Upload 22 files

.gitattributes

@@ -36,3 +36,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 Amazon/train/Industrial_and_Scientific_5_2016-10-2018-11.csv filter=lfs diff=lfs merge=lfs -text
 Amazon/train/Office_Products_5_2016-10-2018-11.csv filter=lfs diff=lfs merge=lfs -text
 Industrial_ckpt/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+Office_ckpt/tokenizer.json filter=lfs diff=lfs merge=lfs -text

Office_ckpt/added_tokens.json

@@ -0,0 +1,624 @@
+{
+  "</tool_call>": 151658,
+  "<a_0>": 151665,
+  "<a_101>": 151666,
+  "<a_102>": 151667,
+  "<a_106>": 151668,
+  "<a_116>": 151669,
+  "<a_117>": 151670,
+  "<a_118>": 151671,
+  "<a_11>": 151672,
+  "<a_120>": 151673,
+  "<a_122>": 151674,
+  "<a_123>": 151675,
+  "<a_127>": 151676,
+  "<a_130>": 151677,
+  "<a_131>": 151678,
+  "<a_133>": 151679,
+  "<a_135>": 151680,
+  "<a_137>": 151681,
+  "<a_142>": 151682,
+  "<a_143>": 151683,
+  "<a_145>": 151684,
+  "<a_14>": 151685,
+  "<a_160>": 151686,
+  "<a_162>": 151687,
+  "<a_166>": 151688,
+  "<a_170>": 151689,
+  "<a_177>": 151690,
+  "<a_178>": 151691,
+  "<a_180>": 151692,
+  "<a_183>": 151693,
+  "<a_184>": 151694,
+  "<a_186>": 151695,
+  "<a_187>": 151696,
+  "<a_188>": 151697,
+  "<a_18>": 151698,
+  "<a_191>": 151699,
+  "<a_192>": 151700,
+  "<a_195>": 151701,
+  "<a_197>": 151702,
+  "<a_1>": 151703,
+  "<a_201>": 151704,
+  "<a_202>": 151705,
+  "<a_203>": 151706,
+  "<a_204>": 151707,
+  "<a_205>": 151708,
+  "<a_20>": 151709,
+  "<a_212>": 151710,
+  "<a_216>": 151711,
+  "<a_221>": 151712,
+  "<a_224>": 151713,
+  "<a_225>": 151714,
+  "<a_230>": 151715,
+  "<a_232>": 151716,
+  "<a_235>": 151717,
+  "<a_238>": 151718,
+  "<a_23>": 151719,
+  "<a_242>": 151720,
+  "<a_248>": 151721,
+  "<a_250>": 151722,
+  "<a_252>": 151723,
+  "<a_253>": 151724,
+  "<a_255>": 151725,
+  "<a_28>": 151726,
+  "<a_31>": 151727,
+  "<a_34>": 151728,
+  "<a_39>": 151729,
+  "<a_3>": 151730,
+  "<a_41>": 151731,
+  "<a_45>": 151732,
+  "<a_46>": 151733,
+  "<a_47>": 151734,
+  "<a_53>": 151735,
+  "<a_55>": 151736,
+  "<a_60>": 151737,
+  "<a_66>": 151738,
+  "<a_67>": 151739,
+  "<a_74>": 151740,
+  "<a_76>": 151741,
+  "<a_77>": 151742,
+  "<a_78>": 151743,
+  "<a_7>": 151744,
+  "<a_81>": 151745,
+  "<a_84>": 151746,
+  "<a_87>": 151747,
+  "<a_91>": 151748,
+  "<a_93>": 151749,
+  "<a_94>": 151750,
+  "<a_96>": 151751,
+  "<a_99>": 151752,
+  "<b_0>": 151753,
+  "<b_100>": 151754,
+  "<b_101>": 151755,
+  "<b_102>": 151756,
+  "<b_103>": 151757,
+  "<b_104>": 151758,
+  "<b_105>": 151759,
+  "<b_106>": 151760,
+  "<b_107>": 151761,
+  "<b_108>": 151762,
+  "<b_109>": 151763,
+  "<b_10>": 151764,
+  "<b_110>": 151765,
+  "<b_111>": 151766,
+  "<b_112>": 151767,
+  "<b_113>": 151768,
+  "<b_114>": 151769,
+  "<b_115>": 151770,
+  "<b_116>": 151771,
+  "<b_117>": 151772,
+  "<b_118>": 151773,
+  "<b_119>": 151774,
+  "<b_11>": 151775,
+  "<b_120>": 151776,
+  "<b_121>": 151777,
+  "<b_122>": 151778,
+  "<b_123>": 151779,
+  "<b_124>": 151780,
+  "<b_125>": 151781,
+  "<b_126>": 151782,
+  "<b_127>": 151783,
+  "<b_128>": 151784,
+  "<b_129>": 151785,
+  "<b_12>": 151786,
+  "<b_130>": 151787,
+  "<b_131>": 151788,
+  "<b_132>": 151789,
+  "<b_133>": 151790,
+  "<b_134>": 151791,
+  "<b_135>": 151792,
+  "<b_136>": 151793,
+  "<b_137>": 151794,
+  "<b_138>": 151795,
+  "<b_139>": 151796,
+  "<b_13>": 151797,
+  "<b_140>": 151798,
+  "<b_141>": 151799,
+  "<b_142>": 151800,
+  "<b_143>": 151801,
+  "<b_144>": 151802,
+  "<b_145>": 151803,
+  "<b_146>": 151804,
+  "<b_147>": 151805,
+  "<b_148>": 151806,
+  "<b_149>": 151807,
+  "<b_14>": 151808,
+  "<b_150>": 151809,
+  "<b_151>": 151810,
+  "<b_152>": 151811,
+  "<b_153>": 151812,
+  "<b_154>": 151813,
+  "<b_155>": 151814,
+  "<b_156>": 151815,
+  "<b_157>": 151816,
+  "<b_158>": 151817,
+  "<b_159>": 151818,
+  "<b_15>": 151819,
+  "<b_160>": 151820,
+  "<b_161>": 151821,
+  "<b_162>": 151822,
+  "<b_163>": 151823,
+  "<b_164>": 151824,
+  "<b_165>": 151825,
+  "<b_166>": 151826,
+  "<b_167>": 151827,
+  "<b_168>": 151828,
+  "<b_169>": 151829,
+  "<b_16>": 151830,
+  "<b_170>": 151831,
+  "<b_171>": 151832,
+  "<b_172>": 151833,
+  "<b_173>": 151834,
+  "<b_174>": 151835,
+  "<b_175>": 151836,
+  "<b_176>": 151837,
+  "<b_177>": 151838,
+  "<b_178>": 151839,
+  "<b_179>": 151840,
+  "<b_17>": 151841,
+  "<b_180>": 151842,
+  "<b_181>": 151843,
+  "<b_182>": 151844,
+  "<b_183>": 151845,
+  "<b_184>": 151846,
+  "<b_185>": 151847,
+  "<b_186>": 151848,
+  "<b_187>": 151849,
+  "<b_188>": 151850,
+  "<b_189>": 151851,
+  "<b_18>": 151852,
+  "<b_190>": 151853,
+  "<b_191>": 151854,
+  "<b_192>": 151855,
+  "<b_193>": 151856,
+  "<b_194>": 151857,
+  "<b_195>": 151858,
+  "<b_196>": 151859,
+  "<b_197>": 151860,
+  "<b_198>": 151861,
+  "<b_199>": 151862,
+  "<b_19>": 151863,
+  "<b_1>": 151864,
+  "<b_200>": 151865,
+  "<b_201>": 151866,
+  "<b_202>": 151867,
+  "<b_203>": 151868,
+  "<b_204>": 151869,
+  "<b_205>": 151870,
+  "<b_206>": 151871,
+  "<b_207>": 151872,
+  "<b_208>": 151873,
+  "<b_209>": 151874,
+  "<b_20>": 151875,
+  "<b_210>": 151876,
+  "<b_211>": 151877,
+  "<b_212>": 151878,
+  "<b_213>": 151879,
+  "<b_214>": 151880,
+  "<b_215>": 151881,
+  "<b_216>": 151882,
+  "<b_217>": 151883,
+  "<b_218>": 151884,
+  "<b_219>": 151885,
+  "<b_21>": 151886,
+  "<b_220>": 151887,
+  "<b_221>": 151888,
+  "<b_222>": 151889,
+  "<b_223>": 151890,
+  "<b_224>": 151891,
+  "<b_225>": 151892,
+  "<b_226>": 151893,
+  "<b_227>": 151894,
+  "<b_228>": 151895,
+  "<b_229>": 151896,
+  "<b_22>": 151897,
+  "<b_230>": 151898,
+  "<b_231>": 151899,
+  "<b_232>": 151900,
+  "<b_233>": 151901,
+  "<b_234>": 151902,
+  "<b_235>": 151903,
+  "<b_236>": 151904,
+  "<b_237>": 151905,
+  "<b_238>": 151906,
+  "<b_239>": 151907,
+  "<b_23>": 151908,
+  "<b_240>": 151909,
+  "<b_241>": 151910,
+  "<b_242>": 151911,
+  "<b_243>": 151912,
+  "<b_244>": 151913,
+  "<b_245>": 151914,
+  "<b_246>": 151915,
+  "<b_247>": 151916,
+  "<b_248>": 151917,
+  "<b_249>": 151918,
+  "<b_24>": 151919,
+  "<b_250>": 151920,
+  "<b_251>": 151921,
+  "<b_252>": 151922,
+  "<b_253>": 151923,
+  "<b_254>": 151924,
+  "<b_255>": 151925,
+  "<b_25>": 151926,
+  "<b_26>": 151927,
+  "<b_27>": 151928,
+  "<b_28>": 151929,
+  "<b_29>": 151930,
+  "<b_2>": 151931,
+  "<b_30>": 151932,
+  "<b_31>": 151933,
+  "<b_32>": 151934,
+  "<b_33>": 151935,
+  "<b_34>": 151936,
+  "<b_35>": 151937,
+  "<b_36>": 151938,
+  "<b_37>": 151939,
+  "<b_38>": 151940,
+  "<b_39>": 151941,
+  "<b_3>": 151942,
+  "<b_40>": 151943,
+  "<b_41>": 151944,
+  "<b_42>": 151945,
+  "<b_43>": 151946,
+  "<b_44>": 151947,
+  "<b_45>": 151948,
+  "<b_46>": 151949,
+  "<b_47>": 151950,
+  "<b_48>": 151951,
+  "<b_49>": 151952,
+  "<b_4>": 151953,
+  "<b_50>": 151954,
+  "<b_51>": 151955,
+  "<b_52>": 151956,
+  "<b_53>": 151957,
+  "<b_54>": 151958,
+  "<b_55>": 151959,
+  "<b_56>": 151960,
+  "<b_57>": 151961,
+  "<b_58>": 151962,
+  "<b_59>": 151963,
+  "<b_5>": 151964,
+  "<b_60>": 151965,
+  "<b_61>": 151966,
+  "<b_62>": 151967,
+  "<b_63>": 151968,
+  "<b_64>": 151969,
+  "<b_65>": 151970,
+  "<b_66>": 151971,
+  "<b_67>": 151972,
+  "<b_68>": 151973,
+  "<b_69>": 151974,
+  "<b_6>": 151975,
+  "<b_70>": 151976,
+  "<b_71>": 151977,
+  "<b_72>": 151978,
+  "<b_73>": 151979,
+  "<b_74>": 151980,
+  "<b_75>": 151981,
+  "<b_76>": 151982,
+  "<b_77>": 151983,
+  "<b_78>": 151984,
+  "<b_79>": 151985,
+  "<b_7>": 151986,
+  "<b_80>": 151987,
+  "<b_81>": 151988,
+  "<b_82>": 151989,
+  "<b_83>": 151990,
+  "<b_84>": 151991,
+  "<b_85>": 151992,
+  "<b_86>": 151993,
+  "<b_87>": 151994,
+  "<b_88>": 151995,
+  "<b_89>": 151996,
+  "<b_8>": 151997,
+  "<b_90>": 151998,
+  "<b_91>": 151999,
+  "<b_92>": 152000,
+  "<b_93>": 152001,
+  "<b_94>": 152002,
+  "<b_95>": 152003,
+  "<b_96>": 152004,
+  "<b_97>": 152005,
+  "<b_98>": 152006,
+  "<b_99>": 152007,
+  "<b_9>": 152008,
+  "<c_0>": 152009,
+  "<c_100>": 152010,
+  "<c_101>": 152011,
+  "<c_102>": 152012,
+  "<c_103>": 152013,
+  "<c_104>": 152014,
+  "<c_105>": 152015,
+  "<c_106>": 152016,
+  "<c_107>": 152017,
+  "<c_108>": 152018,
+  "<c_109>": 152019,
+  "<c_10>": 152020,
+  "<c_110>": 152021,
+  "<c_111>": 152022,
+  "<c_112>": 152023,
+  "<c_113>": 152024,
+  "<c_114>": 152025,
+  "<c_115>": 152026,
+  "<c_116>": 152027,
+  "<c_117>": 152028,
+  "<c_118>": 152029,
+  "<c_119>": 152030,
+  "<c_11>": 152031,
+  "<c_120>": 152032,
+  "<c_121>": 152033,
+  "<c_122>": 152034,
+  "<c_123>": 152035,
+  "<c_124>": 152036,
+  "<c_125>": 152037,
+  "<c_126>": 152038,
+  "<c_127>": 152039,
+  "<c_128>": 152040,
+  "<c_129>": 152041,
+  "<c_12>": 152042,
+  "<c_130>": 152043,
+  "<c_131>": 152044,
+  "<c_132>": 152045,
+  "<c_133>": 152046,
+  "<c_134>": 152047,
+  "<c_135>": 152048,
+  "<c_136>": 152049,
+  "<c_137>": 152050,
+  "<c_138>": 152051,
+  "<c_139>": 152052,
+  "<c_13>": 152053,
+  "<c_140>": 152054,
+  "<c_141>": 152055,
+  "<c_142>": 152056,
+  "<c_143>": 152057,
+  "<c_144>": 152058,
+  "<c_145>": 152059,
+  "<c_146>": 152060,
+  "<c_147>": 152061,
+  "<c_148>": 152062,
+  "<c_149>": 152063,
+  "<c_14>": 152064,
+  "<c_150>": 152065,
+  "<c_151>": 152066,
+  "<c_152>": 152067,
+  "<c_153>": 152068,
+  "<c_154>": 152069,
+  "<c_155>": 152070,
+  "<c_156>": 152071,
+  "<c_157>": 152072,
+  "<c_158>": 152073,
+  "<c_159>": 152074,
+  "<c_15>": 152075,
+  "<c_160>": 152076,
+  "<c_161>": 152077,
+  "<c_162>": 152078,
+  "<c_163>": 152079,
+  "<c_164>": 152080,
+  "<c_165>": 152081,
+  "<c_166>": 152082,
+  "<c_167>": 152083,
+  "<c_168>": 152084,
+  "<c_169>": 152085,
+  "<c_16>": 152086,
+  "<c_170>": 152087,
+  "<c_171>": 152088,
+  "<c_172>": 152089,
+  "<c_173>": 152090,
+  "<c_174>": 152091,
+  "<c_175>": 152092,
+  "<c_176>": 152093,
+  "<c_177>": 152094,
+  "<c_178>": 152095,
+  "<c_179>": 152096,
+  "<c_17>": 152097,
+  "<c_180>": 152098,
+  "<c_181>": 152099,
+  "<c_182>": 152100,
+  "<c_183>": 152101,
+  "<c_184>": 152102,
+  "<c_185>": 152103,
+  "<c_186>": 152104,
+  "<c_187>": 152105,
+  "<c_188>": 152106,
+  "<c_189>": 152107,
+  "<c_18>": 152108,
+  "<c_190>": 152109,
+  "<c_191>": 152110,
+  "<c_192>": 152111,
+  "<c_193>": 152112,
+  "<c_194>": 152113,
+  "<c_195>": 152114,
+  "<c_196>": 152115,
+  "<c_197>": 152116,
+  "<c_198>": 152117,
+  "<c_199>": 152118,
+  "<c_19>": 152119,
+  "<c_1>": 152120,
+  "<c_200>": 152121,
+  "<c_201>": 152122,
+  "<c_202>": 152123,
+  "<c_203>": 152124,
+  "<c_204>": 152125,
+  "<c_205>": 152126,
+  "<c_206>": 152127,
+  "<c_207>": 152128,
+  "<c_208>": 152129,
+  "<c_209>": 152130,
+  "<c_20>": 152131,
+  "<c_210>": 152132,
+  "<c_211>": 152133,
+  "<c_212>": 152134,
+  "<c_213>": 152135,
+  "<c_214>": 152136,
+  "<c_215>": 152137,
+  "<c_216>": 152138,
+  "<c_217>": 152139,
+  "<c_218>": 152140,
+  "<c_219>": 152141,
+  "<c_21>": 152142,
+  "<c_220>": 152143,
+  "<c_221>": 152144,
+  "<c_222>": 152145,
+  "<c_223>": 152146,
+  "<c_224>": 152147,
+  "<c_225>": 152148,
+  "<c_226>": 152149,
+  "<c_227>": 152150,
+  "<c_228>": 152151,
+  "<c_229>": 152152,
+  "<c_22>": 152153,
+  "<c_230>": 152154,
+  "<c_231>": 152155,
+  "<c_232>": 152156,
+  "<c_233>": 152157,
+  "<c_234>": 152158,
+  "<c_235>": 152159,
+  "<c_236>": 152160,
+  "<c_237>": 152161,
+  "<c_238>": 152162,
+  "<c_239>": 152163,
+  "<c_23>": 152164,
+  "<c_240>": 152165,
+  "<c_241>": 152166,
+  "<c_242>": 152167,
+  "<c_243>": 152168,
+  "<c_244>": 152169,
+  "<c_245>": 152170,
+  "<c_246>": 152171,
+  "<c_247>": 152172,
+  "<c_248>": 152173,
+  "<c_249>": 152174,
+  "<c_24>": 152175,
+  "<c_250>": 152176,
+  "<c_251>": 152177,
+  "<c_252>": 152178,
+  "<c_253>": 152179,
+  "<c_254>": 152180,
+  "<c_255>": 152181,
+  "<c_25>": 152182,
+  "<c_26>": 152183,
+  "<c_27>": 152184,
+  "<c_28>": 152185,
+  "<c_29>": 152186,
+  "<c_2>": 152187,
+  "<c_30>": 152188,
+  "<c_31>": 152189,
+  "<c_32>": 152190,
+  "<c_33>": 152191,
+  "<c_34>": 152192,
+  "<c_35>": 152193,
+  "<c_36>": 152194,
+  "<c_37>": 152195,
+  "<c_38>": 152196,
+  "<c_39>": 152197,
+  "<c_3>": 152198,
+  "<c_40>": 152199,
+  "<c_41>": 152200,
+  "<c_42>": 152201,
+  "<c_43>": 152202,
+  "<c_44>": 152203,
+  "<c_45>": 152204,
+  "<c_46>": 152205,
+  "<c_47>": 152206,
+  "<c_48>": 152207,
+  "<c_49>": 152208,
+  "<c_4>": 152209,
+  "<c_50>": 152210,
+  "<c_51>": 152211,
+  "<c_52>": 152212,
+  "<c_53>": 152213,
+  "<c_54>": 152214,
+  "<c_55>": 152215,
+  "<c_56>": 152216,
+  "<c_57>": 152217,
+  "<c_58>": 152218,
+  "<c_59>": 152219,
+  "<c_5>": 152220,
+  "<c_60>": 152221,
+  "<c_61>": 152222,
+  "<c_62>": 152223,
+  "<c_63>": 152224,
+  "<c_64>": 152225,
+  "<c_65>": 152226,
+  "<c_66>": 152227,
+  "<c_67>": 152228,
+  "<c_68>": 152229,
+  "<c_69>": 152230,
+  "<c_6>": 152231,
+  "<c_70>": 152232,
+  "<c_71>": 152233,
+  "<c_72>": 152234,
+  "<c_73>": 152235,
+  "<c_74>": 152236,
+  "<c_75>": 152237,
+  "<c_76>": 152238,
+  "<c_77>": 152239,
+  "<c_78>": 152240,
+  "<c_79>": 152241,
+  "<c_7>": 152242,
+  "<c_80>": 152243,
+  "<c_81>": 152244,
+  "<c_82>": 152245,
+  "<c_83>": 152246,
+  "<c_84>": 152247,
+  "<c_85>": 152248,
+  "<c_86>": 152249,
+  "<c_87>": 152250,
+  "<c_88>": 152251,
+  "<c_89>": 152252,
+  "<c_8>": 152253,
+  "<c_90>": 152254,
+  "<c_91>": 152255,
+  "<c_92>": 152256,
+  "<c_93>": 152257,
+  "<c_94>": 152258,
+  "<c_95>": 152259,
+  "<c_96>": 152260,
+  "<c_97>": 152261,
+  "<c_98>": 152262,
+  "<c_99>": 152263,
+  "<c_9>": 152264,
+  "<tool_call>": 151657,
+  "<|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
+}

Office_ckpt/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# 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' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\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 %}

Office_ckpt/config.json

@@ -0,0 +1,58 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.55.4",
+  "use_cache": null,
+  "use_sliding_window": false,
+  "vocab_size": 152265
+}

Office_ckpt/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "transformers_version": "4.55.4"
+}

Office_ckpt/latest.txt

@@ -0,0 +1 @@
+global_step1038

Office_ckpt/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36d2a2034ebb05cb71c510897f2795b31164e50f17b270bc25d2be3ad9a17b22
+size 15984

Office_ckpt/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3c6a047e69957a4fcef4efdb6800b809ec2139e77ee22d4fcfa89f2cd323ecd
+size 15920

Office_ckpt/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ccd8154731e6030b615ae4037f15896288ad29f8b09e158fb8c62ca6f907b9a
+size 15920

Office_ckpt/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6f89fccab8305e6fcb9c2f091f7bfd4540f0cdfeb328fd939b82b833352c8cf
+size 15984

Office_ckpt/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b22090cf19a126293a342f5a96142916c9fd77589ffe907ab9db4ee04994b96b
+size 15984

Office_ckpt/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3b75c906af53e2002f47853b7021f6c107cf9d9c95a63e992594be66db3cf2b
+size 15984

Office_ckpt/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e6508a4ffa116a655533ee330827208aac9391f37a8d25df4ae3803fbc11122
+size 15984

Office_ckpt/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12740e5b2c1d46dbf0ca69e3f7d898ace8ffa7c77093bf7db2d8141c26a09286
+size 15920

Office_ckpt/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f73111d858ccd50a2c47017ecebd12fecd5ef13eed7f9930c60873e2f5b84b2
+size 1064

Office_ckpt/special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "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": "<|im_end|>"
+}

Office_ckpt/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:727f175c5ff824b7cfa45c8577e293b356b255b215a504834c4451298bd5c50a
+size 11532202

Office_ckpt/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29ca1599f8dd75c9f347a26477d6bf3c4afdc0ad9dabb85ee1e6e8e951f3f33e
+size 7544

Office_ckpt/zero_to_fp32.py

@@ -0,0 +1,760 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example:
+#   python zero_to_fp32.py . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import gc
+import json
+import numpy as np
+from tqdm import tqdm
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device, weights_only=False)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+    total_files = len(files)
+    state_dicts = []
+    for f in tqdm(files, desc='Loading checkpoint shards'):
+        state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+class GatheredTensor:
+    """
+    A pseudo tensor that collects partitioned weights.
+    It is more memory efficient when there are multiple groups.
+    """
+
+    def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
+        self.flat_groups = flat_groups
+        self.flat_groups_offset = flat_groups_offset
+        self.offset = offset
+        self.partitioned_numel = partitioned_numel
+        self.shape = shape
+        self.dtype = self.flat_groups[0][0].dtype
+
+    def contiguous(self):
+        """
+        Merge partitioned weights from flat_groups into a single tensor.
+        """
+        end_idx = self.offset + self.partitioned_numel
+        world_size = len(self.flat_groups)
+        pad_flat_param_chunks = []
+
+        for rank_i in range(world_size):
+            # for each rank, we need to collect weights from related group/groups
+            flat_groups_at_rank_i = self.flat_groups[rank_i]
+            start_group_id = None
+            end_group_id = None
+            for group_id in range(len(self.flat_groups_offset)):
+                if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
+                    start_group_id = group_id
+                if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
+                    end_group_id = group_id
+                    break
+            # collect weights from related group/groups
+            for group_id in range(start_group_id, end_group_id + 1):
+                flat_tensor = flat_groups_at_rank_i[group_id]
+                start_offset = self.offset - self.flat_groups_offset[group_id]
+                end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
+                pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
+
+        # collect weights from all ranks
+        pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
+        param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
+        return param
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
+
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
+    for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # memory efficient tensor
+        tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
+        state_dict[name] = tensor
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def to_torch_tensor(state_dict, return_empty_tensor=False):
+    """
+    Convert state_dict of GatheredTensor to torch tensor
+    """
+    torch_state_dict = {}
+    converted_tensors = {}
+    for name, tensor in state_dict.items():
+        tensor_id = id(tensor)
+        if tensor_id in converted_tensors:  # shared tensors
+            shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
+            torch_state_dict[name] = shared_tensor
+        else:
+            converted_tensors[tensor_id] = name
+            if return_empty_tensor:
+                torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
+            else:
+                torch_state_dict[name] = tensor.contiguous()
+    return torch_state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                             tag=None,
+                                             exclude_frozen_parameters=False,
+                                             lazy_mode=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+        - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
+          Convert the pesduo tensor to torch tensor by ``.contiguous()``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
+    You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint. Or you can load state_dict in lazy mode ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
+        for name, lazy_tensor in state_dict.item():
+            tensor = lazy_tensor.contiguous()  # to cpu
+            print(name, tensor)
+            # del tensor to release memory if it no longer in use
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+    if lazy_mode:
+        return state_dict
+    else:
+        return to_torch_tensor(state_dict)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               tag=None,
+                                               exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                                          tag,
+                                                          exclude_frozen_parameters,
+                                                          lazy_mode=True)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        # an memory-efficient approach for sharding
+        empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
+        state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model by shard
+    os.makedirs(output_dir, exist_ok=True)
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
+        shard_state_dict = to_torch_tensor(shard_state_dict)
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard_state_dict, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard_state_dict, output_path)
+        # release the memory of current shard
+        for tensor_name in list(shard_state_dict.keys()):
+            del state_dict[tensor_name]
+            del shard_state_dict[tensor_name]
+        del shard_state_dict
+        gc.collect()
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument("output_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)