 151731,
+  "<|mt_0062|>": 151732,
+  "<|mt_0063|>": 151733,
+  "<|mt_0064|>": 151734,
+  "<|mt_0065|>": 151735,
+  "<|mt_0066|>": 151736,
+  "<|mt_0067|>": 151737,
+  "<|mt_0068|>": 151738,
+  "<|mt_0069|>": 151739,
+  "<|mt_0070|>": 151740,
+  "<|mt_0071|>": 151741,
+  "<|mt_0072|>": 151742,
+  "<|mt_0073|>": 151743,
+  "<|mt_0074|>": 151744,
+  "<|mt_0075|>": 151745,
+  "<|mt_0076|>": 151746,
+  "<|mt_0077|>": 151747,
+  "<|mt_0078|>": 151748,
+  "<|mt_0079|>": 151749,
+  "<|mt_0080|>": 151750,
+  "<|mt_0081|>": 151751,
+  "<|mt_0082|>": 151752,
+  "<|mt_0083|>": 151753,
+  "<|mt_0084|>": 151754,
+  "<|mt_0085|>": 151755,
+  "<|mt_0086|>": 151756,
+  "<|mt_0087|>": 151757,
+  "<|mt_0088|>": 151758,
+  "<|mt_0089|>": 151759,
+  "<|mt_0090|>": 151760,
+  "<|mt_0091|>": 151761,
+  "<|mt_0092|>": 151762,
+  "<|mt_0093|>": 151763,
+  "<|mt_0094|>": 151764,
+  "<|mt_0095|>": 151765,
+  "<|mt_0096|>": 151766,
+  "<|mt_0097|>": 151767,
+  "<|mt_0098|>": 151768,
+  "<|mt_0099|>": 151769,
+  "<|mt_0100|>": 151770,
+  "<|mt_0101|>": 151771,
+  "<|mt_0102|>": 151772,
+  "<|mt_0103|>": 151773,
+  "<|mt_0104|>": 151774,
+  "<|mt_0105|>": 151775,
+  "<|mt_0106|>": 151776,
+  "<|mt_0107|>": 151777,
+  "<|mt_0108|>": 151778,
+  "<|mt_0109|>": 151779,
+  "<|mt_0110|>": 151780,
+  "<|mt_0111|>": 151781,
+  "<|mt_0112|>": 151782,
+  "<|mt_0113|>": 151783,
+  "<|mt_0114|>": 151784,
+  "<|mt_0115|>": 151785,
+  "<|mt_0116|>": 151786,
+  "<|mt_0117|>": 151787,
+  "<|mt_0118|>": 151788,
+  "<|mt_0119|>": 151789,
+  "<|mt_0120|>": 151790,
+  "<|mt_0121|>": 151791,
+  "<|mt_0122|>": 151792,
+  "<|mt_0123|>": 151793,
+  "<|mt_0124|>": 151794,
+  "<|mt_0125|>": 151795,
+  "<|mt_0126|>": 151796,
+  "<|mt_0127|>": 151797,
+  "<|mt_0128|>": 151798,
+  "<|mt_0129|>": 151799,
+  "<|mt_0130|>": 151800,
+  "<|mt_0131|>": 151801,
+  "<|mt_0132|>": 151802,
+  "<|mt_0133|>": 151803,
+  "<|mt_0134|>": 151804,
+  "<|mt_0135|>": 151805,
+  "<|mt_0136|>": 151806,
+  "<|mt_0137|>": 151807,
+  "<|mt_0138|>": 151808,
+  "<|mt_0139|>": 151809,
+  "<|mt_0140|>": 151810,
+  "<|mt_0141|>": 151811,
+  "<|mt_0142|>": 151812,
+  "<|mt_0143|>": 151813,
+  "<|mt_0144|>": 151814,
+  "<|mt_0145|>": 151815,
+  "<|mt_0146|>": 151816,
+  "<|mt_0147|>": 151817,
+  "<|mt_0148|>": 151818,
+  "<|mt_0149|>": 151819,
+  "<|mt_0150|>": 151820,
+  "<|mt_0151|>": 151821,
+  "<|mt_0152|>": 151822,
+  "<|mt_0153|>": 151823,
+  "<|mt_0154|>": 151824,
+  "<|mt_0155|>": 151825,
+  "<|mt_0156|>": 151826,
+  "<|mt_0157|>": 151827,
+  "<|mt_0158|>": 151828,
+  "<|mt_0159|>": 151829,
+  "<|mt_0160|>": 151830,
+  "<|mt_0161|>": 151831,
+  "<|mt_0162|>": 151832,
+  "<|mt_0163|>": 151833,
+  "<|mt_0164|>": 151834,
+  "<|mt_0165|>": 151835,
+  "<|mt_0166|>": 151836,
+  "<|mt_0167|>": 151837,
+  "<|mt_0168|>": 151838,
+  "<|mt_0169|>": 151839,
+  "<|mt_0170|>": 151840,
+  "<|mt_0171|>": 151841,
+  "<|mt_0172|>": 151842,
+  "<|mt_0173|>": 151843,
+  "<|mt_0174|>": 151844,
+  "<|mt_0175|>": 151845,
+  "<|mt_0176|>": 151846,
+  "<|mt_0177|>": 151847,
+  "<|mt_0178|>": 151848,
+  "<|mt_0179|>": 151849,
+  "<|mt_0180|>": 151850,
+  "<|mt_0181|>": 151851,
+  "<|mt_0182|>": 151852,
+  "<|mt_0183|>": 151853,
+  "<|mt_0184|>": 151854,
+  "<|mt_0185|>": 151855,
+  "<|mt_0186|>": 151856,
+  "<|mt_0187|>": 151857,
+  "<|mt_0188|>": 151858,
+  "<|mt_0189|>": 151859,
+  "<|mt_0190|>": 151860,
+  "<|mt_0191|>": 151861,
+  "<|mt_0192|>": 151862,
+  "<|mt_0193|>": 151863,
+  "<|mt_0194|>": 151864,
+  "<|mt_0195|>": 151865,
+  "<|mt_0196|>": 151866,
+  "<|mt_0197|>": 151867,
+  "<|mt_0198|>": 151868,
+  "<|mt_0199|>": 151869,
+  "<|mt_0200|>": 151870,
+  "<|mt_0201|>": 151871,
+  "<|mt_0202|>": 151872,
+  "<|mt_0203|>": 151873,
+  "<|mt_0204|>": 151874,
+  "<|mt_0205|>": 151875,
+  "<|mt_0206|>": 151876,
+  "<|mt_0207|>": 151877,
+  "<|mt_0208|>": 151878,
+  "<|mt_0209|>": 151879,
+  "<|mt_0210|>": 151880,
+  "<|mt_0211|>": 151881,
+  "<|mt_0212|>": 151882,
+  "<|mt_0213|>": 151883,
+  "<|mt_0214|>": 151884,
+  "<|mt_0215|>": 151885,
+  "<|mt_0216|>": 151886,
+  "<|mt_0217|>": 151887,
+  "<|mt_0218|>": 151888,
+  "<|mt_0219|>": 151889,
+  "<|mt_0220|>": 151890,
+  "<|mt_0221|>": 151891,
+  "<|mt_0222|>": 151892,
+  "<|mt_0223|>": 151893,
+  "<|mt_0224|>": 151894,
+  "<|mt_0225|>": 151895,
+  "<|mt_0226|>": 151896,
+  "<|mt_0227|>": 151897,
+  "<|mt_0228|>": 151898,
+  "<|mt_0229|>": 151899,
+  "<|mt_0230|>": 151900,
+  "<|mt_0231|>": 151901,
+  "<|mt_0232|>": 151902,
+  "<|mt_0233|>": 151903,
+  "<|mt_0234|>": 151904,
+  "<|mt_0235|>": 151905,
+  "<|mt_0236|>": 151906,
+  "<|mt_0237|>": 151907,
+  "<|mt_0238|>": 151908,
+  "<|mt_0239|>": 151909,
+  "<|mt_0240|>": 151910,
+  "<|mt_0241|>": 151911,
+  "<|mt_0242|>": 151912,
+  "<|mt_0243|>": 151913,
+  "<|mt_0244|>": 151914,
+  "<|mt_0245|>": 151915,
+  "<|mt_0246|>": 151916,
+  "<|mt_0247|>": 151917,
+  "<|mt_0248|>": 151918,
+  "<|mt_0249|>": 151919,
+  "<|mt_0250|>": 151920,
+  "<|mt_0251|>": 151921,
+  "<|mt_0252|>": 151922,
+  "<|mt_0253|>": 151923,
+  "<|mt_0254|>": 151924,
+  "<|mt_0255|>": 151925,
+  "<|mt_0256|>": 151926,
+  "<|mt_0257|>": 151927,
+  "<|mt_0258|>": 151928,
+  "<|mt_0259|>": 151929,
+  "<|mt_0260|>": 151930,
+  "<|mt_0261|>": 151931,
+  "<|mt_0262|>": 151932,
+  "<|mt_0263|>": 151933,
+  "<|mt_0264|>": 151934,
+  "<|mt_0265|>": 151935,
+  "<|mt_0266|>": 151936,
+  "<|mt_0267|>": 151937,
+  "<|mt_0268|>": 151938,
+  "<|mt_0269|>": 151939,
+  "<|mt_0270|>": 151940,
+  "<|mt_0271|>": 151941,
+  "<|mt_0272|>": 151942,
+  "<|mt_0273|>": 151943,
+  "<|mt_0274|>": 151944,
+  "<|mt_0275|>": 151945,
+  "<|mt_0276|>": 151946,
+  "<|mt_0277|>": 151947,
+  "<|mt_0278|>": 151948,
+  "<|mt_0279|>": 151949,
+  "<|mt_0280|>": 151950,
+  "<|mt_0281|>": 151951,
+  "<|mt_0282|>": 151952,
+  "<|mt_0283|>": 151953,
+  "<|mt_0284|>": 151954,
+  "<|mt_0285|>": 151955,
+  "<|mt_0286|>": 151956,
+  "<|mt_0287|>": 151957,
+  "<|mt_0288|>": 151958,
+  "<|mt_0289|>": 151959,
+  "<|mt_0290|>": 151960,
+  "<|mt_0291|>": 151961,
+  "<|mt_0292|>": 151962,
+  "<|mt_0293|>": 151963,
+  "<|mt_0294|>": 151964,
+  "<|mt_0295|>": 151965,
+  "<|mt_0296|>": 151966,
+  "<|mt_0297|>": 151967,
+  "<|mt_0298|>": 151968,
+  "<|mt_0299|>": 151969,
+  "<|mt_0300|>": 151970,
+  "<|mt_0301|>": 151971,
+  "<|mt_0302|>": 151972,
+  "<|mt_0303|>": 151973,
+  "<|mt_0304|>": 151974,
+  "<|mt_0305|>": 151975,
+  "<|mt_0306|>": 151976,
+  "<|mt_0307|>": 151977,
+  "<|mt_0308|>": 151978,
+  "<|mt_0309|>": 151979,
+  "<|mt_0310|>": 151980,
+  "<|mt_0311|>": 151981,
+  "<|mt_0312|>": 151982,
+  "<|mt_0313|>": 151983,
+  "<|mt_0314|>": 151984,
+  "<|mt_0315|>": 151985,
+  "<|mt_0316|>": 151986,
+  "<|mt_0317|>": 151987,
+  "<|mt_0318|>": 151988,
+  "<|mt_0319|>": 151989,
+  "<|mt_0320|>": 151990,
+  "<|mt_0321|>": 151991,
+  "<|mt_0322|>": 151992,
+  "<|mt_0323|>": 151993,
+  "<|mt_0324|>": 151994,
+  "<|mt_0325|>": 151995,
+  "<|mt_0326|>": 151996,
+  "<|mt_0327|>": 151997,
+  "<|mt_0328|>": 151998,
+  "<|mt_0329|>": 151999,
+  "<|mt_0330|>": 152000,
+  "<|mt_0331|>": 152001,
+  "<|mt_0332|>": 152002,
+  "<|mt_0333|>": 152003,
+  "<|mt_0334|>": 152004,
+  "<|mt_0335|>": 152005,
+  "<|mt_0336|>": 152006,
+  "<|mt_0337|>": 152007,
+  "<|mt_0338|>": 152008,
+  "<|mt_0339|>": 152009,
+  "<|mt_0340|>": 152010,
+  "<|mt_0341|>": 152011,
+  "<|mt_0342|>": 152012,
+  "<|mt_0343|>": 152013,
+  "<|mt_0344|>": 152014,
+  "<|mt_0345|>": 152015,
+  "<|mt_0346|>": 152016,
+  "<|mt_0347|>": 152017,
+  "<|mt_0348|>": 152018,
+  "<|mt_0349|>": 152019,
+  "<|mt_0350|>": 152020,
+  "<|mt_0351|>": 152021,
+  "<|mt_0352|>": 152022,
+  "<|mt_0353|>": 152023,
+  "<|mt_0354|>": 152024,
+  "<|mt_0355|>": 152025,
+  "<|mt_0356|>": 152026,
+  "<|mt_0357|>": 152027,
+  "<|mt_0358|>": 152028,
+  "<|mt_0359|>": 152029,
+  "<|mt_0360|>": 152030,
+  "<|mt_0361|>": 152031,
+  "<|mt_0362|>": 152032,
+  "<|mt_0363|>": 152033,
+  "<|mt_0364|>": 152034,
+  "<|mt_0365|>": 152035,
+  "<|mt_0366|>": 152036,
+  "<|mt_0367|>": 152037,
+  "<|mt_0368|>": 152038,
+  "<|mt_0369|>": 152039,
+  "<|mt_0370|>": 152040,
+  "<|mt_0371|>": 152041,
+  "<|mt_0372|>": 152042,
+  "<|mt_0373|>": 152043,
+  "<|mt_0374|>": 152044,
+  "<|mt_0375|>": 152045,
+  "<|mt_0376|>": 152046,
+  "<|mt_0377|>": 152047,
+  "<|mt_0378|>": 152048,
+  "<|mt_0379|>": 152049,
+  "<|mt_0380|>": 152050,
+  "<|mt_0381|>": 152051,
+  "<|mt_0382|>": 152052,
+  "<|mt_0383|>": 152053,
+  "<|mt_0384|>": 152054,
+  "<|mt_0385|>": 152055,
+  "<|mt_0386|>": 152056,
+  "<|mt_0387|>": 152057,
+  "<|mt_0388|>": 152058,
+  "<|mt_0389|>": 152059,
+  "<|mt_0390|>": 152060,
+  "<|mt_0391|>": 152061,
+  "<|mt_0392|>": 152062,
+  "<|mt_0393|>": 152063,
+  "<|mt_0394|>": 152064,
+  "<|mt_0395|>": 152065,
+  "<|mt_0396|>": 152066,
+  "<|mt_0397|>": 152067,
+  "<|mt_0398|>": 152068,
+  "<|mt_0399|>": 152069,
+  "<|mt_0400|>": 152070,
+  "<|mt_0401|>": 152071,
+  "<|mt_0402|>": 152072,
+  "<|mt_0403|>": 152073,
+  "<|mt_0404|>": 152074,
+  "<|mt_0405|>": 152075,
+  "<|mt_0406|>": 152076,
+  "<|mt_0407|>": 152077,
+  "<|mt_0408|>": 152078,
+  "<|mt_0409|>": 152079,
+  "<|mt_0410|>": 152080,
+  "<|mt_0411|>": 152081,
+  "<|mt_0412|>": 152082,
+  "<|mt_0413|>": 152083,
+  "<|mt_0414|>": 152084,
+  "<|mt_0415|>": 152085,
+  "<|mt_0416|>": 152086,
+  "<|mt_0417|>": 152087,
+  "<|mt_0418|>": 152088,
+  "<|mt_0419|>": 152089,
+  "<|mt_0420|>": 152090,
+  "<|mt_0421|>": 152091,
+  "<|mt_0422|>": 152092,
+  "<|mt_0423|>": 152093,
+  "<|mt_0424|>": 152094,
+  "<|mt_0425|>": 152095,
+  "<|mt_0426|>": 152096,
+  "<|mt_0427|>": 152097,
+  "<|mt_0428|>": 152098,
+  "<|mt_0429|>": 152099,
+  "<|mt_0430|>": 152100,
+  "<|mt_0431|>": 152101,
+  "<|mt_0432|>": 152102,
+  "<|mt_0433|>": 152103,
+  "<|mt_0434|>": 152104,
+  "<|mt_0435|>": 152105,
+  "<|mt_0436|>": 152106,
+  "<|mt_0437|>": 152107,
+  "<|mt_0438|>": 152108,
+  "<|mt_0439|>": 152109,
+  "<|mt_0440|>": 152110,
+  "<|mt_0441|>": 152111,
+  "<|mt_0442|>": 152112,
+  "<|mt_0443|>": 152113,
+  "<|mt_0444|>": 152114,
+  "<|mt_0445|>": 152115,
+  "<|mt_0446|>": 152116,
+  "<|mt_0447|>": 152117,
+  "<|mt_0448|>": 152118,
+  "<|mt_0449|>": 152119,
+  "<|mt_0450|>": 152120,
+  "<|mt_0451|>": 152121,
+  "<|mt_0452|>": 152122,
+  "<|mt_0453|>": 152123,
+  "<|mt_0454|>": 152124,
+  "<|mt_0455|>": 152125,
+  "<|mt_0456|>": 152126,
+  "<|mt_0457|>": 152127,
+  "<|mt_0458|>": 152128,
+  "<|mt_0459|>": 152129,
+  "<|mt_0460|>": 152130,
+  "<|mt_0461|>": 152131,
+  "<|mt_0462|>": 152132,
+  "<|mt_0463|>": 152133,
+  "<|mt_0464|>": 152134,
+  "<|mt_0465|>": 152135,
+  "<|mt_0466|>": 152136,
+  "<|mt_0467|>": 152137,
+  "<|mt_0468|>": 152138,
+  "<|mt_0469|>": 152139,
+  "<|mt_0470|>": 152140,
+  "<|mt_0471|>": 152141,
+  "<|mt_0472|>": 152142,
+  "<|mt_0473|>": 152143,
+  "<|mt_0474|>": 152144,
+  "<|mt_0475|>": 152145,
+  "<|mt_0476|>": 152146,
+  "<|mt_0477|>": 152147,
+  "<|mt_0478|>": 152148,
+  "<|mt_0479|>": 152149,
+  "<|mt_0480|>": 152150,
+  "<|mt_0481|>": 152151,
+  "<|mt_0482|>": 152152,
+  "<|mt_0483|>": 152153,
+  "<|mt_0484|>": 152154,
+  "<|mt_0485|>": 152155,
+  "<|mt_0486|>": 152156,
+  "<|mt_0487|>": 152157,
+  "<|mt_0488|>": 152158,
+  "<|mt_0489|>": 152159,
+  "<|mt_0490|>": 152160,
+  "<|mt_0491|>": 152161,
+  "<|mt_0492|>": 152162,
+  "<|mt_0493|>": 152163,
+  "<|mt_0494|>": 152164,
+  "<|mt_0495|>": 152165,
+  "<|mt_0496|>": 152166,
+  "<|mt_0497|>": 152167,
+  "<|mt_0498|>": 152168,
+  "<|mt_0499|>": 152169,
+  "<|mt_0500|>": 152170,
+  "<|mt_0501|>": 152171,
+  "<|mt_0502|>": 152172,
+  "<|mt_0503|>": 152173,
+  "<|mt_0504|>": 152174,
+  "<|mt_0505|>": 152175,
+  "<|mt_0506|>": 152176,
+  "<|mt_0507|>": 152177,
+  "<|mt_0508|>": 152178,
+  "<|mt_0509|>": 152179,
+  "<|mt_0510|>": 152180,
+  "<|mt_0511|>": 152181,
+  "<|mt_end|>": 152182,
+  "<|mt_start|>": 151669,
+  "<|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
+}

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 %}

config.json

@@ -0,0 +1,70 @@
+{
+  "architectures": [
+    "Qwen3VLForConditionalGeneration"
+  ],
+  "dtype": "float32",
+  "eos_token_id": 151645,
+  "hidden_size": 2560,
+  "image_token_id": 151655,
+  "model_type": "qwen3_vl",
+  "pad_token_id": 151643,
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "dtype": "float32",
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 2560,
+    "initializer_range": 0.02,
+    "intermediate_size": 9728,
+    "max_position_embeddings": 262144,
+    "model_type": "qwen3_vl_text",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 36,
+    "num_key_value_heads": 8,
+    "pad_token_id": 151643,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        24,
+        20,
+        20
+      ],
+      "rope_theta": 5000000,
+      "rope_type": "default"
+    },
+    "rope_theta": 5000000,
+    "use_cache": true,
+    "vocab_size": 152183
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.0",
+  "video_token_id": 151656,
+  "vision_config": {
+    "deepstack_visual_indexes": [
+      5,
+      11,
+      17
+    ],
+    "depth": 24,
+    "dtype": "float32",
+    "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": 2560,
+    "pad_token_id": 151643,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.57.0"
+}

mask_tokenizer_256x2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28536f6fb5224060eedd370c483c95336714e034375e75016438cbd2f168795c
+size 912357638

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2add7806bf141ba8581e80e23da487da58bfedc972a29b08d57c0b7d190112a2
+size 4939538656

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce57726ddd438f5cff222a21023aa926a7affee1f524dad2b5153427286828ce
+size 4944311048

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cc39b8a36af91574c8a3b1c785c66ab9c52d435d96bc2f71b857057a379eecd
+size 4944311104

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3406928acc9fe23ab218b8b597b82ee93456fbd01eefe6ad185b9163ca0fbcea
+size 4484072816

model.safetensors.index.json

@@ -0,0 +1,722 @@
+{
+  "metadata": {
+    "total_parameters": 603504576,
+    "total_size": 19312146432
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.17.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.29.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.30.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.30.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.32.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.32.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.32.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.32.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.32.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.32.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.32.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.32.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.32.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.32.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.32.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.4.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.5.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.norm.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00004.safetensors",
+    "model.visual.merger.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.merger.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.merger.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.merger.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.merger.norm.bias": "model-00001-of-00004.safetensors",
+    "model.visual.merger.norm.weight": "model-00001-of-00004.safetensors",
+    "model.visual.patch_embed.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.pos_embed.weight": "model-00001-of-00004.safetensors"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,39 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "disable_grouping": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Qwen2VLImageProcessorFast",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "input_data_format": null,
+  "max_pixels": null,
+  "merge_size": 2,
+  "min_pixels": null,
+  "pad_size": null,
+  "patch_size": 16,
+  "processor_class": "Qwen3VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "longest_edge": 16777216,
+    "shortest_edge": 65536
+  },
+  "temporal_patch_size": 2
+}

sam2.1_hiera_large.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2647878d5dfa5098f2f8649825738a9345572bae2d4350a2468587ece47dd318
+size 898083611

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "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|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6decf21aa9d65430562d0aa9bb07611aa7d2e8dddb567f1f1ab6d3b1d545fad1
+size 11519800

video_preprocessor_config.json

@@ -0,0 +1,43 @@
+{
+  "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_pad": null,
+  "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": 768,
+  "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,
+  "return_tensors": null,
+  "size": {
+    "longest_edge": 25165824,
+    "shortest_edge": 4096
+  },
+  "temporal_patch_size": 2,
+  "video_metadata": null,
+  "video_processor_type": "Qwen3VLVideoProcessor"
+}