init new model

.gitattributes

@@ -33,3 +33,13 @@ 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
+model-00004-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00006-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00008-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00003-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00007-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00009-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00001-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00005-of-00009.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -108,4 +108,4 @@ LaBahasa 11B was trained on an extensive 9 billion high quality bilingual datase
 ### Training Procedure
 LaBahasa 11B was trained on customized training methodology modifications to enhance:
 * Image input processing capabilities through integration with Llama 3.2's vision features
-* Indonesian language understanding and generation
+* Indonesian language understanding and generation

added_tokens.json

@@ -0,0 +1,1611 @@
+{
+  "<|0.00|>": 50365,
+  "<|0.02|>": 50366,
+  "<|0.04|>": 50367,
+  "<|0.06|>": 50368,
+  "<|0.08|>": 50369,
+  "<|0.10|>": 50370,
+  "<|0.12|>": 50371,
+  "<|0.14|>": 50372,
+  "<|0.16|>": 50373,
+  "<|0.18|>": 50374,
+  "<|0.20|>": 50375,
+  "<|0.22|>": 50376,
+  "<|0.24|>": 50377,
+  "<|0.26|>": 50378,
+  "<|0.28|>": 50379,
+  "<|0.30|>": 50380,
+  "<|0.32|>": 50381,
+  "<|0.34|>": 50382,
+  "<|0.36|>": 50383,
+  "<|0.38|>": 50384,
+  "<|0.40|>": 50385,
+  "<|0.42|>": 50386,
+  "<|0.44|>": 50387,
+  "<|0.46|>": 50388,
+  "<|0.48|>": 50389,
+  "<|0.50|>": 50390,
+  "<|0.52|>": 50391,
+  "<|0.54|>": 50392,
+  "<|0.56|>": 50393,
+  "<|0.58|>": 50394,
+  "<|0.60|>": 50395,
+  "<|0.62|>": 50396,
+  "<|0.64|>": 50397,
+  "<|0.66|>": 50398,
+  "<|0.68|>": 50399,
+  "<|0.70|>": 50400,
+  "<|0.72|>": 50401,
+  "<|0.74|>": 50402,
+  "<|0.76|>": 50403,
+  "<|0.78|>": 50404,
+  "<|0.80|>": 50405,
+  "<|0.82|>": 50406,
+  "<|0.84|>": 50407,
+  "<|0.86|>": 50408,
+  "<|0.88|>": 50409,
+  "<|0.90|>": 50410,
+  "<|0.92|>": 50411,
+  "<|0.94|>": 50412,
+  "<|0.96|>": 50413,
+  "<|0.98|>": 50414,
+  "<|1.00|>": 50415,
+  "<|1.02|>": 50416,
+  "<|1.04|>": 50417,
+  "<|1.06|>": 50418,
+  "<|1.08|>": 50419,
+  "<|1.10|>": 50420,
+  "<|1.12|>": 50421,
+  "<|1.14|>": 50422,
+  "<|1.16|>": 50423,
+  "<|1.18|>": 50424,
+  "<|1.20|>": 50425,
+  "<|1.22|>": 50426,
+  "<|1.24|>": 50427,
+  "<|1.26|>": 50428,
+  "<|1.28|>": 50429,
+  "<|1.30|>": 50430,
+  "<|1.32|>": 50431,
+  "<|1.34|>": 50432,
+  "<|1.36|>": 50433,
+  "<|1.38|>": 50434,
+  "<|1.40|>": 50435,
+  "<|1.42|>": 50436,
+  "<|1.44|>": 50437,
+  "<|1.46|>": 50438,
+  "<|1.48|>": 50439,
+  "<|1.50|>": 50440,
+  "<|1.52|>": 50441,
+  "<|1.54|>": 50442,
+  "<|1.56|>": 50443,
+  "<|1.58|>": 50444,
+  "<|1.60|>": 50445,
+  "<|1.62|>": 50446,
+  "<|1.64|>": 50447,
+  "<|1.66|>": 50448,
+  "<|1.68|>": 50449,
+  "<|1.70|>": 50450,
+  "<|1.72|>": 50451,
+  "<|1.74|>": 50452,
+  "<|1.76|>": 50453,
+  "<|1.78|>": 50454,
+  "<|1.80|>": 50455,
+  "<|1.82|>": 50456,
+  "<|1.84|>": 50457,
+  "<|1.86|>": 50458,
+  "<|1.88|>": 50459,
+  "<|1.90|>": 50460,
+  "<|1.92|>": 50461,
+  "<|1.94|>": 50462,
+  "<|1.96|>": 50463,
+  "<|1.98|>": 50464,
+  "<|10.00|>": 50865,
+  "<|10.02|>": 50866,
+  "<|10.04|>": 50867,
+  "<|10.06|>": 50868,
+  "<|10.08|>": 50869,
+  "<|10.10|>": 50870,
+  "<|10.12|>": 50871,
+  "<|10.14|>": 50872,
+  "<|10.16|>": 50873,
+  "<|10.18|>": 50874,
+  "<|10.20|>": 50875,
+  "<|10.22|>": 50876,
+  "<|10.24|>": 50877,
+  "<|10.26|>": 50878,
+  "<|10.28|>": 50879,
+  "<|10.30|>": 50880,
+  "<|10.32|>": 50881,
+  "<|10.34|>": 50882,
+  "<|10.36|>": 50883,
+  "<|10.38|>": 50884,
+  "<|10.40|>": 50885,
+  "<|10.42|>": 50886,
+  "<|10.44|>": 50887,
+  "<|10.46|>": 50888,
+  "<|10.48|>": 50889,
+  "<|10.50|>": 50890,
+  "<|10.52|>": 50891,
+  "<|10.54|>": 50892,
+  "<|10.56|>": 50893,
+  "<|10.58|>": 50894,
+  "<|10.60|>": 50895,
+  "<|10.62|>": 50896,
+  "<|10.64|>": 50897,
+  "<|10.66|>": 50898,
+  "<|10.68|>": 50899,
+  "<|10.70|>": 50900,
+  "<|10.72|>": 50901,
+  "<|10.74|>": 50902,
+  "<|10.76|>": 50903,
+  "<|10.78|>": 50904,
+  "<|10.80|>": 50905,
+  "<|10.82|>": 50906,
+  "<|10.84|>": 50907,
+  "<|10.86|>": 50908,
+  "<|10.88|>": 50909,
+  "<|10.90|>": 50910,
+  "<|10.92|>": 50911,
+  "<|10.94|>": 50912,
+  "<|10.96|>": 50913,
+  "<|10.98|>": 50914,
+  "<|11.00|>": 50915,
+  "<|11.02|>": 50916,
+  "<|11.04|>": 50917,
+  "<|11.06|>": 50918,
+  "<|11.08|>": 50919,
+  "<|11.10|>": 50920,
+  "<|11.12|>": 50921,
+  "<|11.14|>": 50922,
+  "<|11.16|>": 50923,
+  "<|11.18|>": 50924,
+  "<|11.20|>": 50925,
+  "<|11.22|>": 50926,
+  "<|11.24|>": 50927,
+  "<|11.26|>": 50928,
+  "<|11.28|>": 50929,
+  "<|11.30|>": 50930,
+  "<|11.32|>": 50931,
+  "<|11.34|>": 50932,
+  "<|11.36|>": 50933,
+  "<|11.38|>": 50934,
+  "<|11.40|>": 50935,
+  "<|11.42|>": 50936,
+  "<|11.44|>": 50937,
+  "<|11.46|>": 50938,
+  "<|11.48|>": 50939,
+  "<|11.50|>": 50940,
+  "<|11.52|>": 50941,
+  "<|11.54|>": 50942,
+  "<|11.56|>": 50943,
+  "<|11.58|>": 50944,
+  "<|11.60|>": 50945,
+  "<|11.62|>": 50946,
+  "<|11.64|>": 50947,
+  "<|11.66|>": 50948,
+  "<|11.68|>": 50949,
+  "<|11.70|>": 50950,
+  "<|11.72|>": 50951,
+  "<|11.74|>": 50952,
+  "<|11.76|>": 50953,
+  "<|11.78|>": 50954,
+  "<|11.80|>": 50955,
+  "<|11.82|>": 50956,
+  "<|11.84|>": 50957,
+  "<|11.86|>": 50958,
+  "<|11.88|>": 50959,
+  "<|11.90|>": 50960,
+  "<|11.92|>": 50961,
+  "<|11.94|>": 50962,
+  "<|11.96|>": 50963,
+  "<|11.98|>": 50964,
+  "<|12.00|>": 50965,
+  "<|12.02|>": 50966,
+  "<|12.04|>": 50967,
+  "<|12.06|>": 50968,
+  "<|12.08|>": 50969,
+  "<|12.10|>": 50970,
+  "<|12.12|>": 50971,
+  "<|12.14|>": 50972,
+  "<|12.16|>": 50973,
+  "<|12.18|>": 50974,
+  "<|12.20|>": 50975,
+  "<|12.22|>": 50976,
+  "<|12.24|>": 50977,
+  "<|12.26|>": 50978,
+  "<|12.28|>": 50979,
+  "<|12.30|>": 50980,
+  "<|12.32|>": 50981,
+  "<|12.34|>": 50982,
+  "<|12.36|>": 50983,
+  "<|12.38|>": 50984,
+  "<|12.40|>": 50985,
+  "<|12.42|>": 50986,
+  "<|12.44|>": 50987,
+  "<|12.46|>": 50988,
+  "<|12.48|>": 50989,
+  "<|12.50|>": 50990,
+  "<|12.52|>": 50991,
+  "<|12.54|>": 50992,
+  "<|12.56|>": 50993,
+  "<|12.58|>": 50994,
+  "<|12.60|>": 50995,
+  "<|12.62|>": 50996,
+  "<|12.64|>": 50997,
+  "<|12.66|>": 50998,
+  "<|12.68|>": 50999,
+  "<|12.70|>": 51000,
+  "<|12.72|>": 51001,
+  "<|12.74|>": 51002,
+  "<|12.76|>": 51003,
+  "<|12.78|>": 51004,
+  "<|12.80|>": 51005,
+  "<|12.82|>": 51006,
+  "<|12.84|>": 51007,
+  "<|12.86|>": 51008,
+  "<|12.88|>": 51009,
+  "<|12.90|>": 51010,
+  "<|12.92|>": 51011,
+  "<|12.94|>": 51012,
+  "<|12.96|>": 51013,
+  "<|12.98|>": 51014,
+  "<|13.00|>": 51015,
+  "<|13.02|>": 51016,
+  "<|13.04|>": 51017,
+  "<|13.06|>": 51018,
+  "<|13.08|>": 51019,
+  "<|13.10|>": 51020,
+  "<|13.12|>": 51021,
+  "<|13.14|>": 51022,
+  "<|13.16|>": 51023,
+  "<|13.18|>": 51024,
+  "<|13.20|>": 51025,
+  "<|13.22|>": 51026,
+  "<|13.24|>": 51027,
+  "<|13.26|>": 51028,
+  "<|13.28|>": 51029,
+  "<|13.30|>": 51030,
+  "<|13.32|>": 51031,
+  "<|13.34|>": 51032,
+  "<|13.36|>": 51033,
+  "<|13.38|>": 51034,
+  "<|13.40|>": 51035,
+  "<|13.42|>": 51036,
+  "<|13.44|>": 51037,
+  "<|13.46|>": 51038,
+  "<|13.48|>": 51039,
+  "<|13.50|>": 51040,
+  "<|13.52|>": 51041,
+  "<|13.54|>": 51042,
+  "<|13.56|>": 51043,
+  "<|13.58|>": 51044,
+  "<|13.60|>": 51045,
+  "<|13.62|>": 51046,
+  "<|13.64|>": 51047,
+  "<|13.66|>": 51048,
+  "<|13.68|>": 51049,
+  "<|13.70|>": 51050,
+  "<|13.72|>": 51051,
+  "<|13.74|>": 51052,
+  "<|13.76|>": 51053,
+  "<|13.78|>": 51054,
+  "<|13.80|>": 51055,
+  "<|13.82|>": 51056,
+  "<|13.84|>": 51057,
+  "<|13.86|>": 51058,
+  "<|13.88|>": 51059,
+  "<|13.90|>": 51060,
+  "<|13.92|>": 51061,
+  "<|13.94|>": 51062,
+  "<|13.96|>": 51063,
+  "<|13.98|>": 51064,
+  "<|14.00|>": 51065,
+  "<|14.02|>": 51066,
+  "<|14.04|>": 51067,
+  "<|14.06|>": 51068,
+  "<|14.08|>": 51069,
+  "<|14.10|>": 51070,
+  "<|14.12|>": 51071,
+  "<|14.14|>": 51072,
+  "<|14.16|>": 51073,
+  "<|14.18|>": 51074,
+  "<|14.20|>": 51075,
+  "<|14.22|>": 51076,
+  "<|14.24|>": 51077,
+  "<|14.26|>": 51078,
+  "<|14.28|>": 51079,
+  "<|14.30|>": 51080,
+  "<|14.32|>": 51081,
+  "<|14.34|>": 51082,
+  "<|14.36|>": 51083,
+  "<|14.38|>": 51084,
+  "<|14.40|>": 51085,
+  "<|14.42|>": 51086,
+  "<|14.44|>": 51087,
+  "<|14.46|>": 51088,
+  "<|14.48|>": 51089,
+  "<|14.50|>": 51090,
+  "<|14.52|>": 51091,
+  "<|14.54|>": 51092,
+  "<|14.56|>": 51093,
+  "<|14.58|>": 51094,
+  "<|14.60|>": 51095,
+  "<|14.62|>": 51096,
+  "<|14.64|>": 51097,
+  "<|14.66|>": 51098,
+  "<|14.68|>": 51099,
+  "<|14.70|>": 51100,
+  "<|14.72|>": 51101,
+  "<|14.74|>": 51102,
+  "<|14.76|>": 51103,
+  "<|14.78|>": 51104,
+  "<|14.80|>": 51105,
+  "<|14.82|>": 51106,
+  "<|14.84|>": 51107,
+  "<|14.86|>": 51108,
+  "<|14.88|>": 51109,
+  "<|14.90|>": 51110,
+  "<|14.92|>": 51111,
+  "<|14.94|>": 51112,
+  "<|14.96|>": 51113,
+  "<|14.98|>": 51114,
+  "<|15.00|>": 51115,
+  "<|15.02|>": 51116,
+  "<|15.04|>": 51117,
+  "<|15.06|>": 51118,
+  "<|15.08|>": 51119,
+  "<|15.10|>": 51120,
+  "<|15.12|>": 51121,
+  "<|15.14|>": 51122,
+  "<|15.16|>": 51123,
+  "<|15.18|>": 51124,
+  "<|15.20|>": 51125,
+  "<|15.22|>": 51126,
+  "<|15.24|>": 51127,
+  "<|15.26|>": 51128,
+  "<|15.28|>": 51129,
+  "<|15.30|>": 51130,
+  "<|15.32|>": 51131,
+  "<|15.34|>": 51132,
+  "<|15.36|>": 51133,
+  "<|15.38|>": 51134,
+  "<|15.40|>": 51135,
+  "<|15.42|>": 51136,
+  "<|15.44|>": 51137,
+  "<|15.46|>": 51138,
+  "<|15.48|>": 51139,
+  "<|15.50|>": 51140,
+  "<|15.52|>": 51141,
+  "<|15.54|>": 51142,
+  "<|15.56|>": 51143,
+  "<|15.58|>": 51144,
+  "<|15.60|>": 51145,
+  "<|15.62|>": 51146,
+  "<|15.64|>": 51147,
+  "<|15.66|>": 51148,
+  "<|15.68|>": 51149,
+  "<|15.70|>": 51150,
+  "<|15.72|>": 51151,
+  "<|15.74|>": 51152,
+  "<|15.76|>": 51153,
+  "<|15.78|>": 51154,
+  "<|15.80|>": 51155,
+  "<|15.82|>": 51156,
+  "<|15.84|>": 51157,
+  "<|15.86|>": 51158,
+  "<|15.88|>": 51159,
+  "<|15.90|>": 51160,
+  "<|15.92|>": 51161,
+  "<|15.94|>": 51162,
+  "<|15.96|>": 51163,
+  "<|15.98|>": 51164,
+  "<|16.00|>": 51165,
+  "<|16.02|>": 51166,
+  "<|16.04|>": 51167,
+  "<|16.06|>": 51168,
+  "<|16.08|>": 51169,
+  "<|16.10|>": 51170,
+  "<|16.12|>": 51171,
+  "<|16.14|>": 51172,
+  "<|16.16|>": 51173,
+  "<|16.18|>": 51174,
+  "<|16.20|>": 51175,
+  "<|16.22|>": 51176,
+  "<|16.24|>": 51177,
+  "<|16.26|>": 51178,
+  "<|16.28|>": 51179,
+  "<|16.30|>": 51180,
+  "<|16.32|>": 51181,
+  "<|16.34|>": 51182,
+  "<|16.36|>": 51183,
+  "<|16.38|>": 51184,
+  "<|16.40|>": 51185,
+  "<|16.42|>": 51186,
+  "<|16.44|>": 51187,
+  "<|16.46|>": 51188,
+  "<|16.48|>": 51189,
+  "<|16.50|>": 51190,
+  "<|16.52|>": 51191,
+  "<|16.54|>": 51192,
+  "<|16.56|>": 51193,
+  "<|16.58|>": 51194,
+  "<|16.60|>": 51195,
+  "<|16.62|>": 51196,
+  "<|16.64|>": 51197,
+  "<|16.66|>": 51198,
+  "<|16.68|>": 51199,
+  "<|16.70|>": 51200,
+  "<|16.72|>": 51201,
+  "<|16.74|>": 51202,
+  "<|16.76|>": 51203,
+  "<|16.78|>": 51204,
+  "<|16.80|>": 51205,
+  "<|16.82|>": 51206,
+  "<|16.84|>": 51207,
+  "<|16.86|>": 51208,
+  "<|16.88|>": 51209,
+  "<|16.90|>": 51210,
+  "<|16.92|>": 51211,
+  "<|16.94|>": 51212,
+  "<|16.96|>": 51213,
+  "<|16.98|>": 51214,
+  "<|17.00|>": 51215,
+  "<|17.02|>": 51216,
+  "<|17.04|>": 51217,
+  "<|17.06|>": 51218,
+  "<|17.08|>": 51219,
+  "<|17.10|>": 51220,
+  "<|17.12|>": 51221,
+  "<|17.14|>": 51222,
+  "<|17.16|>": 51223,
+  "<|17.18|>": 51224,
+  "<|17.20|>": 51225,
+  "<|17.22|>": 51226,
+  "<|17.24|>": 51227,
+  "<|17.26|>": 51228,
+  "<|17.28|>": 51229,
+  "<|17.30|>": 51230,
+  "<|17.32|>": 51231,
+  "<|17.34|>": 51232,
+  "<|17.36|>": 51233,
+  "<|17.38|>": 51234,
+  "<|17.40|>": 51235,
+  "<|17.42|>": 51236,
+  "<|17.44|>": 51237,
+  "<|17.46|>": 51238,
+  "<|17.48|>": 51239,
+  "<|17.50|>": 51240,
+  "<|17.52|>": 51241,
+  "<|17.54|>": 51242,
+  "<|17.56|>": 51243,
+  "<|17.58|>": 51244,
+  "<|17.60|>": 51245,
+  "<|17.62|>": 51246,
+  "<|17.64|>": 51247,
+  "<|17.66|>": 51248,
+  "<|17.68|>": 51249,
+  "<|17.70|>": 51250,
+  "<|17.72|>": 51251,
+  "<|17.74|>": 51252,
+  "<|17.76|>": 51253,
+  "<|17.78|>": 51254,
+  "<|17.80|>": 51255,
+  "<|17.82|>": 51256,
+  "<|17.84|>": 51257,
+  "<|17.86|>": 51258,
+  "<|17.88|>": 51259,
+  "<|17.90|>": 51260,
+  "<|17.92|>": 51261,
+  "<|17.94|>": 51262,
+  "<|17.96|>": 51263,
+  "<|17.98|>": 51264,
+  "<|18.00|>": 51265,
+  "<|18.02|>": 51266,
+  "<|18.04|>": 51267,
+  "<|18.06|>": 51268,
+  "<|18.08|>": 51269,
+  "<|18.10|>": 51270,
+  "<|18.12|>": 51271,
+  "<|18.14|>": 51272,
+  "<|18.16|>": 51273,
+  "<|18.18|>": 51274,
+  "<|18.20|>": 51275,
+  "<|18.22|>": 51276,
+  "<|18.24|>": 51277,
+  "<|18.26|>": 51278,
+  "<|18.28|>": 51279,
+  "<|18.30|>": 51280,
+  "<|18.32|>": 51281,
+  "<|18.34|>": 51282,
+  "<|18.36|>": 51283,
+  "<|18.38|>": 51284,
+  "<|18.40|>": 51285,
+  "<|18.42|>": 51286,
+  "<|18.44|>": 51287,
+  "<|18.46|>": 51288,
+  "<|18.48|>": 51289,
+  "<|18.50|>": 51290,
+  "<|18.52|>": 51291,
+  "<|18.54|>": 51292,
+  "<|18.56|>": 51293,
+  "<|18.58|>": 51294,
+  "<|18.60|>": 51295,
+  "<|18.62|>": 51296,
+  "<|18.64|>": 51297,
+  "<|18.66|>": 51298,
+  "<|18.68|>": 51299,
+  "<|18.70|>": 51300,
+  "<|18.72|>": 51301,
+  "<|18.74|>": 51302,
+  "<|18.76|>": 51303,
+  "<|18.78|>": 51304,
+  "<|18.80|>": 51305,
+  "<|18.82|>": 51306,
+  "<|18.84|>": 51307,
+  "<|18.86|>": 51308,
+  "<|18.88|>": 51309,
+  "<|18.90|>": 51310,
+  "<|18.92|>": 51311,
+  "<|18.94|>": 51312,
+  "<|18.96|>": 51313,
+  "<|18.98|>": 51314,
+  "<|19.00|>": 51315,
+  "<|19.02|>": 51316,
+  "<|19.04|>": 51317,
+  "<|19.06|>": 51318,
+  "<|19.08|>": 51319,
+  "<|19.10|>": 51320,
+  "<|19.12|>": 51321,
+  "<|19.14|>": 51322,
+  "<|19.16|>": 51323,
+  "<|19.18|>": 51324,
+  "<|19.20|>": 51325,
+  "<|19.22|>": 51326,
+  "<|19.24|>": 51327,
+  "<|19.26|>": 51328,
+  "<|19.28|>": 51329,
+  "<|19.30|>": 51330,
+  "<|19.32|>": 51331,
+  "<|19.34|>": 51332,
+  "<|19.36|>": 51333,
+  "<|19.38|>": 51334,
+  "<|19.40|>": 51335,
+  "<|19.42|>": 51336,
+  "<|19.44|>": 51337,
+  "<|19.46|>": 51338,
+  "<|19.48|>": 51339,
+  "<|19.50|>": 51340,
+  "<|19.52|>": 51341,
+  "<|19.54|>": 51342,
+  "<|19.56|>": 51343,
+  "<|19.58|>": 51344,
+  "<|19.60|>": 51345,
+  "<|19.62|>": 51346,
+  "<|19.64|>": 51347,
+  "<|19.66|>": 51348,
+  "<|19.68|>": 51349,
+  "<|19.70|>": 51350,
+  "<|19.72|>": 51351,
+  "<|19.74|>": 51352,
+  "<|19.76|>": 51353,
+  "<|19.78|>": 51354,
+  "<|19.80|>": 51355,
+  "<|19.82|>": 51356,
+  "<|19.84|>": 51357,
+  "<|19.86|>": 51358,
+  "<|19.88|>": 51359,
+  "<|19.90|>": 51360,
+  "<|19.92|>": 51361,
+  "<|19.94|>": 51362,
+  "<|19.96|>": 51363,
+  "<|19.98|>": 51364,
+  "<|2.00|>": 50465,
+  "<|2.02|>": 50466,
+  "<|2.04|>": 50467,
+  "<|2.06|>": 50468,
+  "<|2.08|>": 50469,
+  "<|2.10|>": 50470,
+  "<|2.12|>": 50471,
+  "<|2.14|>": 50472,
+  "<|2.16|>": 50473,
+  "<|2.18|>": 50474,
+  "<|2.20|>": 50475,
+  "<|2.22|>": 50476,
+  "<|2.24|>": 50477,
+  "<|2.26|>": 50478,
+  "<|2.28|>": 50479,
+  "<|2.30|>": 50480,
+  "<|2.32|>": 50481,
+  "<|2.34|>": 50482,
+  "<|2.36|>": 50483,
+  "<|2.38|>": 50484,
+  "<|2.40|>": 50485,
+  "<|2.42|>": 50486,
+  "<|2.44|>": 50487,
+  "<|2.46|>": 50488,
+  "<|2.48|>": 50489,
+  "<|2.50|>": 50490,
+  "<|2.52|>": 50491,
+  "<|2.54|>": 50492,
+  "<|2.56|>": 50493,
+  "<|2.58|>": 50494,
+  "<|2.60|>": 50495,
+  "<|2.62|>": 50496,
+  "<|2.64|>": 50497,
+  "<|2.66|>": 50498,
+  "<|2.68|>": 50499,
+  "<|2.70|>": 50500,
+  "<|2.72|>": 50501,
+  "<|2.74|>": 50502,
+  "<|2.76|>": 50503,
+  "<|2.78|>": 50504,
+  "<|2.80|>": 50505,
+  "<|2.82|>": 50506,
+  "<|2.84|>": 50507,
+  "<|2.86|>": 50508,
+  "<|2.88|>": 50509,
+  "<|2.90|>": 50510,
+  "<|2.92|>": 50511,
+  "<|2.94|>": 50512,
+  "<|2.96|>": 50513,
+  "<|2.98|>": 50514,
+  "<|20.00|>": 51365,
+  "<|20.02|>": 51366,
+  "<|20.04|>": 51367,
+  "<|20.06|>": 51368,
+  "<|20.08|>": 51369,
+  "<|20.10|>": 51370,
+  "<|20.12|>": 51371,
+  "<|20.14|>": 51372,
+  "<|20.16|>": 51373,
+  "<|20.18|>": 51374,
+  "<|20.20|>": 51375,
+  "<|20.22|>": 51376,
+  "<|20.24|>": 51377,
+  "<|20.26|>": 51378,
+  "<|20.28|>": 51379,
+  "<|20.30|>": 51380,
+  "<|20.32|>": 51381,
+  "<|20.34|>": 51382,
+  "<|20.36|>": 51383,
+  "<|20.38|>": 51384,
+  "<|20.40|>": 51385,
+  "<|20.42|>": 51386,
+  "<|20.44|>": 51387,
+  "<|20.46|>": 51388,
+  "<|20.48|>": 51389,
+  "<|20.50|>": 51390,
+  "<|20.52|>": 51391,
+  "<|20.54|>": 51392,
+  "<|20.56|>": 51393,
+  "<|20.58|>": 51394,
+  "<|20.60|>": 51395,
+  "<|20.62|>": 51396,
+  "<|20.64|>": 51397,
+  "<|20.66|>": 51398,
+  "<|20.68|>": 51399,
+  "<|20.70|>": 51400,
+  "<|20.72|>": 51401,
+  "<|20.74|>": 51402,
+  "<|20.76|>": 51403,
+  "<|20.78|>": 51404,
+  "<|20.80|>": 51405,
+  "<|20.82|>": 51406,
+  "<|20.84|>": 51407,
+  "<|20.86|>": 51408,
+  "<|20.88|>": 51409,
+  "<|20.90|>": 51410,
+  "<|20.92|>": 51411,
+  "<|20.94|>": 51412,
+  "<|20.96|>": 51413,
+  "<|20.98|>": 51414,
+  "<|21.00|>": 51415,
+  "<|21.02|>": 51416,
+  "<|21.04|>": 51417,
+  "<|21.06|>": 51418,
+  "<|21.08|>": 51419,
+  "<|21.10|>": 51420,
+  "<|21.12|>": 51421,
+  "<|21.14|>": 51422,
+  "<|21.16|>": 51423,
+  "<|21.18|>": 51424,
+  "<|21.20|>": 51425,
+  "<|21.22|>": 51426,
+  "<|21.24|>": 51427,
+  "<|21.26|>": 51428,
+  "<|21.28|>": 51429,
+  "<|21.30|>": 51430,
+  "<|21.32|>": 51431,
+  "<|21.34|>": 51432,
+  "<|21.36|>": 51433,
+  "<|21.38|>": 51434,
+  "<|21.40|>": 51435,
+  "<|21.42|>": 51436,
+  "<|21.44|>": 51437,
+  "<|21.46|>": 51438,
+  "<|21.48|>": 51439,
+  "<|21.50|>": 51440,
+  "<|21.52|>": 51441,
+  "<|21.54|>": 51442,
+  "<|21.56|>": 51443,
+  "<|21.58|>": 51444,
+  "<|21.60|>": 51445,
+  "<|21.62|>": 51446,
+  "<|21.64|>": 51447,
+  "<|21.66|>": 51448,
+  "<|21.68|>": 51449,
+  "<|21.70|>": 51450,
+  "<|21.72|>": 51451,
+  "<|21.74|>": 51452,
+  "<|21.76|>": 51453,
+  "<|21.78|>": 51454,
+  "<|21.80|>": 51455,
+  "<|21.82|>": 51456,
+  "<|21.84|>": 51457,
+  "<|21.86|>": 51458,
+  "<|21.88|>": 51459,
+  "<|21.90|>": 51460,
+  "<|21.92|>": 51461,
+  "<|21.94|>": 51462,
+  "<|21.96|>": 51463,
+  "<|21.98|>": 51464,
+  "<|22.00|>": 51465,
+  "<|22.02|>": 51466,
+  "<|22.04|>": 51467,
+  "<|22.06|>": 51468,
+  "<|22.08|>": 51469,
+  "<|22.10|>": 51470,
+  "<|22.12|>": 51471,
+  "<|22.14|>": 51472,
+  "<|22.16|>": 51473,
+  "<|22.18|>": 51474,
+  "<|22.20|>": 51475,
+  "<|22.22|>": 51476,
+  "<|22.24|>": 51477,
+  "<|22.26|>": 51478,
+  "<|22.28|>": 51479,
+  "<|22.30|>": 51480,
+  "<|22.32|>": 51481,
+  "<|22.34|>": 51482,
+  "<|22.36|>": 51483,
+  "<|22.38|>": 51484,
+  "<|22.40|>": 51485,
+  "<|22.42|>": 51486,
+  "<|22.44|>": 51487,
+  "<|22.46|>": 51488,
+  "<|22.48|>": 51489,
+  "<|22.50|>": 51490,
+  "<|22.52|>": 51491,
+  "<|22.54|>": 51492,
+  "<|22.56|>": 51493,
+  "<|22.58|>": 51494,
+  "<|22.60|>": 51495,
+  "<|22.62|>": 51496,
+  "<|22.64|>": 51497,
+  "<|22.66|>": 51498,
+  "<|22.68|>": 51499,
+  "<|22.70|>": 51500,
+  "<|22.72|>": 51501,
+  "<|22.74|>": 51502,
+  "<|22.76|>": 51503,
+  "<|22.78|>": 51504,
+  "<|22.80|>": 51505,
+  "<|22.82|>": 51506,
+  "<|22.84|>": 51507,
+  "<|22.86|>": 51508,
+  "<|22.88|>": 51509,
+  "<|22.90|>": 51510,
+  "<|22.92|>": 51511,
+  "<|22.94|>": 51512,
+  "<|22.96|>": 51513,
+  "<|22.98|>": 51514,
+  "<|23.00|>": 51515,
+  "<|23.02|>": 51516,
+  "<|23.04|>": 51517,
+  "<|23.06|>": 51518,
+  "<|23.08|>": 51519,
+  "<|23.10|>": 51520,
+  "<|23.12|>": 51521,
+  "<|23.14|>": 51522,
+  "<|23.16|>": 51523,
+  "<|23.18|>": 51524,
+  "<|23.20|>": 51525,
+  "<|23.22|>": 51526,
+  "<|23.24|>": 51527,
+  "<|23.26|>": 51528,
+  "<|23.28|>": 51529,
+  "<|23.30|>": 51530,
+  "<|23.32|>": 51531,
+  "<|23.34|>": 51532,
+  "<|23.36|>": 51533,
+  "<|23.38|>": 51534,
+  "<|23.40|>": 51535,
+  "<|23.42|>": 51536,
+  "<|23.44|>": 51537,
+  "<|23.46|>": 51538,
+  "<|23.48|>": 51539,
+  "<|23.50|>": 51540,
+  "<|23.52|>": 51541,
+  "<|23.54|>": 51542,
+  "<|23.56|>": 51543,
+  "<|23.58|>": 51544,
+  "<|23.60|>": 51545,
+  "<|23.62|>": 51546,
+  "<|23.64|>": 51547,
+  "<|23.66|>": 51548,
+  "<|23.68|>": 51549,
+  "<|23.70|>": 51550,
+  "<|23.72|>": 51551,
+  "<|23.74|>": 51552,
+  "<|23.76|>": 51553,
+  "<|23.78|>": 51554,
+  "<|23.80|>": 51555,
+  "<|23.82|>": 51556,
+  "<|23.84|>": 51557,
+  "<|23.86|>": 51558,
+  "<|23.88|>": 51559,
+  "<|23.90|>": 51560,
+  "<|23.92|>": 51561,
+  "<|23.94|>": 51562,
+  "<|23.96|>": 51563,
+  "<|23.98|>": 51564,
+  "<|24.00|>": 51565,
+  "<|24.02|>": 51566,
+  "<|24.04|>": 51567,
+  "<|24.06|>": 51568,
+  "<|24.08|>": 51569,
+  "<|24.10|>": 51570,
+  "<|24.12|>": 51571,
+  "<|24.14|>": 51572,
+  "<|24.16|>": 51573,
+  "<|24.18|>": 51574,
+  "<|24.20|>": 51575,
+  "<|24.22|>": 51576,
+  "<|24.24|>": 51577,
+  "<|24.26|>": 51578,
+  "<|24.28|>": 51579,
+  "<|24.30|>": 51580,
+  "<|24.32|>": 51581,
+  "<|24.34|>": 51582,
+  "<|24.36|>": 51583,
+  "<|24.38|>": 51584,
+  "<|24.40|>": 51585,
+  "<|24.42|>": 51586,
+  "<|24.44|>": 51587,
+  "<|24.46|>": 51588,
+  "<|24.48|>": 51589,
+  "<|24.50|>": 51590,
+  "<|24.52|>": 51591,
+  "<|24.54|>": 51592,
+  "<|24.56|>": 51593,
+  "<|24.58|>": 51594,
+  "<|24.60|>": 51595,
+  "<|24.62|>": 51596,
+  "<|24.64|>": 51597,
+  "<|24.66|>": 51598,
+  "<|24.68|>": 51599,
+  "<|24.70|>": 51600,
+  "<|24.72|>": 51601,
+  "<|24.74|>": 51602,
+  "<|24.76|>": 51603,
+  "<|24.78|>": 51604,
+  "<|24.80|>": 51605,
+  "<|24.82|>": 51606,
+  "<|24.84|>": 51607,
+  "<|24.86|>": 51608,
+  "<|24.88|>": 51609,
+  "<|24.90|>": 51610,
+  "<|24.92|>": 51611,
+  "<|24.94|>": 51612,
+  "<|24.96|>": 51613,
+  "<|24.98|>": 51614,
+  "<|25.00|>": 51615,
+  "<|25.02|>": 51616,
+  "<|25.04|>": 51617,
+  "<|25.06|>": 51618,
+  "<|25.08|>": 51619,
+  "<|25.10|>": 51620,
+  "<|25.12|>": 51621,
+  "<|25.14|>": 51622,
+  "<|25.16|>": 51623,
+  "<|25.18|>": 51624,
+  "<|25.20|>": 51625,
+  "<|25.22|>": 51626,
+  "<|25.24|>": 51627,
+  "<|25.26|>": 51628,
+  "<|25.28|>": 51629,
+  "<|25.30|>": 51630,
+  "<|25.32|>": 51631,
+  "<|25.34|>": 51632,
+  "<|25.36|>": 51633,
+  "<|25.38|>": 51634,
+  "<|25.40|>": 51635,
+  "<|25.42|>": 51636,
+  "<|25.44|>": 51637,
+  "<|25.46|>": 51638,
+  "<|25.48|>": 51639,
+  "<|25.50|>": 51640,
+  "<|25.52|>": 51641,
+  "<|25.54|>": 51642,
+  "<|25.56|>": 51643,
+  "<|25.58|>": 51644,
+  "<|25.60|>": 51645,
+  "<|25.62|>": 51646,
+  "<|25.64|>": 51647,
+  "<|25.66|>": 51648,
+  "<|25.68|>": 51649,
+  "<|25.70|>": 51650,
+  "<|25.72|>": 51651,
+  "<|25.74|>": 51652,
+  "<|25.76|>": 51653,
+  "<|25.78|>": 51654,
+  "<|25.80|>": 51655,
+  "<|25.82|>": 51656,
+  "<|25.84|>": 51657,
+  "<|25.86|>": 51658,
+  "<|25.88|>": 51659,
+  "<|25.90|>": 51660,
+  "<|25.92|>": 51661,
+  "<|25.94|>": 51662,
+  "<|25.96|>": 51663,
+  "<|25.98|>": 51664,
+  "<|26.00|>": 51665,
+  "<|26.02|>": 51666,
+  "<|26.04|>": 51667,
+  "<|26.06|>": 51668,
+  "<|26.08|>": 51669,
+  "<|26.10|>": 51670,
+  "<|26.12|>": 51671,
+  "<|26.14|>": 51672,
+  "<|26.16|>": 51673,
+  "<|26.18|>": 51674,
+  "<|26.20|>": 51675,
+  "<|26.22|>": 51676,
+  "<|26.24|>": 51677,
+  "<|26.26|>": 51678,
+  "<|26.28|>": 51679,
+  "<|26.30|>": 51680,
+  "<|26.32|>": 51681,
+  "<|26.34|>": 51682,
+  "<|26.36|>": 51683,
+  "<|26.38|>": 51684,
+  "<|26.40|>": 51685,
+  "<|26.42|>": 51686,
+  "<|26.44|>": 51687,
+  "<|26.46|>": 51688,
+  "<|26.48|>": 51689,
+  "<|26.50|>": 51690,
+  "<|26.52|>": 51691,
+  "<|26.54|>": 51692,
+  "<|26.56|>": 51693,
+  "<|26.58|>": 51694,
+  "<|26.60|>": 51695,
+  "<|26.62|>": 51696,
+  "<|26.64|>": 51697,
+  "<|26.66|>": 51698,
+  "<|26.68|>": 51699,
+  "<|26.70|>": 51700,
+  "<|26.72|>": 51701,
+  "<|26.74|>": 51702,
+  "<|26.76|>": 51703,
+  "<|26.78|>": 51704,
+  "<|26.80|>": 51705,
+  "<|26.82|>": 51706,
+  "<|26.84|>": 51707,
+  "<|26.86|>": 51708,
+  "<|26.88|>": 51709,
+  "<|26.90|>": 51710,
+  "<|26.92|>": 51711,
+  "<|26.94|>": 51712,
+  "<|26.96|>": 51713,
+  "<|26.98|>": 51714,
+  "<|27.00|>": 51715,
+  "<|27.02|>": 51716,
+  "<|27.04|>": 51717,
+  "<|27.06|>": 51718,
+  "<|27.08|>": 51719,
+  "<|27.10|>": 51720,
+  "<|27.12|>": 51721,
+  "<|27.14|>": 51722,
+  "<|27.16|>": 51723,
+  "<|27.18|>": 51724,
+  "<|27.20|>": 51725,
+  "<|27.22|>": 51726,
+  "<|27.24|>": 51727,
+  "<|27.26|>": 51728,
+  "<|27.28|>": 51729,
+  "<|27.30|>": 51730,
+  "<|27.32|>": 51731,
+  "<|27.34|>": 51732,
+  "<|27.36|>": 51733,
+  "<|27.38|>": 51734,
+  "<|27.40|>": 51735,
+  "<|27.42|>": 51736,
+  "<|27.44|>": 51737,
+  "<|27.46|>": 51738,
+  "<|27.48|>": 51739,
+  "<|27.50|>": 51740,
+  "<|27.52|>": 51741,
+  "<|27.54|>": 51742,
+  "<|27.56|>": 51743,
+  "<|27.58|>": 51744,
+  "<|27.60|>": 51745,
+  "<|27.62|>": 51746,
+  "<|27.64|>": 51747,
+  "<|27.66|>": 51748,
+  "<|27.68|>": 51749,
+  "<|27.70|>": 51750,
+  "<|27.72|>": 51751,
+  "<|27.74|>": 51752,
+  "<|27.76|>": 51753,
+  "<|27.78|>": 51754,
+  "<|27.80|>": 51755,
+  "<|27.82|>": 51756,
+  "<|27.84|>": 51757,
+  "<|27.86|>": 51758,
+  "<|27.88|>": 51759,
+  "<|27.90|>": 51760,
+  "<|27.92|>": 51761,
+  "<|27.94|>": 51762,
+  "<|27.96|>": 51763,
+  "<|27.98|>": 51764,
+  "<|28.00|>": 51765,
+  "<|28.02|>": 51766,
+  "<|28.04|>": 51767,
+  "<|28.06|>": 51768,
+  "<|28.08|>": 51769,
+  "<|28.10|>": 51770,
+  "<|28.12|>": 51771,
+  "<|28.14|>": 51772,
+  "<|28.16|>": 51773,
+  "<|28.18|>": 51774,
+  "<|28.20|>": 51775,
+  "<|28.22|>": 51776,
+  "<|28.24|>": 51777,
+  "<|28.26|>": 51778,
+  "<|28.28|>": 51779,
+  "<|28.30|>": 51780,
+  "<|28.32|>": 51781,
+  "<|28.34|>": 51782,
+  "<|28.36|>": 51783,
+  "<|28.38|>": 51784,
+  "<|28.40|>": 51785,
+  "<|28.42|>": 51786,
+  "<|28.44|>": 51787,
+  "<|28.46|>": 51788,
+  "<|28.48|>": 51789,
+  "<|28.50|>": 51790,
+  "<|28.52|>": 51791,
+  "<|28.54|>": 51792,
+  "<|28.56|>": 51793,
+  "<|28.58|>": 51794,
+  "<|28.60|>": 51795,
+  "<|28.62|>": 51796,
+  "<|28.64|>": 51797,
+  "<|28.66|>": 51798,
+  "<|28.68|>": 51799,
+  "<|28.70|>": 51800,
+  "<|28.72|>": 51801,
+  "<|28.74|>": 51802,
+  "<|28.76|>": 51803,
+  "<|28.78|>": 51804,
+  "<|28.80|>": 51805,
+  "<|28.82|>": 51806,
+  "<|28.84|>": 51807,
+  "<|28.86|>": 51808,
+  "<|28.88|>": 51809,
+  "<|28.90|>": 51810,
+  "<|28.92|>": 51811,
+  "<|28.94|>": 51812,
+  "<|28.96|>": 51813,
+  "<|28.98|>": 51814,
+  "<|29.00|>": 51815,
+  "<|29.02|>": 51816,
+  "<|29.04|>": 51817,
+  "<|29.06|>": 51818,
+  "<|29.08|>": 51819,
+  "<|29.10|>": 51820,
+  "<|29.12|>": 51821,
+  "<|29.14|>": 51822,
+  "<|29.16|>": 51823,
+  "<|29.18|>": 51824,
+  "<|29.20|>": 51825,
+  "<|29.22|>": 51826,
+  "<|29.24|>": 51827,
+  "<|29.26|>": 51828,
+  "<|29.28|>": 51829,
+  "<|29.30|>": 51830,
+  "<|29.32|>": 51831,
+  "<|29.34|>": 51832,
+  "<|29.36|>": 51833,
+  "<|29.38|>": 51834,
+  "<|29.40|>": 51835,
+  "<|29.42|>": 51836,
+  "<|29.44|>": 51837,
+  "<|29.46|>": 51838,
+  "<|29.48|>": 51839,
+  "<|29.50|>": 51840,
+  "<|29.52|>": 51841,
+  "<|29.54|>": 51842,
+  "<|29.56|>": 51843,
+  "<|29.58|>": 51844,
+  "<|29.60|>": 51845,
+  "<|29.62|>": 51846,
+  "<|29.64|>": 51847,
+  "<|29.66|>": 51848,
+  "<|29.68|>": 51849,
+  "<|29.70|>": 51850,
+  "<|29.72|>": 51851,
+  "<|29.74|>": 51852,
+  "<|29.76|>": 51853,
+  "<|29.78|>": 51854,
+  "<|29.80|>": 51855,
+  "<|29.82|>": 51856,
+  "<|29.84|>": 51857,
+  "<|29.86|>": 51858,
+  "<|29.88|>": 51859,
+  "<|29.90|>": 51860,
+  "<|29.92|>": 51861,
+  "<|29.94|>": 51862,
+  "<|29.96|>": 51863,
+  "<|29.98|>": 51864,
+  "<|3.00|>": 50515,
+  "<|3.02|>": 50516,
+  "<|3.04|>": 50517,
+  "<|3.06|>": 50518,
+  "<|3.08|>": 50519,
+  "<|3.10|>": 50520,
+  "<|3.12|>": 50521,
+  "<|3.14|>": 50522,
+  "<|3.16|>": 50523,
+  "<|3.18|>": 50524,
+  "<|3.20|>": 50525,
+  "<|3.22|>": 50526,
+  "<|3.24|>": 50527,
+  "<|3.26|>": 50528,
+  "<|3.28|>": 50529,
+  "<|3.30|>": 50530,
+  "<|3.32|>": 50531,
+  "<|3.34|>": 50532,
+  "<|3.36|>": 50533,
+  "<|3.38|>": 50534,
+  "<|3.40|>": 50535,
+  "<|3.42|>": 50536,
+  "<|3.44|>": 50537,
+  "<|3.46|>": 50538,
+  "<|3.48|>": 50539,
+  "<|3.50|>": 50540,
+  "<|3.52|>": 50541,
+  "<|3.54|>": 50542,
+  "<|3.56|>": 50543,
+  "<|3.58|>": 50544,
+  "<|3.60|>": 50545,
+  "<|3.62|>": 50546,
+  "<|3.64|>": 50547,
+  "<|3.66|>": 50548,
+  "<|3.68|>": 50549,
+  "<|3.70|>": 50550,
+  "<|3.72|>": 50551,
+  "<|3.74|>": 50552,
+  "<|3.76|>": 50553,
+  "<|3.78|>": 50554,
+  "<|3.80|>": 50555,
+  "<|3.82|>": 50556,
+  "<|3.84|>": 50557,
+  "<|3.86|>": 50558,
+  "<|3.88|>": 50559,
+  "<|3.90|>": 50560,
+  "<|3.92|>": 50561,
+  "<|3.94|>": 50562,
+  "<|3.96|>": 50563,
+  "<|3.98|>": 50564,
+  "<|30.00|>": 51865,
+  "<|4.00|>": 50565,
+  "<|4.02|>": 50566,
+  "<|4.04|>": 50567,
+  "<|4.06|>": 50568,
+  "<|4.08|>": 50569,
+  "<|4.10|>": 50570,
+  "<|4.12|>": 50571,
+  "<|4.14|>": 50572,
+  "<|4.16|>": 50573,
+  "<|4.18|>": 50574,
+  "<|4.20|>": 50575,
+  "<|4.22|>": 50576,
+  "<|4.24|>": 50577,
+  "<|4.26|>": 50578,
+  "<|4.28|>": 50579,
+  "<|4.30|>": 50580,
+  "<|4.32|>": 50581,
+  "<|4.34|>": 50582,
+  "<|4.36|>": 50583,
+  "<|4.38|>": 50584,
+  "<|4.40|>": 50585,
+  "<|4.42|>": 50586,
+  "<|4.44|>": 50587,
+  "<|4.46|>": 50588,
+  "<|4.48|>": 50589,
+  "<|4.50|>": 50590,
+  "<|4.52|>": 50591,
+  "<|4.54|>": 50592,
+  "<|4.56|>": 50593,
+  "<|4.58|>": 50594,
+  "<|4.60|>": 50595,
+  "<|4.62|>": 50596,
+  "<|4.64|>": 50597,
+  "<|4.66|>": 50598,
+  "<|4.68|>": 50599,
+  "<|4.70|>": 50600,
+  "<|4.72|>": 50601,
+  "<|4.74|>": 50602,
+  "<|4.76|>": 50603,
+  "<|4.78|>": 50604,
+  "<|4.80|>": 50605,
+  "<|4.82|>": 50606,
+  "<|4.84|>": 50607,
+  "<|4.86|>": 50608,
+  "<|4.88|>": 50609,
+  "<|4.90|>": 50610,
+  "<|4.92|>": 50611,
+  "<|4.94|>": 50612,
+  "<|4.96|>": 50613,
+  "<|4.98|>": 50614,
+  "<|5.00|>": 50615,
+  "<|5.02|>": 50616,
+  "<|5.04|>": 50617,
+  "<|5.06|>": 50618,
+  "<|5.08|>": 50619,
+  "<|5.10|>": 50620,
+  "<|5.12|>": 50621,
+  "<|5.14|>": 50622,
+  "<|5.16|>": 50623,
+  "<|5.18|>": 50624,
+  "<|5.20|>": 50625,
+  "<|5.22|>": 50626,
+  "<|5.24|>": 50627,
+  "<|5.26|>": 50628,
+  "<|5.28|>": 50629,
+  "<|5.30|>": 50630,
+  "<|5.32|>": 50631,
+  "<|5.34|>": 50632,
+  "<|5.36|>": 50633,
+  "<|5.38|>": 50634,
+  "<|5.40|>": 50635,
+  "<|5.42|>": 50636,
+  "<|5.44|>": 50637,
+  "<|5.46|>": 50638,
+  "<|5.48|>": 50639,
+  "<|5.50|>": 50640,
+  "<|5.52|>": 50641,
+  "<|5.54|>": 50642,
+  "<|5.56|>": 50643,
+  "<|5.58|>": 50644,
+  "<|5.60|>": 50645,
+  "<|5.62|>": 50646,
+  "<|5.64|>": 50647,
+  "<|5.66|>": 50648,
+  "<|5.68|>": 50649,
+  "<|5.70|>": 50650,
+  "<|5.72|>": 50651,
+  "<|5.74|>": 50652,
+  "<|5.76|>": 50653,
+  "<|5.78|>": 50654,
+  "<|5.80|>": 50655,
+  "<|5.82|>": 50656,
+  "<|5.84|>": 50657,
+  "<|5.86|>": 50658,
+  "<|5.88|>": 50659,
+  "<|5.90|>": 50660,
+  "<|5.92|>": 50661,
+  "<|5.94|>": 50662,
+  "<|5.96|>": 50663,
+  "<|5.98|>": 50664,
+  "<|6.00|>": 50665,
+  "<|6.02|>": 50666,
+  "<|6.04|>": 50667,
+  "<|6.06|>": 50668,
+  "<|6.08|>": 50669,
+  "<|6.10|>": 50670,
+  "<|6.12|>": 50671,
+  "<|6.14|>": 50672,
+  "<|6.16|>": 50673,
+  "<|6.18|>": 50674,
+  "<|6.20|>": 50675,
+  "<|6.22|>": 50676,
+  "<|6.24|>": 50677,
+  "<|6.26|>": 50678,
+  "<|6.28|>": 50679,
+  "<|6.30|>": 50680,
+  "<|6.32|>": 50681,
+  "<|6.34|>": 50682,
+  "<|6.36|>": 50683,
+  "<|6.38|>": 50684,
+  "<|6.40|>": 50685,
+  "<|6.42|>": 50686,
+  "<|6.44|>": 50687,
+  "<|6.46|>": 50688,
+  "<|6.48|>": 50689,
+  "<|6.50|>": 50690,
+  "<|6.52|>": 50691,
+  "<|6.54|>": 50692,
+  "<|6.56|>": 50693,
+  "<|6.58|>": 50694,
+  "<|6.60|>": 50695,
+  "<|6.62|>": 50696,
+  "<|6.64|>": 50697,
+  "<|6.66|>": 50698,
+  "<|6.68|>": 50699,
+  "<|6.70|>": 50700,
+  "<|6.72|>": 50701,
+  "<|6.74|>": 50702,
+  "<|6.76|>": 50703,
+  "<|6.78|>": 50704,
+  "<|6.80|>": 50705,
+  "<|6.82|>": 50706,
+  "<|6.84|>": 50707,
+  "<|6.86|>": 50708,
+  "<|6.88|>": 50709,
+  "<|6.90|>": 50710,
+  "<|6.92|>": 50711,
+  "<|6.94|>": 50712,
+  "<|6.96|>": 50713,
+  "<|6.98|>": 50714,
+  "<|7.00|>": 50715,
+  "<|7.02|>": 50716,
+  "<|7.04|>": 50717,
+  "<|7.06|>": 50718,
+  "<|7.08|>": 50719,
+  "<|7.10|>": 50720,
+  "<|7.12|>": 50721,
+  "<|7.14|>": 50722,
+  "<|7.16|>": 50723,
+  "<|7.18|>": 50724,
+  "<|7.20|>": 50725,
+  "<|7.22|>": 50726,
+  "<|7.24|>": 50727,
+  "<|7.26|>": 50728,
+  "<|7.28|>": 50729,
+  "<|7.30|>": 50730,
+  "<|7.32|>": 50731,
+  "<|7.34|>": 50732,
+  "<|7.36|>": 50733,
+  "<|7.38|>": 50734,
+  "<|7.40|>": 50735,
+  "<|7.42|>": 50736,
+  "<|7.44|>": 50737,
+  "<|7.46|>": 50738,
+  "<|7.48|>": 50739,
+  "<|7.50|>": 50740,
+  "<|7.52|>": 50741,
+  "<|7.54|>": 50742,
+  "<|7.56|>": 50743,
+  "<|7.58|>": 50744,
+  "<|7.60|>": 50745,
+  "<|7.62|>": 50746,
+  "<|7.64|>": 50747,
+  "<|7.66|>": 50748,
+  "<|7.68|>": 50749,
+  "<|7.70|>": 50750,
+  "<|7.72|>": 50751,
+  "<|7.74|>": 50752,
+  "<|7.76|>": 50753,
+  "<|7.78|>": 50754,
+  "<|7.80|>": 50755,
+  "<|7.82|>": 50756,
+  "<|7.84|>": 50757,
+  "<|7.86|>": 50758,
+  "<|7.88|>": 50759,
+  "<|7.90|>": 50760,
+  "<|7.92|>": 50761,
+  "<|7.94|>": 50762,
+  "<|7.96|>": 50763,
+  "<|7.98|>": 50764,
+  "<|8.00|>": 50765,
+  "<|8.02|>": 50766,
+  "<|8.04|>": 50767,
+  "<|8.06|>": 50768,
+  "<|8.08|>": 50769,
+  "<|8.10|>": 50770,
+  "<|8.12|>": 50771,
+  "<|8.14|>": 50772,
+  "<|8.16|>": 50773,
+  "<|8.18|>": 50774,
+  "<|8.20|>": 50775,
+  "<|8.22|>": 50776,
+  "<|8.24|>": 50777,
+  "<|8.26|>": 50778,
+  "<|8.28|>": 50779,
+  "<|8.30|>": 50780,
+  "<|8.32|>": 50781,
+  "<|8.34|>": 50782,
+  "<|8.36|>": 50783,
+  "<|8.38|>": 50784,
+  "<|8.40|>": 50785,
+  "<|8.42|>": 50786,
+  "<|8.44|>": 50787,
+  "<|8.46|>": 50788,
+  "<|8.48|>": 50789,
+  "<|8.50|>": 50790,
+  "<|8.52|>": 50791,
+  "<|8.54|>": 50792,
+  "<|8.56|>": 50793,
+  "<|8.58|>": 50794,
+  "<|8.60|>": 50795,
+  "<|8.62|>": 50796,
+  "<|8.64|>": 50797,
+  "<|8.66|>": 50798,
+  "<|8.68|>": 50799,
+  "<|8.70|>": 50800,
+  "<|8.72|>": 50801,
+  "<|8.74|>": 50802,
+  "<|8.76|>": 50803,
+  "<|8.78|>": 50804,
+  "<|8.80|>": 50805,
+  "<|8.82|>": 50806,
+  "<|8.84|>": 50807,
+  "<|8.86|>": 50808,
+  "<|8.88|>": 50809,
+  "<|8.90|>": 50810,
+  "<|8.92|>": 50811,
+  "<|8.94|>": 50812,
+  "<|8.96|>": 50813,
+  "<|8.98|>": 50814,
+  "<|9.00|>": 50815,
+  "<|9.02|>": 50816,
+  "<|9.04|>": 50817,
+  "<|9.06|>": 50818,
+  "<|9.08|>": 50819,
+  "<|9.10|>": 50820,
+  "<|9.12|>": 50821,
+  "<|9.14|>": 50822,
+  "<|9.16|>": 50823,
+  "<|9.18|>": 50824,
+  "<|9.20|>": 50825,
+  "<|9.22|>": 50826,
+  "<|9.24|>": 50827,
+  "<|9.26|>": 50828,
+  "<|9.28|>": 50829,
+  "<|9.30|>": 50830,
+  "<|9.32|>": 50831,
+  "<|9.34|>": 50832,
+  "<|9.36|>": 50833,
+  "<|9.38|>": 50834,
+  "<|9.40|>": 50835,
+  "<|9.42|>": 50836,
+  "<|9.44|>": 50837,
+  "<|9.46|>": 50838,
+  "<|9.48|>": 50839,
+  "<|9.50|>": 50840,
+  "<|9.52|>": 50841,
+  "<|9.54|>": 50842,
+  "<|9.56|>": 50843,
+  "<|9.58|>": 50844,
+  "<|9.60|>": 50845,
+  "<|9.62|>": 50846,
+  "<|9.64|>": 50847,
+  "<|9.66|>": 50848,
+  "<|9.68|>": 50849,
+  "<|9.70|>": 50850,
+  "<|9.72|>": 50851,
+  "<|9.74|>": 50852,
+  "<|9.76|>": 50853,
+  "<|9.78|>": 50854,
+  "<|9.80|>": 50855,
+  "<|9.82|>": 50856,
+  "<|9.84|>": 50857,
+  "<|9.86|>": 50858,
+  "<|9.88|>": 50859,
+  "<|9.90|>": 50860,
+  "<|9.92|>": 50861,
+  "<|9.94|>": 50862,
+  "<|9.96|>": 50863,
+  "<|9.98|>": 50864,
+  "<|af|>": 50327,
+  "<|am|>": 50334,
+  "<|ar|>": 50272,
+  "<|as|>": 50350,
+  "<|az|>": 50304,
+  "<|ba|>": 50355,
+  "<|be|>": 50330,
+  "<|bg|>": 50292,
+  "<|bn|>": 50302,
+  "<|bo|>": 50347,
+  "<|br|>": 50309,
+  "<|bs|>": 50315,
+  "<|ca|>": 50270,
+  "<|cs|>": 50283,
+  "<|cy|>": 50297,
+  "<|da|>": 50285,
+  "<|de|>": 50261,
+  "<|el|>": 50281,
+  "<|endoftext|>": 50257,
+  "<|en|>": 50259,
+  "<|es|>": 50262,
+  "<|et|>": 50307,
+  "<|eu|>": 50310,
+  "<|fa|>": 50300,
+  "<|fi|>": 50277,
+  "<|fo|>": 50338,
+  "<|fr|>": 50265,
+  "<|gl|>": 50319,
+  "<|gu|>": 50333,
+  "<|haw|>": 50352,
+  "<|ha|>": 50354,
+  "<|he|>": 50279,
+  "<|hi|>": 50276,
+  "<|hr|>": 50291,
+  "<|ht|>": 50339,
+  "<|hu|>": 50286,
+  "<|hy|>": 50312,
+  "<|id|>": 50275,
+  "<|is|>": 50311,
+  "<|it|>": 50274,
+  "<|ja|>": 50266,
+  "<|jw|>": 50356,
+  "<|ka|>": 50329,
+  "<|kk|>": 50316,
+  "<|km|>": 50323,
+  "<|kn|>": 50306,
+  "<|ko|>": 50264,
+  "<|la|>": 50294,
+  "<|lb|>": 50345,
+  "<|ln|>": 50353,
+  "<|lo|>": 50336,
+  "<|lt|>": 50293,
+  "<|lv|>": 50301,
+  "<|mg|>": 50349,
+  "<|mi|>": 50295,
+  "<|mk|>": 50308,
+  "<|ml|>": 50296,
+  "<|mn|>": 50314,
+  "<|mr|>": 50320,
+  "<|ms|>": 50282,
+  "<|mt|>": 50343,
+  "<|my|>": 50346,
+  "<|ne|>": 50313,
+  "<|nl|>": 50271,
+  "<|nn|>": 50342,
+  "<|nospeech|>": 50363,
+  "<|notimestamps|>": 50364,
+  "<|no|>": 50288,
+  "<|oc|>": 50328,
+  "<|pa|>": 50321,
+  "<|pl|>": 50269,
+  "<|ps|>": 50340,
+  "<|pt|>": 50267,
+  "<|ro|>": 50284,
+  "<|ru|>": 50263,
+  "<|sa|>": 50344,
+  "<|sd|>": 50332,
+  "<|si|>": 50322,
+  "<|sk|>": 50298,
+  "<|sl|>": 50305,
+  "<|sn|>": 50324,
+  "<|so|>": 50326,
+  "<|sq|>": 50317,
+  "<|sr|>": 50303,
+  "<|startoflm|>": 50361,
+  "<|startofprev|>": 50362,
+  "<|startoftranscript|>": 50258,
+  "<|su|>": 50357,
+  "<|sv|>": 50273,
+  "<|sw|>": 50318,
+  "<|ta|>": 50287,
+  "<|te|>": 50299,
+  "<|tg|>": 50331,
+  "<|th|>": 50289,
+  "<|tk|>": 50341,
+  "<|tl|>": 50348,
+  "<|transcribe|>": 50360,
+  "<|translate|>": 50359,
+  "<|tr|>": 50268,
+  "<|tt|>": 50351,
+  "<|uk|>": 50280,
+  "<|ur|>": 50290,
+  "<|uz|>": 50337,
+  "<|vi|>": 50278,
+  "<|yi|>": 50335,
+  "<|yo|>": 50325,
+  "<|yue|>": 50358,
+  "<|zh|>": 50260
+}

bahasa_config.py

@@ -0,0 +1,171 @@
+import dataclasses
+from enum import Enum
+from typing import Any, Dict, List, Optional, Union
+
+import transformers
+
+
+@dataclasses.dataclass
+class LoraConfigSimplified:
+    """
+    Low Rank Approximation (LoRA) configuration.
+
+    Used for language and audio models separately.
+    """
+
+    # The rank of the approximation
+    r: int = 0
+    lora_alpha: float = 8
+    target_modules: Optional[List[str]] = dataclasses.field(
+        default_factory=lambda: ["k_proj", "q_proj", "linear_k", "linear_q"]
+    )
+
+
+class LossFunction(str, Enum):
+    CrossEntropy = "ce"
+    KL_Divergence = "kl"
+
+
+@dataclasses.dataclass
+class LossConfig:
+    loss_function: LossFunction = LossFunction.KL_Divergence
+    kl_temperature: float = 2.0
+
+    @property
+    def requires_alt_fields(self):
+        return self.loss_function == LossFunction.KL_Divergence
+
+
+class BahasaConfig(transformers.PretrainedConfig):
+    r"""
+    This is the configuration class to store the configuration of a [`BahasaForConditionalGeneration`]. It is used to instantiate an
+    Bahasa model according to the specified arguments, defining the model architecture.
+
+    Configuration objects inherit from [`PretrainedConfig`] and can be used to control the model outputs. Read the
+    documentation from [`PretrainedConfig`] for more information.
+
+    Args:
+        audio_config (`Wav2Vec2Config`,  *optional*):
+            Custom audio config or dict
+        text_config (`Union[AutoConfig, dict]`, *optional*):
+            The config object of the text backbone. Can be any of `LlamaConfig` or `MistralConfig`.
+        ignore_index (`int`, *optional*, defaults to -100):
+            The ignore index for the loss function.
+        audio_token_index (`int`, *optional*, defaults to 32000):
+            The audio token index to encode the audio prompt.
+        stack_factor (`int`, *optional*, defaults to 8):
+            Audio downsampling factor for the multimodal projector.
+        norm_init (`float`, *optional*, defaults to 0.4):
+            The initialization value for the layer normalization.
+        projector_act (`str`, *optional*, defaults to `"swiglu"`):
+            The activation function used by the multimodal projector.
+        text_model_lora_config (`LoraConfigSimplified`, *optional*):
+            The LoRA configuration for finetuning the text model.
+        audio_model_lora_config (`LoraConfigSimplified`, *optional*):
+            The LoRA configuration for finetuning the audio model.
+
+
+    Example:
+
+    ```python
+    >>> from transformers import BahasaForConditionalGeneration, Wav2Vec2Config, BahasaConfig, LlamaConfig
+
+    >>> # Initializing an audio encoder config
+    >>> audio_config = Wav2Vec2Config()
+
+    >>> # Initializing a Llama config
+    >>> text_config = LlamaConfig()
+
+    >>> # Initializing a default configuration
+    >>> configuration = BahasaConfig(audio_config, text_config)
+
+    >>> # Initializing a completely untrained model from the configuration
+    >>> model = BahasaForConditionalGeneration(configuration)
+
+    >>> # Accessing the model configuration
+    >>> configuration = model.config
+
+    >>> # Initialize a model from pretrained checkpoints and random projector weights
+    >>> config = BahasaConfig(audio_model_id="facebook/wav2vec2-base-960h", text_model_id="meta-llama/Llama-2-7b-chat-hf")
+    ```"""
+
+    model_type = "bahasa"
+    is_composition = False
+
+    def __init__(
+        self,
+        audio_config: Optional[Dict[str, Any]] = None,
+        _text_config: Optional[Dict[str, Any]] = None,
+        audio_model_id: Optional[str] = None,
+        text_model_id: Optional[str] = None,
+        ignore_index: int = -100,
+        hidden_size: int = 4096,
+        stack_factor: int = 8,
+        norm_init: float = 0.4,
+        projector_act: str = "swiglu",
+        text_model_lora_config: Optional[LoraConfigSimplified] = None,
+        audio_model_lora_config: Optional[LoraConfigSimplified] = None,
+        **kwargs,
+    ):
+        self.ignore_index = ignore_index
+
+        self.audio_model_id = audio_model_id
+        self.text_model_id = text_model_id
+
+        self.hidden_size = hidden_size
+        self.stack_factor = stack_factor
+        self.norm_init = norm_init
+        self.projector_act = projector_act
+
+        if text_model_id is not None:
+            self._text_config: Union[
+                transformers.LlamaConfig, transformers.MllamaConfig
+            ] = transformers.AutoConfig.from_pretrained(text_model_id)
+        else:
+            _text_config = _text_config or {}
+            self._text_config = transformers.CONFIG_MAPPING[
+                _text_config.get("model_type", "llama")
+            ](**_text_config)
+
+        if audio_model_id is not None:
+            self.audio_config: transformers.PretrainedConfig = (
+                transformers.AutoConfig.from_pretrained(audio_model_id)
+            )
+        else:
+            audio_config = audio_config or {}
+            self.audio_config = transformers.CONFIG_MAPPING[
+                audio_config.get("model_type", "wav2vec2")
+            ](**audio_config)
+
+        self.text_model_lora_config = (
+            text_model_lora_config
+            if isinstance(text_model_lora_config, dict)
+            else dataclasses.asdict(text_model_lora_config or LoraConfigSimplified())
+        )
+        self.audio_model_lora_config = (
+            audio_model_lora_config
+            if isinstance(audio_model_lora_config, dict)
+            else dataclasses.asdict(audio_model_lora_config or LoraConfigSimplified())
+        )
+
+        self.vocab_size = self.text_config.vocab_size
+        self.initializer_range = self.text_config.initializer_range
+
+        super().__init__(**kwargs)
+
+    @property
+    def text_config(self):
+        if isinstance(self._text_config, transformers.MllamaConfig):
+            return self._text_config.text_config
+        return self._text_config
+
+    def to_diff_dict(self) -> Dict[str, Any]:
+        diff_dict = super().to_diff_dict()
+
+        # remove text_config and audio_config if text_model_id and audio_model_id are present
+        if self.text_model_id is not None:
+            diff_dict.pop("text_config", None)
+        if self.audio_model_id is not None:
+            diff_dict.pop("audio_config", None)
+
+        return diff_dict

bahasa_model.py

@@ -0,0 +1,895 @@
+import logging
+from typing import Any, Dict, List, Optional, Set, Tuple, Union
+
+import peft
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+import transformers
+import transformers.activations
+import transformers.modeling_outputs
+import transformers.models
+from transformers.models.whisper import modeling_whisper as whisper
+
+from transformers.models.mllama.modeling_mllama import MllamaForConditionalGeneration
+from transformers.models.mllama.modeling_mllama import _prepare_cross_attention_mask
+from transformers.modeling_outputs import CausalLMOutputWithPast
+
+# We must use relative import in this directory to allow uploading to HF Hub
+# Even "from . import X" pattern doesn't work (undocumented and unclear why)
+from .bahasa_config import LossConfig
+from .bahasa_config import LossFunction
+from .bahasa_config import BahasaConfig
+
+
+class BahasaModel(transformers.LlamaPreTrainedModel, transformers.GenerationMixin):
+    """
+    The Bahasa model which consists of an audio encoder and a language model.
+
+    Audio input is processed by the audio encoder, then every `stack_factor` frames are stacked together and
+    projected to the language model's embedding space using a few linear layers.
+    The text is embedded by the language model as usual and then the audio and text embeddings are merged together.
+
+    A special token `<|audio|>` is used to indicate the start of the audio embeddings in the merged embeddings.
+
+    Parameters:
+        config: Model configuration class with all the parameters of the model.
+    """
+
+    config_class = BahasaConfig
+    config: BahasaConfig  # for type hinting
+    # We minimize the weights in state_dict in order to reduce the size of the checkpoint
+    # The issue is that load_pretrained() uses state_dict() keys to know what keys are expected
+    # As such we have to tell is to ignore some keys that are not always in the model
+    _keys_to_ignore_on_load_unexpected = ["audio_tower.*", "language_model.*"]
+    # Usually we load encoder weights from a pretrained model, so we don't want to load the decoder weights
+    # Technically we never hit this issue because these keys are already removed from state_dict() however,
+    # but there's no harm in keeping it here for when we change that behavior.
+    _keys_to_ignore_on_load_missing = ["audio_tower.*"]
+
+    def __init__(self, config: BahasaConfig):
+        super().__init__(config)
+        self._register_load_state_dict_pre_hook(self._pre_load_state_dict_hook)
+
+        self.keep_params: Set[str] = set()
+        self.vocab_size = config.vocab_size
+
+        self.audio_tower = self._create_audio_tower(config)
+        self.multi_modal_projector = self._create_multi_modal_projector(config)
+        self.language_model = self._create_language_model(config)
+
+        # Determine no_split_modules dynamically to use with FSDP auto_wrap policy.
+        # FSDP throws an error if some of the layer types are not found in the model.
+        # This would be something like ["LlamaDecoderLayer", "WhisperEncoderLayer"]
+        self._no_split_modules = (self.language_model._no_split_modules or []) + (
+            self.audio_tower._no_split_modules or []
+        )
+
+        self.loss_config = LossConfig()
+        self.post_init()
+
+    def get_input_embeddings(self):
+        return self.language_model.get_input_embeddings()
+
+    def set_input_embeddings(self, value):
+        self.language_model.set_input_embeddings(value)
+
+    def get_output_embeddings(self):
+        return self.language_model.get_output_embeddings()
+
+    def set_output_embeddings(self, new_embeddings):
+        self.language_model.set_output_embeddings(new_embeddings)
+
+    def set_decoder(self, decoder):
+        self.language_model.set_decoder(decoder)
+
+    def get_decoder(self):
+        return self.language_model.get_decoder()
+
+    def tie_weights(self):
+        return self.language_model.tie_weights()
+
+    def set_loss_config(self, loss_config: LossConfig):
+        self.loss_config = loss_config
+
+    def _setup_cache(
+        self, cache_cls, max_batch_size: int, max_cache_len: Optional[int] = None
+    ):
+        self.language_model._setup_cache(cache_cls, max_batch_size, max_cache_len)
+
+    def _reorder_cache(self, past_key_values, beam_idx):
+        return self.language_model._reorder_cache(past_key_values, beam_idx)
+
+    def resize_token_embeddings(
+        self,
+        new_num_tokens: Optional[int] = None,
+        pad_to_multiple_of: Optional[int] = None,
+    ) -> nn.Embedding:
+        model_embeds = self.language_model.resize_token_embeddings(
+            new_num_tokens, pad_to_multiple_of
+        )
+        # update vocab size
+        self.config.text_config.vocab_size = model_embeds.num_embeddings
+        self.config.vocab_size = model_embeds.num_embeddings
+        self.vocab_size = model_embeds.num_embeddings
+        return model_embeds
+
+    def _compute_kl_loss(
+        self,
+        lm_output: transformers.modeling_outputs.CausalLMOutputWithPast,
+        labels: Optional[torch.Tensor] = None,
+        past_key_values: Optional[Union[Tuple, transformers.cache_utils.Cache]] = None,
+        alt_input_ids: Optional[torch.Tensor] = None,
+        alt_attention_mask: Optional[torch.Tensor] = None,
+        alt_labels: Optional[torch.Tensor] = None,
+        **kwargs,
+    ):
+        # disable gradient computation for the teacher model
+        with torch.no_grad():
+            # compute the teacher (text-only) model's distribution
+            alt_inputs_embeds = self.get_input_embeddings().forward(alt_input_ids)
+            alt_lm_output = self.language_model.forward(
+                inputs_embeds=alt_inputs_embeds,
+                labels=alt_labels,
+                attention_mask=alt_attention_mask,
+                past_key_values=past_key_values,
+                **kwargs,
+            )
+        # compute the KL divergence loss between the two models
+        kl_loss = F.kl_div(
+            F.log_softmax(
+                lm_output.logits[labels != -100] / self.loss_config.kl_temperature,
+                dim=-1,
+            ),
+            F.softmax(
+                alt_lm_output.logits[alt_labels != -100]
+                / self.loss_config.kl_temperature,
+                dim=-1,
+            ),
+            reduction="batchmean",
+        )
+        return {"loss": kl_loss}
+
+    def generate(
+        self,
+        input_ids: torch.Tensor,
+        inputs_embeds: Optional[torch.FloatTensor] = None,
+        audio_values: Optional[torch.FloatTensor] = None,
+        audio_token_start_idx: Optional[torch.Tensor] = None,
+        audio_token_len: Optional[torch.Tensor] = None,
+        **kwargs,
+    ):
+        if inputs_embeds is None:
+            # B x T  ->  B x T x D
+            inputs_embeds = self.get_input_embeddings().forward(input_ids)
+
+        if audio_values is not None:
+            inputs_embeds = self._process_audio_input(
+                inputs_embeds, audio_values, audio_token_start_idx, audio_token_len
+            )
+
+        # We need to pass input_ids, otherwise MllamaForConditionalGeneration won't know
+        # if there was any image_token in the input_ids
+        return self.language_model.generate(
+            inputs_embeds=inputs_embeds, input_ids=input_ids, **kwargs
+        )
+
+    def _process_audio_input(
+        self,
+        inputs_embeds: torch.FloatTensor,
+        audio_values: torch.FloatTensor,
+        audio_token_start_idx: Optional[torch.Tensor],
+        audio_token_len: Optional[torch.Tensor],
+    ):
+        assert (
+            audio_token_start_idx is not None and audio_token_len is not None
+        ), "audio_token_start_idx and audio_token_len must be provided if audio_values are provided."
+        assert (
+            len(audio_token_start_idx) == len(audio_token_len) == len(audio_values)
+        ), "audio_token_start_idx, audio_token_len, and audio_values must have the same batch size."
+
+        # B x A/3200 x D
+        audio_tower_output = self.audio_tower.forward(
+            audio_values.to(self.audio_tower.dtype)
+        ).last_hidden_state
+        audio_tower_output = audio_tower_output.to(inputs_embeds.dtype)
+
+        audio_embeds = self.multi_modal_projector.forward(audio_tower_output)
+
+        # combine audio and text embeddings
+        for i, (audio, start, length) in enumerate(
+            zip(audio_embeds, audio_token_start_idx, audio_token_len)
+        ):
+            length = min(length, audio.shape[0])
+            inputs_embeds[i, start : start + length] = audio[:length]
+
+        return inputs_embeds
+
+    def forward(
+        self,
+        input_ids: torch.Tensor,
+        audio_values: Optional[torch.FloatTensor] = None,
+        inputs_embeds: Optional[torch.FloatTensor] = None,
+        labels: Optional[torch.Tensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        audio_token_start_idx: Optional[torch.Tensor] = None,
+        audio_token_len: Optional[torch.Tensor] = None,
+        past_key_values: Optional[Union[Tuple, transformers.cache_utils.Cache]] = None,
+        # Vision model arguments for Mllama. These are not used in text-only Llama. Handled through kwargs.
+        # We need to include them, as the forward signature is used by the Trainer to determine the model inputs.
+        pixel_values: Optional[torch.Tensor] = None,
+        aspect_ratio_ids: Optional[torch.Tensor] = None,
+        aspect_ratio_mask: Optional[torch.Tensor] = None,
+        cross_attention_mask: Optional[torch.Tensor] = None,
+        # the alt_* fields are needed for KL divergence loss
+        alt_input_ids: Optional[torch.Tensor] = None,
+        alt_attention_mask: Optional[torch.Tensor] = None,
+        alt_labels: Optional[torch.Tensor] = None,
+        **kwargs,
+    ) -> Union[Tuple, transformers.modeling_outputs.CausalLMOutputWithPast]:
+        """
+        Forward pass for the Bahasa model.
+
+        `input_ids` are the tokenized text input. They are embedded by the language model as usual.
+        `audio_values` are processed by the audio encoder and then every `stack_factor` frames are stacked together and
+        projected to the language model's embedding space using a few linear layers.
+        The audio and text embeddings are merged together. A special token `<|audio|>` is used to indicate the start
+        of the audio embeddings in the merged embeddings.
+
+        Args:
+            input_ids: The tokenized text input.
+            audio_values: The processed audio values.
+            inputs_embeds: The embeddings for the input tokens.
+            labels: The tokenized text labels.
+            attention_mask: The attention mask for the input.
+            position_ids: The position ids for the input.
+            past_key_values: The past key value cache for the language model attention layers.
+            **kwargs: Additional keyword arguments. Passed directly to the language model.
+        """
+        if inputs_embeds is None:
+            # B x T  ->  B x T x D
+            inputs_embeds = self.get_input_embeddings().forward(input_ids)
+
+        if audio_values is not None:
+            inputs_embeds = self._process_audio_input(
+                inputs_embeds, audio_values, audio_token_start_idx, audio_token_len
+            )
+
+        for key in [
+            "pixel_values",
+            "aspect_ratio_ids",
+            "aspect_ratio_mask",
+            "cross_attention_mask",
+        ]:
+            if locals()[key] is not None:
+                kwargs[key] = locals()[key]
+
+        lm_output = self.language_model.forward(
+            inputs_embeds=inputs_embeds,
+            labels=labels,
+            attention_mask=attention_mask,
+            past_key_values=past_key_values,
+            **kwargs,
+        )
+        if self.training:
+            if self.loss_config.loss_function == LossFunction.CrossEntropy:
+                return lm_output
+            elif self.loss_config.loss_function == LossFunction.KL_Divergence:
+                return self._compute_kl_loss(
+                    lm_output=lm_output,
+                    labels=labels,
+                    past_key_values=past_key_values,
+                    alt_input_ids=alt_input_ids,
+                    alt_attention_mask=alt_attention_mask,
+                    alt_labels=alt_labels,
+                    **kwargs,
+                )
+            else:
+                raise ValueError(
+                    f"Unsupported loss function: {self.loss_config.loss_function}"
+                )
+        else:
+            return lm_output
+
+    @classmethod
+    def _create_multi_modal_projector(
+        cls, config: BahasaConfig
+    ) -> "BahasaProjector":
+        projector = BahasaProjector(config)
+        projector.to(config.torch_dtype)
+        return projector
+
+    @classmethod
+    def _create_audio_tower(
+        cls, config: BahasaConfig
+    ) -> Union[transformers.Wav2Vec2Model, "BahasaAudioEncoder"]:
+        if config.audio_model_id is not None:
+            if "whisper" in config.audio_model_id is not None:
+                audio_tower = BahasaAudioEncoder.from_pretrained(
+                    config.audio_model_id, torch_dtype=config.torch_dtype
+                )
+            else:
+                audio_tower = transformers.AutoModel.from_pretrained(
+                    config.audio_model_id, torch_dtype=config.torch_dtype
+                )
+        else:
+            if "whisper" in config.audio_config._name_or_path:
+                audio_tower = BahasaAudioEncoder(config.audio_config)
+            else:
+                with transformers.modeling_utils.no_init_weights():
+                    # we only ever use from_config if the weights are retrained, hence initializing is not
+                    # required. This makes the model quite creation faster since init on CPU is quite slow.
+                    audio_tower = transformers.AutoModel.from_config(
+                        config.audio_config
+                    )
+
+        if isinstance(
+            audio_tower,
+            (transformers.Wav2Vec2BertModel, transformers.WhisperModel),
+        ):
+            # For these models we only need the encoder part
+            # Wav2Vec2BertModel -> Wav2Vec2BertEncoder
+            # WhisperModel -> WhisperEncoder
+            audio_tower = audio_tower.encoder
+
+        audio_tower = apply_lora(audio_tower, config.audio_model_lora_config)
+        return audio_tower
+
+    @classmethod
+    def _create_language_model(
+        cls, config: BahasaConfig
+    ) -> Union[
+        transformers.LlamaForCausalLM, transformers.MllamaForConditionalGeneration
+    ]:
+        base_classes: List[
+            transformers.models.auto.auto_factory._BaseAutoModelClass
+        ] = [
+            BahasaVisionLanguageModel,
+            transformers.AutoModelForPreTraining,
+            transformers.AutoModelForCausalLM,
+        ]
+        if config.text_model_id is not None:
+            for base_cls in base_classes:
+                try:
+                    language_model = base_cls.from_pretrained(
+                        config.text_model_id,
+                        attn_implementation=config._attn_implementation,
+                        torch_dtype=config.torch_dtype,
+                    )
+                    break
+                except ValueError:
+                    pass
+        else:
+            # we only ever use from_config if the weights are retrained, hence initializing is not
+            # required. This makes the model quite creation faster since init on CPU is quite slow.
+            with transformers.modeling_utils.no_init_weights():
+                for base_cls in base_classes:
+                    try:
+                        language_model = base_cls.from_config(
+                            config._text_config,
+                            attn_implementation=config._attn_implementation,
+                            torch_dtype=config.torch_dtype,
+                        )
+                        break
+                    except ValueError:
+                        pass
+
+        language_model = apply_lora(language_model, config.text_model_lora_config)
+        return language_model
+
+    def merge_and_unload(self):
+        if isinstance(self.language_model, peft.PeftModel):
+            self.language_model = self.language_model.merge_and_unload()
+            # no need to download base language model weights anymore, so we can remove the id
+            self.config.text_model_id = None
+            self.keep_params.update(
+                set(
+                    [
+                        f"language_model.{name}"
+                        for name, _ in self.language_model.named_parameters()
+                    ]
+                )
+            )
+
+        if isinstance(self.audio_tower, peft.PeftModel):
+            self.audio_tower = self.audio_tower.merge_and_unload()
+            # no need to download base audio model weights anymore, so we can remove the id
+            self.config.audio_model_id = None
+            self.keep_params.update(
+                set(
+                    [
+                        f"audio_tower.{name}"
+                        for name, _ in self.audio_tower.named_parameters()
+                    ]
+                )
+            )
+
+        for param in ["text_model_lora_config", "audio_model_lora_config"]:
+            if hasattr(self.config, param):
+                delattr(self.config, param)
+
+    def push_to_hub(self, *args, **kwargs):
+        self.merge_and_unload()
+        self.to(self.language_model.dtype)
+        return super().push_to_hub(*args, **kwargs)
+
+    def save_pretrained(
+        self, *args, state_dict: Optional[Dict[str, Any]] = None, **kwargs
+    ):
+        if state_dict is None:
+            state_dict = super().state_dict()
+
+        named_params = dict(self.named_parameters())
+
+        state_dict = {
+            k: v
+            for k, v in state_dict.items()
+            if k in self.keep_params
+            or (k in named_params and named_params[k].requires_grad)
+        }
+
+        super().save_pretrained(*args, state_dict=state_dict, **kwargs)
+
+    def _pre_load_state_dict_hook(self, state_dict: Dict[str, Any], *args, **kwargs):
+        self.keep_params.update(set(state_dict.keys()))
+
+    def print_trainable_parameters(self):
+        """
+        Prints the number of trainable parameters in the model (reuses Peft model's method)
+        """
+        count_params = peft.peft_model.PeftModel.get_nb_trainable_parameters
+
+        trainable_params, all_param = count_params(self)
+
+        logging.info(
+            f"trainable params: {trainable_params:,d} || all params: {all_param:,d}"
+            f" || trainable%: {100 * trainable_params / all_param:.1f}%"
+        )
+
+        lm_trainable_params, lm_all_params = count_params(self.language_model)
+        audio_trainable_params, audio_all_params = count_params(self.audio_tower)
+
+        projector_trainable_params = (
+            trainable_params - lm_trainable_params - audio_trainable_params
+        )
+        projector_all_params = all_param - lm_all_params - audio_all_params
+
+        logging.info(
+            f"Trainable%:   "
+            f" LLM: {100 * lm_trainable_params / lm_all_params:.1f}%"
+            f" || Audio Encoder: {100 * audio_trainable_params / audio_all_params:.1f}%"
+            f" || Projector: {100 * projector_trainable_params / projector_all_params:.1f}%"
+        )
+
+
+def is_cache_empty(
+    past_key_values: Optional[Union[Tuple, transformers.cache_utils.Cache]]
+) -> bool:
+    """
+    Check if the cache is empty.
+    """
+    if past_key_values is None:
+        return True
+    if isinstance(past_key_values, tuple):
+        return all(len(c) == 0 for c in past_key_values)
+    return past_key_values.get_seq_length() == 0
+
+
+def apply_lora(model: torch.nn.Module, lora_config: dict) -> torch.nn.Module:
+    """
+    Applies LoRA finetuning to the model. If the `r` parameter is set to 0, the model is frozen instead.
+    """
+    lora_config = peft.LoraConfig(**lora_config or {})
+
+    if lora_config.r == 0:
+        # freeze the model entirely
+        for param in model.parameters():
+            param.requires_grad = False
+    else:
+        model = peft.get_peft_model(model, lora_config)
+
+    return model
+
+
+class StackAudioFrames(nn.Module):
+    """
+    Stack the audio embedding frames to reduce the sequence length by a factor of `stack_factor`.
+
+    The number of output frames will be `ceil(T / stack_factor) + 1` where `T` is the number of input frames.
+    NOTE: the extra +1 is intentional: in case the number of audio tokens are over-estimated by the processor,
+    we want to make sure `processor.audio_token_replacement` (i.e. EOS) doesn't get leaked into the middle of embeddings.
+    In most cases this extra padding will get removed in the model's forward function so it has no effect.
+    """
+
+    def __init__(self, stack_factor: int = 8):
+        super().__init__()
+        self.stack_factor = stack_factor
+
+    def forward(self, audio_embeds: torch.Tensor) -> torch.Tensor:
+        B, T, C = audio_embeds.shape
+        T_pad = (T + self.stack_factor - 1) // self.stack_factor * self.stack_factor
+        audio_embeds = F.pad(audio_embeds, (0, 0, 0, T_pad - T + self.stack_factor))
+        B, T, C = audio_embeds.shape
+        audio_embeds = audio_embeds.view(
+            B, T // self.stack_factor, C * self.stack_factor
+        )
+        return audio_embeds
+
+
+class RMSNorm(transformers.models.llama.modeling_llama.LlamaRMSNorm):
+    def __init__(self, hidden_size: int, init: float = 1, eps: float = 1e-6):
+        super().__init__(hidden_size=hidden_size, eps=eps)
+        self.weight.data.fill_(init)
+
+
+class SwiGLU(nn.Module):
+    def forward(self, x):
+        x, gate = x.chunk(2, dim=-1)
+        return F.silu(gate) * x
+
+
+class BahasaProjector(nn.Sequential):
+    def __init__(self, config: BahasaConfig):
+        super().__init__()
+        self.hidden_dim = config.hidden_size
+        self._pad_and_stack = StackAudioFrames(config.stack_factor)
+        dim = config.audio_config.hidden_size * config.stack_factor
+        self.ln_pre = RMSNorm(dim, init=config.norm_init)
+        self.linear_1 = nn.Linear(dim, self.hidden_dim, bias=False)
+        dim = self.hidden_dim
+        self.act = transformers.activations.get_activation(config.projector_act)
+        dim = dim // 2 if config.projector_act == "swiglu" else dim
+        self.linear_2 = nn.Linear(dim, config.text_config.hidden_size, bias=False)
+        self.ln_post = RMSNorm(config.text_config.hidden_size, init=config.norm_init)
+
+    def forward(self, audio_features: torch.Tensor) -> torch.Tensor:
+        audio_features = self._pad_and_stack(audio_features)
+        audio_features = self.ln_pre(audio_features)
+        hidden_states = self.linear_1(audio_features)
+        hidden_states = self.act(hidden_states)
+        hidden_states = self.linear_2(hidden_states)
+        hidden_states = self.ln_post(hidden_states)
+        return hidden_states
+
+
+class BahasaAudioEncoder(whisper.WhisperEncoder):
+    """
+    Encoder portion of OpenAI's Whisper model.
+
+    This implementation is a slightly modified version of HF Transformers' Whisper Encoder, with only a few fixes:
+    1. base_model_prefix updated to allow for doing `.from_pretrained` directly on the encoder
+    2. allow less than 30 second of audio padding to be passed in:
+        - relaxed ValueError check for `input_features` length to be less than or equal to `expected_seq_length` instead of strictly equal
+        - embed_pos is now sliced to match the length of `inputs_embeds`
+
+    Original: https://github.com/huggingface/transformers/blob/main/src/transformers/models/whisper/modeling_whisper.py
+    """
+
+    base_model_prefix = "model.encoder"
+    _no_split_modules = ["WhisperEncoderLayer"]
+
+    def forward(
+        self,
+        input_features,
+        attention_mask=None,
+        head_mask=None,
+        output_attentions=None,
+        output_hidden_states=None,
+        return_dict=None,
+    ):
+        expected_seq_length = (
+            self.config.max_source_positions
+            * self.conv1.stride[0]
+            * self.conv2.stride[0]
+        )
+        if input_features.shape[-1] > expected_seq_length:
+            raise ValueError(
+                f"Whisper expects the mel input features to be of length {expected_seq_length} or less, but found {input_features.shape[-1]}. Make sure to pad the input mel features to {expected_seq_length}."
+            )
+
+        output_attentions = (
+            output_attentions
+            if output_attentions is not None
+            else self.config.output_attentions
+        )
+        output_hidden_states = (
+            output_hidden_states
+            if output_hidden_states is not None
+            else self.config.output_hidden_states
+        )
+        return_dict = (
+            return_dict if return_dict is not None else self.config.use_return_dict
+        )
+        inputs_embeds = nn.functional.gelu(self.conv1(input_features))
+        inputs_embeds = nn.functional.gelu(self.conv2(inputs_embeds))
+
+        inputs_embeds = inputs_embeds.permute(0, 2, 1)
+        embed_pos = self.embed_positions.weight[: inputs_embeds.size(-2)]
+
+        hidden_states = inputs_embeds + embed_pos
+        hidden_states = nn.functional.dropout(
+            hidden_states, p=self.dropout, training=self.training
+        )
+
+        encoder_states = () if output_hidden_states else None
+        all_attentions = () if output_attentions else None
+
+        # check if head_mask has a correct number of layers specified if desired
+        if head_mask is not None:
+            assert head_mask.size()[0] == (
+                len(self.layers)
+            ), f"The head_mask should be specified for {len(self.layers)} layers, but it is for {head_mask.size()[0]}."
+
+        for idx, encoder_layer in enumerate(self.layers):
+            if output_hidden_states:
+                encoder_states = encoder_states + (hidden_states,)
+            # add LayerDrop (see https://arxiv.org/abs/1909.11556 for description)
+            to_drop = False
+            if self.training:
+                dropout_probability = torch.rand([])
+                if dropout_probability < self.layerdrop:  # skip the layer
+                    to_drop = True
+
+            if to_drop:
+                layer_outputs = (None, None)
+            else:
+                if self.gradient_checkpointing and self.training:
+                    layer_outputs = self._gradient_checkpointing_func(
+                        encoder_layer.__call__,
+                        hidden_states,
+                        None,
+                        (head_mask[idx] if head_mask is not None else None),
+                        output_attentions,
+                    )
+                else:
+                    layer_outputs = encoder_layer(
+                        hidden_states,
+                        None,
+                        layer_head_mask=(
+                            head_mask[idx] if head_mask is not None else None
+                        ),
+                        output_attentions=output_attentions,
+                    )
+
+                hidden_states = layer_outputs[0]
+
+            if output_attentions:
+                all_attentions = all_attentions + (layer_outputs[1],)
+
+        hidden_states = self.layer_norm(hidden_states)
+        if output_hidden_states:
+            encoder_states = encoder_states + (hidden_states,)
+
+        if not return_dict:
+            return tuple(
+                v
+                for v in [hidden_states, encoder_states, all_attentions]
+                if v is not None
+            )
+        return transformers.modeling_outputs.BaseModelOutput(
+            last_hidden_state=hidden_states,
+            hidden_states=encoder_states,
+            attentions=all_attentions,
+        )
+
+class BahasaVisionLanguageModel(MllamaForConditionalGeneration):
+    """
+    Custom wrapper for MllamaForConditionalGeneration that keeps the original
+    PreTrainedModel functionality but modifies the generation behavior
+    """
+    
+    def __init__(self, config):
+        super().__init__(config)
+    
+    @classmethod
+    def from_pretrained(cls, pretrained_model_name_or_path, *args, **kwargs):
+        # This will load the model using the original class's from_pretrained
+        return super().from_pretrained(pretrained_model_name_or_path, *args, **kwargs)
+    
+    @classmethod
+    def from_config(cls, config, *args, **kwargs):
+
+        return super()._from_config(config, *args, **kwargs)
+    
+    def forward(
+        self,
+        input_ids: Optional[torch.LongTensor] = None,
+        pixel_values: Optional[torch.FloatTensor] = None,
+        aspect_ratio_mask: Optional[torch.Tensor] = None,
+        aspect_ratio_ids: Optional[torch.Tensor] = None,
+        attention_mask: Optional[torch.Tensor] = None,
+        cross_attention_mask: Optional[torch.Tensor] = None,
+        cross_attention_states: Optional[torch.Tensor] = None,
+        position_ids: Optional[torch.LongTensor] = None,
+        past_key_values: Optional[List[torch.FloatTensor]] = None,
+        inputs_embeds: Optional[torch.FloatTensor] = None,
+        labels: Optional[torch.LongTensor] = None,
+        use_cache: Optional[bool] = None,
+        output_attentions: Optional[bool] = None,
+        output_hidden_states: Optional[bool] = None,
+        return_dict: Optional[bool] = None,
+        cache_position: Optional[torch.LongTensor] = None,
+        num_logits_to_keep: int = 0,
+    ) -> Union[Tuple, CausalLMOutputWithPast]:
+        r"""
+        Args:
+            labels (`torch.LongTensor` of shape `(batch_size, sequence_length)`, *optional*):
+                Labels for computing the masked language modeling loss. Indices should either be in `[0, ...,
+                config.vocab_size]` or -100 (see `input_ids` docstring). Tokens with indices set to `-100` are ignored
+                (masked), the loss is only computed for the tokens with labels in `[0, ..., config.vocab_size]`.
+
+            num_logits_to_keep (`int`, *optional*):
+                Calculate logits for the last `num_logits_to_keep` tokens. If `0`, calculate logits for all
+                `input_ids` (special case). Only last token logits are needed for generation, and calculating them only for that
+                token can save memory, which becomes pretty significant for long sequences or large vocabulary size.
+
+
+        Returns:
+
+        Example:
+
+        ```python
+        >>> from PIL import Image
+        >>> import requests
+        >>> from transformers import AutoProcessor, MllamaForConditionalGeneration
+
+        >>> checkpoint = "meta-llama/Llama-3.2-11B-Vision"
+        >>> model = MllamaForConditionalGeneration.from_pretrained(checkpoint)
+        >>> processor = AutoProcessor.from_pretrained(checkpoint)
+
+        >>> prompt = "<|image|>If I had to write a haiku for this one"
+        >>> url = "https://www.ilankelman.org/stopsigns/australia.jpg"
+        >>> image = Image.open(requests.get(url, stream=True).raw)
+
+        >>> inputs = processor(text=prompt, images=image, return_tensors="pt")
+
+        >>> # Generate
+        >>> output = model.generate(**inputs, max_new_tokens=15)
+
+        >>> prompt_len = inputs.input_ids.shape[-1]
+        >>> generated_ids = output[:, prompt_len:]
+        >>> generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)
+        >>> print(generated_text)
+        [', it would be:.\\nA stop sign in Chinatown.\\n']
+        ```
+        """
+        output_attentions = output_attentions if output_attentions is not None else self.config.output_attentions
+        output_hidden_states = (
+            output_hidden_states if output_hidden_states is not None else self.config.output_hidden_states
+        )
+        return_dict = return_dict if return_dict is not None else self.config.use_return_dict
+
+        if (input_ids is None) ^ (inputs_embeds is not None):
+            raise ValueError(
+                "You cannot specify both input_ids and inputs_embeds at the same time, and must specify either one"
+            )
+
+        if pixel_values is not None and cross_attention_states is not None:
+            raise ValueError("`pixel_values` and `cross_attention_states` cannot be provided simultaneously")
+
+        if pixel_values is not None:
+            if aspect_ratio_ids is None:
+                raise ValueError("`aspect_ratio_ids` must be provided if `pixel_values` is provided")
+            # get vision tokens from vision model
+            vision_outputs = self.vision_model(
+                pixel_values=pixel_values,
+                aspect_ratio_ids=aspect_ratio_ids,
+                aspect_ratio_mask=aspect_ratio_mask,
+                output_hidden_states=output_hidden_states,
+                output_attentions=output_attentions,
+                return_dict=return_dict,
+            )
+            cross_attention_states = vision_outputs[0]
+            cross_attention_states = self.multi_modal_projector(cross_attention_states).reshape(
+                -1, cross_attention_states.shape[-2], self.hidden_size
+            )
+
+        if cross_attention_mask is not None:
+            cross_attention_mask, full_text_row_masked_out_mask = _prepare_cross_attention_mask(
+                cross_attention_mask,
+                num_vision_tokens=self.vision_model.num_patches,
+                dtype=self.dtype,
+            )
+        else:
+            full_text_row_masked_out_mask = None
+
+        if cross_attention_mask is not None and cache_position is not None:
+            cross_attention_mask = cross_attention_mask[:, :, cache_position]
+            full_text_row_masked_out_mask = full_text_row_masked_out_mask[:, :, cache_position]
+
+        outputs = self.language_model(
+            input_ids=input_ids,
+            attention_mask=attention_mask,
+            position_ids=position_ids,
+            cross_attention_states=cross_attention_states,
+            cross_attention_mask=cross_attention_mask,
+            full_text_row_masked_out_mask=full_text_row_masked_out_mask,
+            past_key_values=past_key_values,
+            use_cache=use_cache,
+            inputs_embeds=inputs_embeds,
+            labels=labels,
+            output_hidden_states=output_hidden_states,
+            output_attentions=output_attentions,
+            return_dict=return_dict,
+            cache_position=cache_position,
+            num_logits_to_keep=num_logits_to_keep,
+        )
+
+        return outputs
+
+    def prepare_inputs_for_generation(
+        self,
+        input_ids=None,
+        inputs_embeds=None,
+        attention_mask=None,
+        position_ids=None,
+        pixel_values=None,
+        aspect_ratio_ids=None,
+        aspect_ratio_mask=None,
+        cross_attention_mask=None,
+        past_key_values=None,
+        use_cache=False,
+        cache_position=None,
+        num_logits_to_keep=None,
+        **kwargs,
+    ):
+        # If we have cache: let's slice `input_ids` through `cache_position`, to keep only the unprocessed tokens
+        # Exception 1: when passing input_embeds, input_ids may be missing entries
+        # Exception 2: some generation methods do special slicing of input_ids, so we don't need to do it here
+        if past_key_values is not None:
+            if inputs_embeds is not None:  # Exception 1
+                input_ids = input_ids[:, -cache_position.shape[0] :]
+            elif input_ids.shape[1] != cache_position.shape[0]:  # Default case (the "else", a no op, is Exception 2)
+                input_ids = input_ids[:, cache_position]
+
+        # TODO: we have no attention_mask so this won't work, check if we really won't need attention mask and find another way
+        if attention_mask is not None and position_ids is None:
+            # create position_ids on the fly for batch generation
+            position_ids = attention_mask.long().cumsum(-1) - 1
+            position_ids.masked_fill_(attention_mask == 0, 1)
+            if past_key_values:
+                position_ids = position_ids[:, -input_ids.shape[1] :]
+
+                # This `clone` call is needed to avoid recapturing cuda graphs with `torch.compile`'s  `mode="reduce-overhead`, as otherwise the input `position_ids` would have various stride during the decoding. Here, simply using `.contiguous()` is not sufficient as in the batch size = 1 case, `position_ids` is already contiguous but with varying stride which retriggers a capture.
+                position_ids = position_ids.clone(memory_format=torch.contiguous_format)
+
+        # if `inputs_embeds` are passed, we only want to use them in the 1st generation step
+        if inputs_embeds is not None and (cache_position[0] == 0 or input_ids.shape[1] > 1): ## CHANGES MULTITURN
+            if input_ids.shape[1] > 1:  ## CHANGES MULTITURN
+                inputs_embeds = inputs_embeds[:, cache_position, :] ## CHANGES MULTITURN
+            model_inputs = {"inputs_embeds": inputs_embeds, "input_ids": None}
+        else:
+            # The clone here is for the same reason as for `position_ids`.
+            model_inputs = {"input_ids": input_ids.clone(memory_format=torch.contiguous_format), "inputs_embeds": None}
+
+        if num_logits_to_keep is not None:
+            model_inputs["num_logits_to_keep"] = num_logits_to_keep
+
+        model_inputs.update(
+            {
+                "position_ids": position_ids,
+                "cache_position": cache_position,
+                "past_key_values": past_key_values,
+                "use_cache": use_cache,
+                "attention_mask": attention_mask,
+                "cross_attention_mask": cross_attention_mask,
+            }
+        )
+
+        # If we're in pre-fill or cacheless decoding step, then we need pixel_values and aspect ratios
+        # to compute image hidden states, otherwise they are cached within each cross attn layer
+        if (input_ids == self.config.image_token_index).any():
+            model_inputs["pixel_values"] = pixel_values
+            model_inputs["aspect_ratio_ids"] = aspect_ratio_ids
+            model_inputs["aspect_ratio_mask"] = aspect_ratio_mask
+
+        return model_inputs
+
+
+BahasaConfig.register_for_auto_class()
+BahasaModel.register_for_auto_class()
+
+transformers.AutoConfig.register("bahasa", BahasaConfig)
+transformers.AutoModel.register(BahasaConfig, BahasaModel)
+
+transformers.activations.ACT2FN["swiglu"] = SwiGLU

bahasa_processing.py

@@ -0,0 +1,229 @@
+from typing import Optional, Union
+
+import numpy as np
+import torch
+import transformers
+
+from .bahasa_config import BahasaConfig
+
+
+class BahasaProcessor(transformers.ProcessorMixin):
+    """
+    Constructs an Bahasa processor which wraps an audio processor and a text_processor into a single processor.
+
+    Args:
+        audio_processor: The audio processor for the audio encoder.
+        text_processor: The processor for the language model.
+    """
+
+    attributes = ["audio_processor", "text_processor"]
+    audio_processor_class = (
+        "Wav2Vec2Processor",
+        "SeamlessM4TFeatureExtractor",
+        "WhisperProcessor",
+    )
+    text_processor_class = (
+        "PreTrainedTokenizer",
+        "PreTrainedTokenizerFast",
+        "MllamaProcessor",
+    )
+
+    tokenizer: transformers.PreTrainedTokenizerBase
+    text_processor: Union[
+        transformers.ProcessorMixin, transformers.PreTrainedTokenizerBase
+    ]
+    audio_processor: transformers.ProcessorMixin
+
+    def __init__(
+        self,
+        audio_processor=None,
+        text_processor=None,
+        audio_padding: str = "longest",
+        encoder_ds_factor: int = 320,
+        stack_factor: int = 8,
+        audio_placeholder: str = "<|audio|>",
+    ):
+        """
+        Args:
+            audio_processor: The audio processor for the audio encoder.
+            text_processor: The processor for the language model.
+            audio_padding: The padding strategy for the audio encoder.
+            encoder_ds_factor: The downsample factor of the audio encoder.
+            stack_factor: The factor by which the audio encoder output is stacked in the multimodal projector.
+            audio_placeholder: The placeholder for the audio in the text.
+        """
+        self.audio_padding = audio_padding
+        self.encoder_ds_factor = encoder_ds_factor
+        self.stack_factor = stack_factor
+        self.audio_placeholder = audio_placeholder
+
+        if isinstance(text_processor, transformers.MllamaProcessor):
+            self.tokenizer: transformers.PreTrainedTokenizerFast = (
+                text_processor.tokenizer
+            )
+        else:
+            self.tokenizer = text_processor
+
+        super().__init__(audio_processor=audio_processor, text_processor=text_processor)
+
+        self.audio_token_replacement = self.tokenizer.bos_token
+        assert (
+            self.audio_token_replacement is not None
+        ), "The tokenizer has no EOS token. Cannot recover."
+        # if tokenizer.pad_token_id is None:
+        #     tokenizer.pad_token_id = tokenizer.eos_token_id
+
+    @classmethod
+    def from_pretrained(cls, pretrained_model_name_or_path, **kwargs):
+        config: BahasaConfig = transformers.AutoConfig.from_pretrained(
+            pretrained_model_name_or_path, **kwargs
+        )
+        audio_processor = transformers.AutoProcessor.from_pretrained(
+            config.audio_model_id
+            or config.audio_config._name_or_path
+            or "facebook/wav2vec2-base-960h"
+        )
+
+        text_processor = transformers.AutoProcessor.from_pretrained(
+            config._text_config.name_or_path, **kwargs
+        )
+        text_processor.tokenizer.padding_side = "left"
+        text_processor.tokenizer.pad_token = text_processor.tokenizer.eos_token
+        new_template = """{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- if strftime_now is defined %}\n        {%- set date_string = strftime_now(\"%d %b %Y\") %}\n    {%- else %}\n        {%- set date_string = \"26 Jul 2024\" %}\n    {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- Find out if there are any images #}\n{% set image_ns = namespace(has_images=false) %}      \n{%- for message in messages %}\n    {%- if message['content'] is iterable and not message['content'] is string %}\n        {%- for content in message['content'] %}\n            {%- if content['type'] == 'image' %}\n                {%- set image_ns.has_images = true %}\n            {%- endif %}\n        {%- endfor %}\n    {%- endif %}\n{%- endfor %}\n\n{#- Always include system message, regardless of images #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n    {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n    {%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n    {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n' }}\n        {%- if message['content'] is string %}\n            {{- message['content'] }}\n        {%- else %}\n            {%- for content in message['content'] %}\n                {%- if content['type'] == 'image' %}\n                    {{- '<|image|>' }}\n                {%- elif content['type'] == 'text' %}\n                    {{- content['text'] }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n        {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n        {{- '\"parameters\": ' }}\n        {{- tool_call.arguments | tojson }}\n        {{- \"}\" }}\n        {{- \"<|eot_id|>\" }}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n"""
+        text_processor.tokenizer.chat_template = new_template
+
+        return cls(
+            audio_processor=audio_processor,
+            text_processor=text_processor,
+            stack_factor=config.stack_factor,
+        )
+
+    def __call__(
+        self,
+        text: Optional[str] = None,
+        audio: Optional[Union[np.ndarray, torch.Tensor]] = None,
+        images: Optional[transformers.image_utils.ImageInput] = None,
+        sampling_rate: Optional[int] = None,
+        return_tensors: Optional[
+            Union[str, transformers.TensorType]
+        ] = transformers.TensorType.PYTORCH,
+        **kwargs,
+    ) -> transformers.BatchFeature:
+        """
+        Main method to prepare for the model one text sequence and audio. This method forwards the `text`
+        and `kwargs` arguments to PreTrainedTokenizerFast's [`~PreTrainedTokenizerFast.__call__`] if `text` is not `None` to encode
+        the text. To prepare the audio(s), this method forwards the `audio`, `sampling_rate` and `kwargs` arguments to
+        audio processor's [`~Wav2Vec2Processor.__call__`] if `audio` is not `None`. Please refer to the docstring
+        of the above two methods for more information.
+
+        Args:
+            text (`str`, `List[str]`):
+                The sequence to be encoded. Sequence can be a string or (pretokenized string).
+            audio (`np.ndarray`, `torch.Tensor`, `List[np.ndarray]`, `List[torch.Tensor]`):
+                The audio to be prepared. Audio can be NumPy array or PyTorch tensor. In case of a
+                NumPy array/PyTorch tensor, each audio should be of shape (C, T), where C is a number of channels, and T the
+                sample length of the audio.
+            sampling_rate (`int`, *optional*, defaults to 16000):
+                Sampling rate of the input audio. We expect 16kHz audio. Don't change this value unless you know what
+                you are doing.
+            return_tensors (`str` or [`~utils.TensorType`], *optional*):
+                If set, will return tensors of a particular framework. Acceptable values are:
+
+                - `'tf'`: Return TensorFlow `tf.constant` objects.
+                - `'pt'`: Return PyTorch `torch.Tensor` objects.
+                - `'np'`: Return NumPy `np.ndarray` objects.
+                - `'jax'`: Return JAX `jnp.ndarray` objects.
+
+        Returns:
+            [`BatchFeature`]: A [`BatchFeature`] with the following fields:
+
+            - **input_ids** -- List of token ids to be fed to a model. Returned when `text` is not `None`.
+            - **attention_mask** -- List of indices specifying which tokens should be attended to by the model (when
+              `return_attention_mask=True` or if *"attention_mask"* is in `self.model_input_names` and if `text` is not
+              `None`).
+            - **audio_values** -- Processed audio values to be fed to a model. Returned when `audio` is not `None`.
+            - **audio_token_len** -- Predicted number of audio frames: this value is guaranteed to be a close upper bound.
+              Returned when `audio` is not `None`.
+            - **audio_token_start_idx** -- The index in the tokenized text where the audio starts. Returned when `audio` is not `None`.
+        """
+        # TODO: Add support for multiple audio and text inputs.
+        data = {}
+        audio_embed_frames = 0
+        if audio is not None and len(audio) > 0:
+            if self.audio_padding == "max_length":
+                # 30 seconds is the expected length for Whisper
+                assert sampling_rate is not None, "Sampling rate must be provided."
+                audio_len = 30 * sampling_rate
+            else:
+                audio_len = audio.shape[-1]
+            # It's guaranteed that the number of frames is less than or equal to this amount.
+            # For Whisper this is exact AFAICT, but for Wav2Vec2 it's an upper bound.
+            # Currently, StackAudioFrames makes sure an over-estimation won't cause issues by padding the audio embeddings.
+            nb_encoder_frames = int(round(audio_len / self.encoder_ds_factor + 1e-4))
+            audio_embed_frames = int(np.ceil(nb_encoder_frames / self.stack_factor))
+            data["audio_token_len"] = [audio_embed_frames]
+
+            # Main audio processing. The processor is model-specific.
+            x = self.audio_processor(
+                audio,
+                sampling_rate=sampling_rate,
+                padding="longest",
+                max_length=audio_len,
+                **kwargs,
+            )
+            if "input_features" in x:
+                data["audio_values"] = x.input_features
+            else:
+                data["audio_values"] = x.input_values
+
+        if text is not None:
+            assert isinstance(
+                text, str
+            ), "Text must be a string. Batch mode not supported yet."
+            if self.audio_placeholder in text:
+                if "audio_token_len" not in data:
+                    raise ValueError(
+                        f"audio must be provided when using audio placeholder ({self.audio_placeholder}) in text."
+                    )
+
+                start_idx = len(
+                    self.tokenizer.encode(
+                        text[: text.index(self.audio_placeholder)],
+                        add_special_tokens=False,
+                    )
+                )
+                data["audio_token_start_idx"] = [start_idx]
+
+                # Replace the audio placeholder with the audio token.
+                #   e.g. "Transcribe\n<|audio|>" -> "Transcribe </s></s></s></s></s></s></s></s>"
+                #        where the number of </s> is the number of audio frames.
+                text = text.replace(
+                    self.audio_placeholder,
+                    self.audio_token_replacement * audio_embed_frames,
+                )
+
+            # Special tokens like BOS should already have been added by the caller.
+            data.update(
+                self.text_processor(
+                    text=[text], images=images, add_special_tokens=False, **kwargs
+                )
+            )
+
+        return transformers.BatchFeature(data=data, tensor_type=return_tensors)
+
+    def batch_decode(self, *args, **kwargs):
+        return self.tokenizer.batch_decode(*args, **kwargs)
+
+    def decode(self, *args, **kwargs):
+        return self.tokenizer.decode(*args, **kwargs)
+
+    @property
+    def model_input_names(self):
+        text_processor_input_names = self.text_processor.model_input_names
+        audio_processor_input_names = self.audio_processor.model_input_names
+        return list(set(text_processor_input_names + audio_processor_input_names))
+
+
+BahasaProcessor.register_for_auto_class()
+
+transformers.AutoProcessor.register(BahasaConfig, BahasaProcessor)

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- if strftime_now is defined %}\n        {%- set date_string = strftime_now(\"%d %b %Y\") %}\n    {%- else %}\n        {%- set date_string = \"26 Jul 2024\" %}\n    {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- Find out if there are any images #}\n{% set image_ns = namespace(has_images=false) %}      \n{%- for message in messages %}\n    {%- if message['content'] is iterable and not message['content'] is string %}\n        {%- for content in message['content'] %}\n            {%- if content['type'] == 'image' %}\n                {%- set image_ns.has_images = true %}\n            {%- endif %}\n        {%- endfor %}\n    {%- endif %}\n{%- endfor %}\n\n{#- Always include system message, regardless of images #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n    {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n    {%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n    {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n' }}\n        {%- if message['content'] is string %}\n            {{- message['content'] }}\n        {%- else %}\n            {%- for content in message['content'] %}\n                {%- if content['type'] == 'image' %}\n                    {{- '<|image|>' }}\n                {%- elif content['type'] == 'text' %}\n                    {{- content['text'] }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n        {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n        {{- '\"parameters\": ' }}\n        {{- tool_call.arguments | tojson }}\n        {{- \"}\" }}\n        {{- \"<|eot_id|>\" }}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n"
+}

config.json

@@ -0,0 +1,308 @@
+{
+  "_text_config": {
+    "_name_or_path": "meta-llama/Llama-3.2-11B-Vision-Instruct",
+    "architectures": [
+      "MllamaForConditionalGeneration"
+    ],
+    "bos_token_id": null,
+    "eos_token_id": null,
+    "image_token_index": 128256,
+    "model_type": "mllama",
+    "text_config": {
+      "_name_or_path": "",
+      "add_cross_attention": false,
+      "architectures": null,
+      "bad_words_ids": null,
+      "begin_suppress_tokens": null,
+      "bos_token_id": 128000,
+      "chunk_size_feed_forward": 0,
+      "cross_attention_hidden_size": null,
+      "cross_attention_layers": [
+        3,
+        8,
+        13,
+        18,
+        23,
+        28,
+        33,
+        38
+      ],
+      "decoder_start_token_id": null,
+      "diversity_penalty": 0.0,
+      "do_sample": false,
+      "dropout": 0,
+      "early_stopping": false,
+      "encoder_no_repeat_ngram_size": 0,
+      "eos_token_id": [
+        128001,
+        128008,
+        128009
+      ],
+      "exponential_decay_length_penalty": null,
+      "finetuning_task": null,
+      "forced_bos_token_id": null,
+      "forced_eos_token_id": null,
+      "hidden_act": "silu",
+      "hidden_size": 4096,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "initializer_range": 0.02,
+      "intermediate_size": 14336,
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "length_penalty": 1.0,
+      "max_length": 20,
+      "max_position_embeddings": 131072,
+      "min_length": 0,
+      "model_type": "mllama_text_model",
+      "no_repeat_ngram_size": 0,
+      "num_attention_heads": 32,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_hidden_layers": 40,
+      "num_key_value_heads": 8,
+      "num_return_sequences": 1,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "output_scores": false,
+      "pad_token_id": 128004,
+      "prefix": null,
+      "problem_type": null,
+      "pruned_heads": {},
+      "remove_invalid_values": false,
+      "repetition_penalty": 1.0,
+      "return_dict": true,
+      "return_dict_in_generate": false,
+      "rms_norm_eps": 1e-05,
+      "rope_scaling": {
+        "factor": 8.0,
+        "high_freq_factor": 4.0,
+        "low_freq_factor": 1.0,
+        "original_max_position_embeddings": 8192,
+        "rope_type": "llama3"
+      },
+      "rope_theta": 500000.0,
+      "sep_token_id": null,
+      "suppress_tokens": null,
+      "task_specific_params": null,
+      "temperature": 1.0,
+      "tf_legacy_loss": false,
+      "tie_encoder_decoder": false,
+      "tie_word_embeddings": false,
+      "tokenizer_class": null,
+      "top_k": 50,
+      "top_p": 1.0,
+      "torch_dtype": "bfloat16",
+      "torchscript": false,
+      "typical_p": 1.0,
+      "use_bfloat16": false,
+      "use_cache": true,
+      "vocab_size": 128256
+    },
+    "tie_word_embeddings": true,
+    "torch_dtype": "bfloat16",
+    "vision_config": {
+      "_name_or_path": "",
+      "add_cross_attention": false,
+      "architectures": null,
+      "attention_heads": 16,
+      "bad_words_ids": null,
+      "begin_suppress_tokens": null,
+      "bos_token_id": null,
+      "chunk_size_feed_forward": 0,
+      "cross_attention_hidden_size": null,
+      "decoder_start_token_id": null,
+      "diversity_penalty": 0.0,
+      "do_sample": false,
+      "early_stopping": false,
+      "encoder_no_repeat_ngram_size": 0,
+      "eos_token_id": null,
+      "exponential_decay_length_penalty": null,
+      "finetuning_task": null,
+      "forced_bos_token_id": null,
+      "forced_eos_token_id": null,
+      "hidden_act": "gelu",
+      "hidden_size": 1280,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "image_size": 560,
+      "initializer_range": 0.02,
+      "intermediate_layers_indices": [
+        3,
+        7,
+        15,
+        23,
+        30
+      ],
+      "intermediate_size": 5120,
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "length_penalty": 1.0,
+      "max_length": 20,
+      "max_num_tiles": 4,
+      "min_length": 0,
+      "model_type": "mllama_vision_model",
+      "no_repeat_ngram_size": 0,
+      "norm_eps": 1e-05,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_channels": 3,
+      "num_global_layers": 8,
+      "num_hidden_layers": 32,
+      "num_return_sequences": 1,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "output_scores": false,
+      "pad_token_id": null,
+      "patch_size": 14,
+      "prefix": null,
+      "problem_type": null,
+      "pruned_heads": {},
+      "remove_invalid_values": false,
+      "repetition_penalty": 1.0,
+      "return_dict": true,
+      "return_dict_in_generate": false,
+      "sep_token_id": null,
+      "supported_aspect_ratios": [
+        [
+          1,
+          1
+        ],
+        [
+          1,
+          2
+        ],
+        [
+          1,
+          3
+        ],
+        [
+          1,
+          4
+        ],
+        [
+          2,
+          1
+        ],
+        [
+          2,
+          2
+        ],
+        [
+          3,
+          1
+        ],
+        [
+          4,
+          1
+        ]
+      ],
+      "suppress_tokens": null,
+      "task_specific_params": null,
+      "temperature": 1.0,
+      "tf_legacy_loss": false,
+      "tie_encoder_decoder": false,
+      "tie_word_embeddings": true,
+      "tokenizer_class": null,
+      "top_k": 50,
+      "top_p": 1.0,
+      "torch_dtype": "bfloat16",
+      "torchscript": false,
+      "typical_p": 1.0,
+      "use_bfloat16": false,
+      "vision_output_dim": 7680
+    }
+  },
+  "architectures": [
+    "BahasaModel"
+  ],
+  "audio_config": {
+    "_name_or_path": "openai/whisper-large-v3",
+    "activation_dropout": 0.0,
+    "activation_function": "gelu",
+    "apply_spec_augment": false,
+    "architectures": [
+      "WhisperForConditionalGeneration"
+    ],
+    "attention_dropout": 0.0,
+    "begin_suppress_tokens": [
+      220,
+      50257
+    ],
+    "bos_token_id": 50257,
+    "d_model": 1280,
+    "decoder_attention_heads": 20,
+    "decoder_ffn_dim": 5120,
+    "decoder_layerdrop": 0.0,
+    "decoder_layers": 32,
+    "decoder_start_token_id": 50258,
+    "dropout": 0.0,
+    "encoder_attention_heads": 20,
+    "encoder_ffn_dim": 5120,
+    "encoder_layerdrop": 0.0,
+    "encoder_layers": 32,
+    "eos_token_id": 50257,
+    "init_std": 0.02,
+    "is_encoder_decoder": true,
+    "max_length": 448,
+    "max_source_positions": 1500,
+    "max_target_positions": 448,
+    "median_filter_width": 7,
+    "model_type": "whisper",
+    "num_hidden_layers": 32,
+    "num_mel_bins": 128,
+    "pad_token_id": 50256,
+    "scale_embedding": false,
+    "torch_dtype": "float16",
+    "use_cache": true,
+    "vocab_size": 51866
+  },
+  "audio_model_id": null,
+  "audio_model_lora_config": {
+    "lora_alpha": 8,
+    "r": 0,
+    "target_modules": [
+      "k_proj",
+      "q_proj",
+      "linear_k",
+      "linear_q"
+    ]
+  },
+  "auto_map": {
+    "AutoConfig": "bahasa_config.BahasaConfig",
+    "AutoModel": "bahasa_model.BahasaModel"
+  },
+  "hidden_size": 4096,
+  "ignore_index": -100,
+  "initializer_range": 0.02,
+  "model_type": "bahasa",
+  "norm_init": 0.4,
+  "projector_act": "swiglu",
+  "stack_factor": 8,
+  "text_model_id": null,
+  "text_model_lora_config": {
+    "lora_alpha": 8,
+    "r": 0,
+    "target_modules": [
+      "k_proj",
+      "q_proj",
+      "linear_k",
+      "linear_q"
+    ]
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "pad_token_id": 128004,
+  "transformers_version": "4.45.2"
+}

model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9652af262d00e2101b2be52fe89d4641c2805e20e18c8b1efb84924511522af1
+size 5364271116

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:836a642ccb3840334acb7b3e8247bde411964f48fb4a2dd009c8eda312d4f442
+size 5323300432

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7241708514b032894ca2ed8073c06ebf3814a716befa0d2bd9e9f712ff1b930
+size 5234715576

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66d709f377160483bfd53b866a87b0015c45e879ca8580a6421df175ba1a8e17
+size 5234681000

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a341a4e1726af7e122bfaa69ee622be9807a483b7172490df95b8ab3306c2bda
+size 5234697536

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d2d63b94e8bab371b3bb5db1c7b1405f8658a79cdc8ab0085990dc3791b1883
+size 5234697536

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87b74c979a45539453dad9fe213ba7256b6a2eae648a8d3d5ed568316b54a60f
+size 5234697536

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6257c9af81c5acf3a745570fe6185b4b589dea5c2cc4f8ef5ac07515a2229f8e
+size 5234715640

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62407a61992625b087c142b173a4e1019f3872c1ed63dbcae24aee5d04c39c13
+size 3334555784

normalizer.json

@@ -0,0 +1,1742 @@
+{
+  "accessorise": "accessorize",
+  "accessorised": "accessorized",
+  "accessorises": "accessorizes",
+  "accessorising": "accessorizing",
+  "acclimatisation": "acclimatization",
+  "acclimatise": "acclimatize",
+  "acclimatised": "acclimatized",
+  "acclimatises": "acclimatizes",
+  "acclimatising": "acclimatizing",
+  "accoutrements": "accouterments",
+  "aeon": "eon",
+  "aeons": "eons",
+  "aerogramme": "aerogram",
+  "aerogrammes": "aerograms",
+  "aeroplane": "airplane",
+  "aeroplanes": "airplanes",
+  "aesthete": "esthete",
+  "aesthetes": "esthetes",
+  "aesthetic": "esthetic",
+  "aesthetically": "esthetically",
+  "aesthetics": "esthetics",
+  "aetiology": "etiology",
+  "ageing": "aging",
+  "aggrandisement": "aggrandizement",
+  "agonise": "agonize",
+  "agonised": "agonized",
+  "agonises": "agonizes",
+  "agonising": "agonizing",
+  "agonisingly": "agonizingly",
+  "almanack": "almanac",
+  "almanacks": "almanacs",
+  "aluminium": "aluminum",
+  "amortisable": "amortizable",
+  "amortisation": "amortization",
+  "amortisations": "amortizations",
+  "amortise": "amortize",
+  "amortised": "amortized",
+  "amortises": "amortizes",
+  "amortising": "amortizing",
+  "amphitheatre": "amphitheater",
+  "amphitheatres": "amphitheaters",
+  "anaemia": "anemia",
+  "anaemic": "anemic",
+  "anaesthesia": "anesthesia",
+  "anaesthetic": "anesthetic",
+  "anaesthetics": "anesthetics",
+  "anaesthetise": "anesthetize",
+  "anaesthetised": "anesthetized",
+  "anaesthetises": "anesthetizes",
+  "anaesthetising": "anesthetizing",
+  "anaesthetist": "anesthetist",
+  "anaesthetists": "anesthetists",
+  "anaesthetize": "anesthetize",
+  "anaesthetized": "anesthetized",
+  "anaesthetizes": "anesthetizes",
+  "anaesthetizing": "anesthetizing",
+  "analogue": "analog",
+  "analogues": "analogs",
+  "analyse": "analyze",
+  "analysed": "analyzed",
+  "analyses": "analyzes",
+  "analysing": "analyzing",
+  "anglicise": "anglicize",
+  "anglicised": "anglicized",
+  "anglicises": "anglicizes",
+  "anglicising": "anglicizing",
+  "annualised": "annualized",
+  "antagonise": "antagonize",
+  "antagonised": "antagonized",
+  "antagonises": "antagonizes",
+  "antagonising": "antagonizing",
+  "apologise": "apologize",
+  "apologised": "apologized",
+  "apologises": "apologizes",
+  "apologising": "apologizing",
+  "appal": "appall",
+  "appals": "appalls",
+  "appetiser": "appetizer",
+  "appetisers": "appetizers",
+  "appetising": "appetizing",
+  "appetisingly": "appetizingly",
+  "arbour": "arbor",
+  "arbours": "arbors",
+  "archaeologically": "archeologically",
+  "archaeologist": "archeologist",
+  "archaeologists": "archeologists",
+  "archaeology": "archeology</span>",
+  "archeological": "archaeological",
+  "ardour": "ardor",
+  "armour": "armor",
+  "armoured": "armored",
+  "armourer": "armorer",
+  "armourers": "armorers",
+  "armouries": "armories",
+  "armoury": "armory",
+  "artefact": "artifact",
+  "artefacts": "artifacts",
+  "authorise": "authorize",
+  "authorised": "authorized",
+  "authorises": "authorizes",
+  "authorising": "authorizing",
+  "axe": "ax",
+  "backpedalled": "backpedaled",
+  "backpedalling": "backpedaling",
+  "bannister": "banister",
+  "bannisters": "banisters",
+  "baptise": "baptize",
+  "baptised": "baptized",
+  "baptises": "baptizes",
+  "baptising": "baptizing",
+  "bastardise": "bastardize",
+  "bastardised": "bastardized",
+  "bastardises": "bastardizes",
+  "bastardising": "bastardizing",
+  "battleax": "battleaxe",
+  "baulk": "balk",
+  "baulked": "balked",
+  "baulking": "balking",
+  "baulks": "balks",
+  "bedevilled": "bedeviled",
+  "bedevilling": "bedeviling",
+  "behaviour": "behavior",
+  "behavioural": "behavioral",
+  "behaviourism": "behaviorism",
+  "behaviourist": "behaviorist",
+  "behaviourists": "behaviorists",
+  "behaviours": "behaviors",
+  "behove": "behoove",
+  "behoved": "behooved",
+  "behoves": "behooves",
+  "bejewelled": "bejeweled",
+  "belabour": "belabor",
+  "belaboured": "belabored",
+  "belabouring": "belaboring",
+  "belabours": "belabors",
+  "bevelled": "beveled",
+  "bevvies": "bevies",
+  "bevvy": "bevy",
+  "biassed": "biased",
+  "biassing": "biasing",
+  "bingeing": "binging",
+  "bougainvillaea": "bougainvillea",
+  "bougainvillaeas": "bougainvilleas",
+  "bowdlerise": "bowdlerize",
+  "bowdlerised": "bowdlerized",
+  "bowdlerises": "bowdlerizes",
+  "bowdlerising": "bowdlerizing",
+  "breathalyse": "breathalyze",
+  "breathalysed": "breathalyzed",
+  "breathalyser": "breathalyzer",
+  "breathalysers": "breathalyzers",
+  "breathalyses": "breathalyzes",
+  "breathalysing": "breathalyzing",
+  "brutalise": "brutalize",
+  "brutalised": "brutalized",
+  "brutalises": "brutalizes",
+  "brutalising": "brutalizing",
+  "busses": "buses",
+  "bussing": "busing",
+  "caesarean": "cesarean",
+  "caesareans": "cesareans",
+  "calibre": "caliber",
+  "calibres": "calibers",
+  "calliper": "caliper",
+  "callipers": "calipers",
+  "callisthenics": "calisthenics",
+  "canalise": "canalize",
+  "canalised": "canalized",
+  "canalises": "canalizes",
+  "canalising": "canalizing",
+  "cancelation": "cancellation",
+  "cancelations": "cancellations",
+  "cancelled": "canceled",
+  "cancelling": "canceling",
+  "candour": "candor",
+  "cannibalise": "cannibalize",
+  "cannibalised": "cannibalized",
+  "cannibalises": "cannibalizes",
+  "cannibalising": "cannibalizing",
+  "canonise": "canonize",
+  "canonised": "canonized",
+  "canonises": "canonizes",
+  "canonising": "canonizing",
+  "capitalise": "capitalize",
+  "capitalised": "capitalized",
+  "capitalises": "capitalizes",
+  "capitalising": "capitalizing",
+  "caramelise": "caramelize",
+  "caramelised": "caramelized",
+  "caramelises": "caramelizes",
+  "caramelising": "caramelizing",
+  "carbonise": "carbonize",
+  "carbonised": "carbonized",
+  "carbonises": "carbonizes",
+  "carbonising": "carbonizing",
+  "carolled": "caroled",
+  "carolling": "caroling",
+  "catalogue": "catalog",
+  "catalogued": "cataloged",
+  "catalogues": "catalogs",
+  "cataloguing": "cataloging",
+  "catalyse": "catalyze",
+  "catalysed": "catalyzed",
+  "catalyses": "catalyzes",
+  "catalysing": "catalyzing",
+  "categorise": "categorize",
+  "categorised": "categorized",
+  "categorises": "categorizes",
+  "categorising": "categorizing",
+  "cauterise": "cauterize",
+  "cauterised": "cauterized",
+  "cauterises": "cauterizes",
+  "cauterising": "cauterizing",
+  "cavilled": "caviled",
+  "cavilling": "caviling",
+  "centigramme": "centigram",
+  "centigrammes": "centigrams",
+  "centilitre": "centiliter",
+  "centilitres": "centiliters",
+  "centimetre": "centimeter",
+  "centimetres": "centimeters",
+  "centralise": "centralize",
+  "centralised": "centralized",
+  "centralises": "centralizes",
+  "centralising": "centralizing",
+  "centre": "center",
+  "centred": "centered",
+  "centrefold": "centerfold",
+  "centrefolds": "centerfolds",
+  "centrepiece": "centerpiece",
+  "centrepieces": "centerpieces",
+  "centres": "centers",
+  "channelled": "channeled",
+  "channelling": "channeling",
+  "characterise": "characterize",
+  "characterised": "characterized",
+  "characterises": "characterizes",
+  "characterising": "characterizing",
+  "cheque": "check",
+  "chequebook": "checkbook",
+  "chequebooks": "checkbooks",
+  "chequered": "checkered",
+  "cheques": "checks",
+  "chilli": "chili",
+  "chimaera": "chimera",
+  "chimaeras": "chimeras",
+  "chiselled": "chiseled",
+  "chiselling": "chiseling",
+  "circularise": "circularize",
+  "circularised": "circularized",
+  "circularises": "circularizes",
+  "circularising": "circularizing",
+  "civilise": "civilize",
+  "civilised": "civilized",
+  "civilises": "civilizes",
+  "civilising": "civilizing",
+  "clamour": "clamor",
+  "clamoured": "clamored",
+  "clamouring": "clamoring",
+  "clamours": "clamors",
+  "clangour": "clangor",
+  "clarinettist": "clarinetist",
+  "clarinettists": "clarinetists",
+  "collectivise": "collectivize",
+  "collectivised": "collectivized",
+  "collectivises": "collectivizes",
+  "collectivising": "collectivizing",
+  "colonisation": "colonization",
+  "colonise": "colonize",
+  "colonised": "colonized",
+  "coloniser": "colonizer",
+  "colonisers": "colonizers",
+  "colonises": "colonizes",
+  "colonising": "colonizing",
+  "colour": "color",
+  "colourant": "colorant",
+  "colourants": "colorants",
+  "coloured": "colored",
+  "coloureds": "coloreds",
+  "colourful": "colorful",
+  "colourfully": "colorfully",
+  "colouring": "coloring",
+  "colourize": "colorize",
+  "colourized": "colorized",
+  "colourizes": "colorizes",
+  "colourizing": "colorizing",
+  "colourless": "colorless",
+  "colours": "colors",
+  "commercialise": "commercialize",
+  "commercialised": "commercialized",
+  "commercialises": "commercializes",
+  "commercialising": "commercializing",
+  "compartmentalise": "compartmentalize",
+  "compartmentalised": "compartmentalized",
+  "compartmentalises": "compartmentalizes",
+  "compartmentalising": "compartmentalizing",
+  "computerise": "computerize",
+  "computerised": "computerized",
+  "computerises": "computerizes",
+  "computerising": "computerizing",
+  "conceptualise": "conceptualize",
+  "conceptualised": "conceptualized",
+  "conceptualises": "conceptualizes",
+  "conceptualising": "conceptualizing",
+  "connexion": "connection",
+  "connexions": "connections",
+  "contextualise": "contextualize",
+  "contextualised": "contextualized",
+  "contextualises": "contextualizes",
+  "contextualising": "contextualizing",
+  "cosier": "cozier",
+  "cosies": "cozies",
+  "cosiest": "coziest",
+  "cosily": "cozily",
+  "cosiness": "coziness",
+  "cosy": "cozy",
+  "councillor": "councilor",
+  "councillors": "councilors",
+  "counselled": "counseled",
+  "counselling": "counseling",
+  "counsellor": "counselor",
+  "counsellors": "counselors",
+  "crenelated": "crenellated",
+  "criminalise": "criminalize",
+  "criminalised": "criminalized",
+  "criminalises": "criminalizes",
+  "criminalising": "criminalizing",
+  "criticise": "criticize",
+  "criticised": "criticized",
+  "criticises": "criticizes",
+  "criticising": "criticizing",
+  "crueller": "crueler",
+  "cruellest": "cruelest",
+  "crystallisation": "crystallization",
+  "crystallise": "crystallize",
+  "crystallised": "crystallized",
+  "crystallises": "crystallizes",
+  "crystallising": "crystallizing",
+  "cudgelled": "cudgeled",
+  "cudgelling": "cudgeling",
+  "customise": "customize",
+  "customised": "customized",
+  "customises": "customizes",
+  "customising": "customizing",
+  "cypher": "cipher",
+  "cyphers": "ciphers",
+  "decentralisation": "decentralization",
+  "decentralise": "decentralize",
+  "decentralised": "decentralized",
+  "decentralises": "decentralizes",
+  "decentralising": "decentralizing",
+  "decriminalisation": "decriminalization",
+  "decriminalise": "decriminalize",
+  "decriminalised": "decriminalized",
+  "decriminalises": "decriminalizes",
+  "decriminalising": "decriminalizing",
+  "defence": "defense",
+  "defenceless": "defenseless",
+  "defences": "defenses",
+  "dehumanisation": "dehumanization",
+  "dehumanise": "dehumanize",
+  "dehumanised": "dehumanized",
+  "dehumanises": "dehumanizes",
+  "dehumanising": "dehumanizing",
+  "demeanour": "demeanor",
+  "demilitarisation": "demilitarization",
+  "demilitarise": "demilitarize",
+  "demilitarised": "demilitarized",
+  "demilitarises": "demilitarizes",
+  "demilitarising": "demilitarizing",
+  "demobilisation": "demobilization",
+  "demobilise": "demobilize",
+  "demobilised": "demobilized",
+  "demobilises": "demobilizes",
+  "demobilising": "demobilizing",
+  "democratisation": "democratization",
+  "democratise": "democratize",
+  "democratised": "democratized",
+  "democratises": "democratizes",
+  "democratising": "democratizing",
+  "demonise": "demonize",
+  "demonised": "demonized",
+  "demonises": "demonizes",
+  "demonising": "demonizing",
+  "demoralisation": "demoralization",
+  "demoralise": "demoralize",
+  "demoralised": "demoralized",
+  "demoralises": "demoralizes",
+  "demoralising": "demoralizing",
+  "denationalisation": "denationalization",
+  "denationalise": "denationalize",
+  "denationalised": "denationalized",
+  "denationalises": "denationalizes",
+  "denationalising": "denationalizing",
+  "deodorise": "deodorize",
+  "deodorised": "deodorized",
+  "deodorises": "deodorizes",
+  "deodorising": "deodorizing",
+  "depersonalise": "depersonalize",
+  "depersonalised": "depersonalized",
+  "depersonalises": "depersonalizes",
+  "depersonalising": "depersonalizing",
+  "deputise": "deputize",
+  "deputised": "deputized",
+  "deputises": "deputizes",
+  "deputising": "deputizing",
+  "desensitisation": "desensitization",
+  "desensitise": "desensitize",
+  "desensitised": "desensitized",
+  "desensitises": "desensitizes",
+  "desensitising": "desensitizing",
+  "destabilisation": "destabilization",
+  "destabilise": "destabilize",
+  "destabilised": "destabilized",
+  "destabilises": "destabilizes",
+  "destabilising": "destabilizing",
+  "dialled": "dialed",
+  "dialling": "dialing",
+  "dialogue": "dialog",
+  "dialogues": "dialogs",
+  "diarrhoea": "diarrhea",
+  "digitise": "digitize",
+  "digitised": "digitized",
+  "digitises": "digitizes",
+  "digitising": "digitizing",
+  "disc": "disk",
+  "discolour": "discolor",
+  "discoloured": "discolored",
+  "discolouring": "discoloring",
+  "discolours": "discolors",
+  "discs": "disks",
+  "disembowelled": "disemboweled",
+  "disembowelling": "disemboweling",
+  "disfavour": "disfavor",
+  "dishevelled": "disheveled",
+  "dishonour": "dishonor",
+  "dishonourable": "dishonorable",
+  "dishonourably": "dishonorably",
+  "dishonoured": "dishonored",
+  "dishonouring": "dishonoring",
+  "dishonours": "dishonors",
+  "disorganisation": "disorganization",
+  "disorganised": "disorganized",
+  "distil": "distill",
+  "distils": "distills",
+  "dramatisation": "dramatization",
+  "dramatisations": "dramatizations",
+  "dramatise": "dramatize",
+  "dramatised": "dramatized",
+  "dramatises": "dramatizes",
+  "dramatising": "dramatizing",
+  "draught": "draft",
+  "draughtboard": "draftboard",
+  "draughtboards": "draftboards",
+  "draughtier": "draftier",
+  "draughtiest": "draftiest",
+  "draughts": "drafts",
+  "draughtsman": "draftsman",
+  "draughtsmanship": "draftsmanship",
+  "draughtsmen": "draftsmen",
+  "draughtswoman": "draftswoman",
+  "draughtswomen": "draftswomen",
+  "draughty": "drafty",
+  "drivelled": "driveled",
+  "drivelling": "driveling",
+  "duelled": "dueled",
+  "duelling": "dueling",
+  "economise": "economize",
+  "economised": "economized",
+  "economises": "economizes",
+  "economising": "economizing",
+  "editorialise": "editorialize",
+  "editorialised": "editorialized",
+  "editorialises": "editorializes",
+  "editorialising": "editorializing",
+  "edoema": "edema",
+  "empathise": "empathize",
+  "empathised": "empathized",
+  "empathises": "empathizes",
+  "empathising": "empathizing",
+  "emphasise": "emphasize",
+  "emphasised": "emphasized",
+  "emphasises": "emphasizes",
+  "emphasising": "emphasizing",
+  "enamelled": "enameled",
+  "enamelling": "enameling",
+  "enamoured": "enamored",
+  "encyclopaedia": "encyclopedia",
+  "encyclopaedias": "encyclopedias",
+  "encyclopaedic": "encyclopedic",
+  "endeavour": "endeavor",
+  "endeavoured": "endeavored",
+  "endeavouring": "endeavoring",
+  "endeavours": "endeavors",
+  "energise": "energize",
+  "energised": "energized",
+  "energises": "energizes",
+  "energising": "energizing",
+  "enrol": "enroll",
+  "enrols": "enrolls",
+  "enthral": "enthrall",
+  "enthrals": "enthralls",
+  "epaulette": "epaulet",
+  "epaulettes": "epaulets",
+  "epicentre": "epicenter",
+  "epicentres": "epicenters",
+  "epilogue": "epilog",
+  "epilogues": "epilogs",
+  "epitomise": "epitomize",
+  "epitomised": "epitomized",
+  "epitomises": "epitomizes",
+  "epitomising": "epitomizing",
+  "equalisation": "equalization",
+  "equalise": "equalize",
+  "equalised": "equalized",
+  "equaliser": "equalizer",
+  "equalisers": "equalizers",
+  "equalises": "equalizes",
+  "equalising": "equalizing",
+  "eulogise": "eulogize",
+  "eulogised": "eulogized",
+  "eulogises": "eulogizes",
+  "eulogising": "eulogizing",
+  "evangelise": "evangelize",
+  "evangelised": "evangelized",
+  "evangelises": "evangelizes",
+  "evangelising": "evangelizing",
+  "exorcise": "exorcize",
+  "exorcised": "exorcized",
+  "exorcises": "exorcizes",
+  "exorcising": "exorcizing",
+  "extemporisation": "extemporization",
+  "extemporise": "extemporize",
+  "extemporised": "extemporized",
+  "extemporises": "extemporizes",
+  "extemporising": "extemporizing",
+  "externalisation": "externalization",
+  "externalisations": "externalizations",
+  "externalise": "externalize",
+  "externalised": "externalized",
+  "externalises": "externalizes",
+  "externalising": "externalizing",
+  "factorise": "factorize",
+  "factorised": "factorized",
+  "factorises": "factorizes",
+  "factorising": "factorizing",
+  "faecal": "fecal",
+  "faeces": "feces",
+  "familiarisation": "familiarization",
+  "familiarise": "familiarize",
+  "familiarised": "familiarized",
+  "familiarises": "familiarizes",
+  "familiarising": "familiarizing",
+  "fantasise": "fantasize",
+  "fantasised": "fantasized",
+  "fantasises": "fantasizes",
+  "fantasising": "fantasizing",
+  "favour": "favor",
+  "favourable": "favorable",
+  "favourably": "favorably",
+  "favoured": "favored",
+  "favouring": "favoring",
+  "favourite": "favorite",
+  "favourites": "favorites",
+  "favouritism": "favoritism",
+  "favours": "favors",
+  "feminise": "feminize",
+  "feminised": "feminized",
+  "feminises": "feminizes",
+  "feminising": "feminizing",
+  "fertilisation": "fertilization",
+  "fertilise": "fertilize",
+  "fertilised": "fertilized",
+  "fertiliser": "fertilizer",
+  "fertilisers": "fertilizers",
+  "fertilises": "fertilizes",
+  "fertilising": "fertilizing",
+  "fervour": "fervor",
+  "fibre": "fiber",
+  "fibreglass": "fiberglass",
+  "fibres": "fibers",
+  "fictionalisation": "fictionalization",
+  "fictionalisations": "fictionalizations",
+  "fictionalise": "fictionalize",
+  "fictionalised": "fictionalized",
+  "fictionalises": "fictionalizes",
+  "fictionalising": "fictionalizing",
+  "fillet": "filet",
+  "filleted": "fileted",
+  "filleting": "fileting",
+  "fillets": "filets",
+  "finalisation": "finalization",
+  "finalise": "finalize",
+  "finalised": "finalized",
+  "finalises": "finalizes",
+  "finalising": "finalizing",
+  "flautist": "flutist",
+  "flautists": "flutists",
+  "flavour": "flavor",
+  "flavoured": "flavored",
+  "flavouring": "flavoring",
+  "flavourings": "flavorings",
+  "flavourless": "flavorless",
+  "flavours": "flavors",
+  "flavoursome": "flavorsome",
+  "flyer / flier": "flier / flyer",
+  "foetal": "fetal",
+  "foetid": "fetid",
+  "foetus": "fetus",
+  "foetuses": "fetuses",
+  "formalisation": "formalization",
+  "formalise": "formalize",
+  "formalised": "formalized",
+  "formalises": "formalizes",
+  "formalising": "formalizing",
+  "fossilisation": "fossilization",
+  "fossilise": "fossilize",
+  "fossilised": "fossilized",
+  "fossilises": "fossilizes",
+  "fossilising": "fossilizing",
+  "fraternisation": "fraternization",
+  "fraternise": "fraternize",
+  "fraternised": "fraternized",
+  "fraternises": "fraternizes",
+  "fraternising": "fraternizing",
+  "fulfil": "fulfill",
+  "fulfilment": "fulfillment",
+  "fulfils": "fulfills",
+  "funnelled": "funneled",
+  "funnelling": "funneling",
+  "gage": "gauge",
+  "gaged": "gauged",
+  "gages": "gauges",
+  "gaging": "gauging",
+  "galvanise": "galvanize",
+  "galvanised": "galvanized",
+  "galvanises": "galvanizes",
+  "galvanising": "galvanizing",
+  "gambolled": "gamboled",
+  "gambolling": "gamboling",
+  "gaol": "jail",
+  "gaolbird": "jailbird",
+  "gaolbirds": "jailbirds",
+  "gaolbreak": "jailbreak",
+  "gaolbreaks": "jailbreaks",
+  "gaoled": "jailed",
+  "gaoler": "jailer",
+  "gaolers": "jailers",
+  "gaoling": "jailing",
+  "gaols": "jails",
+  "gasses": "gases",
+  "generalisation": "generalization",
+  "generalisations": "generalizations",
+  "generalise": "generalize",
+  "generalised": "generalized",
+  "generalises": "generalizes",
+  "generalising": "generalizing",
+  "ghettoise": "ghettoize",
+  "ghettoised": "ghettoized",
+  "ghettoises": "ghettoizes",
+  "ghettoising": "ghettoizing",
+  "gipsies": "gypsies",
+  "glamor": "glamour",
+  "glamorise": "glamorize",
+  "glamorised": "glamorized",
+  "glamorises": "glamorizes",
+  "glamorising": "glamorizing",
+  "globalisation": "globalization",
+  "globalise": "globalize",
+  "globalised": "globalized",
+  "globalises": "globalizes",
+  "globalising": "globalizing",
+  "glueing": "gluing",
+  "goitre": "goiter",
+  "goitres": "goiters",
+  "gonorrhoea": "gonorrhea",
+  "gramme": "gram",
+  "grammes": "grams",
+  "gravelled": "graveled",
+  "grey": "gray",
+  "greyed": "grayed",
+  "greying": "graying",
+  "greyish": "grayish",
+  "greyness": "grayness",
+  "greys": "grays",
+  "grovelled": "groveled",
+  "grovelling": "groveling",
+  "groyne": "groin",
+  "groynes": "groins",
+  "gruelling": "grueling",
+  "gruellingly": "gruelingly",
+  "gryphon": "griffin",
+  "gryphons": "griffins",
+  "gynaecological": "gynecological",
+  "gynaecologist": "gynecologist",
+  "gynaecologists": "gynecologists",
+  "gynaecology": "gynecology",
+  "haematological": "hematological",
+  "haematologist": "hematologist",
+  "haematologists": "hematologists",
+  "haematology": "hematology",
+  "haemoglobin": "hemoglobin",
+  "haemophilia": "hemophilia",
+  "haemophiliac": "hemophiliac",
+  "haemophiliacs": "hemophiliacs",
+  "haemorrhage": "hemorrhage",
+  "haemorrhaged": "hemorrhaged",
+  "haemorrhages": "hemorrhages",
+  "haemorrhaging": "hemorrhaging",
+  "haemorrhoids": "hemorrhoids",
+  "harbour": "harbor",
+  "harboured": "harbored",
+  "harbouring": "harboring",
+  "harbours": "harbors",
+  "harmonisation": "harmonization",
+  "harmonise": "harmonize",
+  "harmonised": "harmonized",
+  "harmonises": "harmonizes",
+  "harmonising": "harmonizing",
+  "homoeopath": "homeopath",
+  "homoeopathic": "homeopathic",
+  "homoeopaths": "homeopaths",
+  "homoeopathy": "homeopathy",
+  "homogenise": "homogenize",
+  "homogenised": "homogenized",
+  "homogenises": "homogenizes",
+  "homogenising": "homogenizing",
+  "honour": "honor",
+  "honourable": "honorable",
+  "honourably": "honorably",
+  "honoured": "honored",
+  "honouring": "honoring",
+  "honours": "honors",
+  "hospitalisation": "hospitalization",
+  "hospitalise": "hospitalize",
+  "hospitalised": "hospitalized",
+  "hospitalises": "hospitalizes",
+  "hospitalising": "hospitalizing",
+  "humanise": "humanize",
+  "humanised": "humanized",
+  "humanises": "humanizes",
+  "humanising": "humanizing",
+  "humour": "humor",
+  "humoured": "humored",
+  "humouring": "humoring",
+  "humourless": "humorless",
+  "humours": "humors",
+  "hybridise": "hybridize",
+  "hybridised": "hybridized",
+  "hybridises": "hybridizes",
+  "hybridising": "hybridizing",
+  "hypnotise": "hypnotize",
+  "hypnotised": "hypnotized",
+  "hypnotises": "hypnotizes",
+  "hypnotising": "hypnotizing",
+  "hypothesise": "hypothesize",
+  "hypothesised": "hypothesized",
+  "hypothesises": "hypothesizes",
+  "hypothesising": "hypothesizing",
+  "idealisation": "idealization",
+  "idealise": "idealize",
+  "idealised": "idealized",
+  "idealises": "idealizes",
+  "idealising": "idealizing",
+  "idolise": "idolize",
+  "idolised": "idolized",
+  "idolises": "idolizes",
+  "idolising": "idolizing",
+  "immobilisation": "immobilization",
+  "immobilise": "immobilize",
+  "immobilised": "immobilized",
+  "immobiliser": "immobilizer",
+  "immobilisers": "immobilizers",
+  "immobilises": "immobilizes",
+  "immobilising": "immobilizing",
+  "immortalise": "immortalize",
+  "immortalised": "immortalized",
+  "immortalises": "immortalizes",
+  "immortalising": "immortalizing",
+  "immunisation": "immunization",
+  "immunise": "immunize",
+  "immunised": "immunized",
+  "immunises": "immunizes",
+  "immunising": "immunizing",
+  "impanelled": "impaneled",
+  "impanelling": "impaneling",
+  "imperilled": "imperiled",
+  "imperilling": "imperiling",
+  "individualise": "individualize",
+  "individualised": "individualized",
+  "individualises": "individualizes",
+  "individualising": "individualizing",
+  "industrialise": "industrialize",
+  "industrialised": "industrialized",
+  "industrialises": "industrializes",
+  "industrialising": "industrializing",
+  "inflexion": "inflection",
+  "inflexions": "inflections",
+  "initialise": "initialize",
+  "initialised": "initialized",
+  "initialises": "initializes",
+  "initialising": "initializing",
+  "initialled": "initialed",
+  "initialling": "initialing",
+  "instal": "install",
+  "instalment": "installment",
+  "instalments": "installments",
+  "instals": "installs",
+  "instil": "instill",
+  "instils": "instills",
+  "institutionalisation": "institutionalization",
+  "institutionalise": "institutionalize",
+  "institutionalised": "institutionalized",
+  "institutionalises": "institutionalizes",
+  "institutionalising": "institutionalizing",
+  "intellectualise": "intellectualize",
+  "intellectualised": "intellectualized",
+  "intellectualises": "intellectualizes",
+  "intellectualising": "intellectualizing",
+  "internalisation": "internalization",
+  "internalise": "internalize",
+  "internalised": "internalized",
+  "internalises": "internalizes",
+  "internalising": "internalizing",
+  "internationalisation": "internationalization",
+  "internationalise": "internationalize",
+  "internationalised": "internationalized",
+  "internationalises": "internationalizes",
+  "internationalising": "internationalizing",
+  "ionisation": "ionization",
+  "ionise": "ionize",
+  "ionised": "ionized",
+  "ioniser": "ionizer",
+  "ionisers": "ionizers",
+  "ionises": "ionizes",
+  "ionising": "ionizing",
+  "italicise": "italicize",
+  "italicised": "italicized",
+  "italicises": "italicizes",
+  "italicising": "italicizing",
+  "itemise": "itemize",
+  "itemised": "itemized",
+  "itemises": "itemizes",
+  "itemising": "itemizing",
+  "jeopardise": "jeopardize",
+  "jeopardised": "jeopardized",
+  "jeopardises": "jeopardizes",
+  "jeopardising": "jeopardizing",
+  "jewelled": "jeweled",
+  "jeweller": "jeweler",
+  "jewellers": "jewelers",
+  "jewellery": "jewelry",
+  "judgement": "judgment",
+  "kilogramme": "kilogram",
+  "kilogrammes": "kilograms",
+  "kilometre": "kilometer",
+  "kilometres": "kilometers",
+  "labelled": "labeled",
+  "labelling": "labeling",
+  "labour": "labor",
+  "laboured": "labored",
+  "labourer": "laborer",
+  "labourers": "laborers",
+  "labouring": "laboring",
+  "labours": "labors",
+  "lacklustre": "lackluster",
+  "legalisation": "legalization",
+  "legalise": "legalize",
+  "legalised": "legalized",
+  "legalises": "legalizes",
+  "legalising": "legalizing",
+  "legitimise": "legitimize",
+  "legitimised": "legitimized",
+  "legitimises": "legitimizes",
+  "legitimising": "legitimizing",
+  "leukaemia": "leukemia",
+  "levelled": "leveled",
+  "leveller": "leveler",
+  "levellers": "levelers",
+  "levelling": "leveling",
+  "libelled": "libeled",
+  "libelling": "libeling",
+  "libellous": "libelous",
+  "liberalisation": "liberalization",
+  "liberalise": "liberalize",
+  "liberalised": "liberalized",
+  "liberalises": "liberalizes",
+  "liberalising": "liberalizing",
+  "licence": "license",
+  "licenced": "licensed",
+  "licences": "licenses",
+  "licencing": "licensing",
+  "likeable": "likable",
+  "lionisation": "lionization",
+  "lionise": "lionize",
+  "lionised": "lionized",
+  "lionises": "lionizes",
+  "lionising": "lionizing",
+  "liquidise": "liquidize",
+  "liquidised": "liquidized",
+  "liquidiser": "liquidizer",
+  "liquidisers": "liquidizers",
+  "liquidises": "liquidizes",
+  "liquidising": "liquidizing",
+  "litre": "liter",
+  "litres": "liters",
+  "localise": "localize",
+  "localised": "localized",
+  "localises": "localizes",
+  "localising": "localizing",
+  "louvre": "louver",
+  "louvred": "louvered",
+  "louvres": "louvers",
+  "lustre": "luster",
+  "magnetise": "magnetize",
+  "magnetised": "magnetized",
+  "magnetises": "magnetizes",
+  "magnetising": "magnetizing",
+  "manoeuvrability": "maneuverability",
+  "manoeuvrable": "maneuverable",
+  "manoeuvre": "maneuver",
+  "manoeuvred": "maneuvered",
+  "manoeuvres": "maneuvers",
+  "manoeuvring": "maneuvering",
+  "manoeuvrings": "maneuverings",
+  "marginalisation": "marginalization",
+  "marginalise": "marginalize",
+  "marginalised": "marginalized",
+  "marginalises": "marginalizes",
+  "marginalising": "marginalizing",
+  "marshalled": "marshaled",
+  "marshalling": "marshaling",
+  "marvelled": "marveled",
+  "marvelling": "marveling",
+  "marvellous": "marvelous",
+  "marvellously": "marvelously",
+  "materialisation": "materialization",
+  "materialise": "materialize",
+  "materialised": "materialized",
+  "materialises": "materializes",
+  "materialising": "materializing",
+  "maximisation": "maximization",
+  "maximise": "maximize",
+  "maximised": "maximized",
+  "maximises": "maximizes",
+  "maximising": "maximizing",
+  "meagre": "meager",
+  "mechanisation": "mechanization",
+  "mechanise": "mechanize",
+  "mechanised": "mechanized",
+  "mechanises": "mechanizes",
+  "mechanising": "mechanizing",
+  "mediaeval": "medieval",
+  "memorialise": "memorialize",
+  "memorialised": "memorialized",
+  "memorialises": "memorializes",
+  "memorialising": "memorializing",
+  "memorise": "memorize",
+  "memorised": "memorized",
+  "memorises": "memorizes",
+  "memorising": "memorizing",
+  "mesmerise": "mesmerize",
+  "mesmerised": "mesmerized",
+  "mesmerises": "mesmerizes",
+  "mesmerising": "mesmerizing",
+  "metabolise": "metabolize",
+  "metabolised": "metabolized",
+  "metabolises": "metabolizes",
+  "metabolising": "metabolizing",
+  "metre": "meter",
+  "metres": "meters",
+  "mhm": "hmm",
+  "micrometre": "micrometer",
+  "micrometres": "micrometers",
+  "militarise": "militarize",
+  "militarised": "militarized",
+  "militarises": "militarizes",
+  "militarising": "militarizing",
+  "milligramme": "milligram",
+  "milligrammes": "milligrams",
+  "millilitre": "milliliter",
+  "millilitres": "milliliters",
+  "millimetre": "millimeter",
+  "millimetres": "millimeters",
+  "miniaturisation": "miniaturization",
+  "miniaturise": "miniaturize",
+  "miniaturised": "miniaturized",
+  "miniaturises": "miniaturizes",
+  "miniaturising": "miniaturizing",
+  "minibusses": "minibuses",
+  "minimise": "minimize",
+  "minimised": "minimized",
+  "minimises": "minimizes",
+  "minimising": "minimizing",
+  "misbehaviour": "misbehavior",
+  "misdemeanour": "misdemeanor",
+  "misdemeanours": "misdemeanors",
+  "misspelt": "misspelled",
+  "mitre": "miter",
+  "mitres": "miters",
+  "mm": "hmm",
+  "mmm": "hmm",
+  "mobilisation": "mobilization",
+  "mobilise": "mobilize",
+  "mobilised": "mobilized",
+  "mobilises": "mobilizes",
+  "mobilising": "mobilizing",
+  "modelled": "modeled",
+  "modeller": "modeler",
+  "modellers": "modelers",
+  "modelling": "modeling",
+  "modernise": "modernize",
+  "modernised": "modernized",
+  "modernises": "modernizes",
+  "modernising": "modernizing",
+  "moisturise": "moisturize",
+  "moisturised": "moisturized",
+  "moisturiser": "moisturizer",
+  "moisturisers": "moisturizers",
+  "moisturises": "moisturizes",
+  "moisturising": "moisturizing",
+  "monologue": "monolog",
+  "monologues": "monologs",
+  "monopolisation": "monopolization",
+  "monopolise": "monopolize",
+  "monopolised": "monopolized",
+  "monopolises": "monopolizes",
+  "monopolising": "monopolizing",
+  "moralise": "moralize",
+  "moralised": "moralized",
+  "moralises": "moralizes",
+  "moralising": "moralizing",
+  "motorised": "motorized",
+  "mould": "mold",
+  "moulded": "molded",
+  "moulder": "molder",
+  "mouldered": "moldered",
+  "mouldering": "moldering",
+  "moulders": "molders",
+  "mouldier": "moldier",
+  "mouldiest": "moldiest",
+  "moulding": "molding",
+  "mouldings": "moldings",
+  "moulds": "molds",
+  "mouldy": "moldy",
+  "moult": "molt",
+  "moulted": "molted",
+  "moulting": "molting",
+  "moults": "molts",
+  "moustache": "mustache",
+  "moustached": "mustached",
+  "moustaches": "mustaches",
+  "moustachioed": "mustachioed",
+  "multicoloured": "multicolored",
+  "nationalisation": "nationalization",
+  "nationalisations": "nationalizations",
+  "nationalise": "nationalize",
+  "nationalised": "nationalized",
+  "nationalises": "nationalizes",
+  "nationalising": "nationalizing",
+  "naturalisation": "naturalization",
+  "naturalise": "naturalize",
+  "naturalised": "naturalized",
+  "naturalises": "naturalizes",
+  "naturalising": "naturalizing",
+  "neighbour": "neighbor",
+  "neighbourhood": "neighborhood",
+  "neighbourhoods": "neighborhoods",
+  "neighbouring": "neighboring",
+  "neighbourliness": "neighborliness",
+  "neighbourly": "neighborly",
+  "neighbours": "neighbors",
+  "neutralisation": "neutralization",
+  "neutralise": "neutralize",
+  "neutralised": "neutralized",
+  "neutralises": "neutralizes",
+  "neutralising": "neutralizing",
+  "normalisation": "normalization",
+  "normalise": "normalize",
+  "normalised": "normalized",
+  "normalises": "normalizes",
+  "normalising": "normalizing",
+  "odour": "odor",
+  "odourless": "odorless",
+  "odours": "odors",
+  "oesophagus": "esophagus",
+  "oesophaguses": "esophaguses",
+  "oestrogen": "estrogen",
+  "offence": "offense",
+  "offences": "offenses",
+  "omelette": "omelet",
+  "omelettes": "omelets",
+  "optimise": "optimize",
+  "optimised": "optimized",
+  "optimises": "optimizes",
+  "optimising": "optimizing",
+  "organisation": "organization",
+  "organisational": "organizational",
+  "organisations": "organizations",
+  "organise": "organize",
+  "organised": "organized",
+  "organiser": "organizer",
+  "organisers": "organizers",
+  "organises": "organizes",
+  "organising": "organizing",
+  "orthopaedic": "orthopedic",
+  "orthopaedics": "orthopedics",
+  "ostracise": "ostracize",
+  "ostracised": "ostracized",
+  "ostracises": "ostracizes",
+  "ostracising": "ostracizing",
+  "outmanoeuvre": "outmaneuver",
+  "outmanoeuvred": "outmaneuvered",
+  "outmanoeuvres": "outmaneuvers",
+  "outmanoeuvring": "outmaneuvering",
+  "overemphasise": "overemphasize",
+  "overemphasised": "overemphasized",
+  "overemphasises": "overemphasizes",
+  "overemphasising": "overemphasizing",
+  "oxidisation": "oxidization",
+  "oxidise": "oxidize",
+  "oxidised": "oxidized",
+  "oxidises": "oxidizes",
+  "oxidising": "oxidizing",
+  "paederast": "pederast",
+  "paederasts": "pederasts",
+  "paediatric": "pediatric",
+  "paediatrician": "pediatrician",
+  "paediatricians": "pediatricians",
+  "paediatrics": "pediatrics",
+  "paedophile": "pedophile",
+  "paedophiles": "pedophiles",
+  "paedophilia": "pedophilia",
+  "palaeolithic": "paleolithic",
+  "palaeontologist": "paleontologist",
+  "palaeontologists": "paleontologists",
+  "palaeontology": "paleontology",
+  "panelled": "paneled",
+  "panelling": "paneling",
+  "panellist": "panelist",
+  "panellists": "panelists",
+  "paralyse": "paralyze",
+  "paralysed": "paralyzed",
+  "paralyses": "paralyzes",
+  "paralysing": "paralyzing",
+  "parcelled": "parceled",
+  "parcelling": "parceling",
+  "parlour": "parlor",
+  "parlours": "parlors",
+  "particularise": "particularize",
+  "particularised": "particularized",
+  "particularises": "particularizes",
+  "particularising": "particularizing",
+  "passivisation": "passivization",
+  "passivise": "passivize",
+  "passivised": "passivized",
+  "passivises": "passivizes",
+  "passivising": "passivizing",
+  "pasteurisation": "pasteurization",
+  "pasteurise": "pasteurize",
+  "pasteurised": "pasteurized",
+  "pasteurises": "pasteurizes",
+  "pasteurising": "pasteurizing",
+  "patronise": "patronize",
+  "patronised": "patronized",
+  "patronises": "patronizes",
+  "patronising": "patronizing",
+  "patronisingly": "patronizingly",
+  "pedalled": "pedaled",
+  "pedalling": "pedaling",
+  "pedestrianisation": "pedestrianization",
+  "pedestrianise": "pedestrianize",
+  "pedestrianised": "pedestrianized",
+  "pedestrianises": "pedestrianizes",
+  "pedestrianising": "pedestrianizing",
+  "penalise": "penalize",
+  "penalised": "penalized",
+  "penalises": "penalizes",
+  "penalising": "penalizing",
+  "pencilled": "penciled",
+  "pencilling": "penciling",
+  "personalise": "personalize",
+  "personalised": "personalized",
+  "personalises": "personalizes",
+  "personalising": "personalizing",
+  "pharmacopoeia": "pharmacopeia",
+  "pharmacopoeias": "pharmacopeias",
+  "philosophise": "philosophize",
+  "philosophised": "philosophized",
+  "philosophises": "philosophizes",
+  "philosophising": "philosophizing",
+  "philtre": "filter",
+  "philtres": "filters",
+  "phoney": "phony",
+  "plagiarise": "plagiarize",
+  "plagiarised": "plagiarized",
+  "plagiarises": "plagiarizes",
+  "plagiarising": "plagiarizing",
+  "plough": "plow",
+  "ploughed": "plowed",
+  "ploughing": "plowing",
+  "ploughman": "plowman",
+  "ploughmen": "plowmen",
+  "ploughs": "plows",
+  "ploughshare": "plowshare",
+  "ploughshares": "plowshares",
+  "polarisation": "polarization",
+  "polarise": "polarize",
+  "polarised": "polarized",
+  "polarises": "polarizes",
+  "polarising": "polarizing",
+  "politicisation": "politicization",
+  "politicise": "politicize",
+  "politicised": "politicized",
+  "politicises": "politicizes",
+  "politicising": "politicizing",
+  "popularisation": "popularization",
+  "popularise": "popularize",
+  "popularised": "popularized",
+  "popularises": "popularizes",
+  "popularising": "popularizing",
+  "pouffe": "pouf",
+  "pouffes": "poufs",
+  "practise": "practice",
+  "practised": "practiced",
+  "practises": "practices",
+  "practising": "practicing",
+  "praesidium": "presidium",
+  "praesidiums": "presidiums",
+  "pressurisation": "pressurization",
+  "pressurise": "pressurize",
+  "pressurised": "pressurized",
+  "pressurises": "pressurizes",
+  "pressurising": "pressurizing",
+  "pretence": "pretense",
+  "pretences": "pretenses",
+  "primaeval": "primeval",
+  "prioritisation": "prioritization",
+  "prioritise": "prioritize",
+  "prioritised": "prioritized",
+  "prioritises": "prioritizes",
+  "prioritising": "prioritizing",
+  "privatisation": "privatization",
+  "privatisations": "privatizations",
+  "privatise": "privatize",
+  "privatised": "privatized",
+  "privatises": "privatizes",
+  "privatising": "privatizing",
+  "professionalisation": "professionalization",
+  "professionalise": "professionalize",
+  "professionalised": "professionalized",
+  "professionalises": "professionalizes",
+  "professionalising": "professionalizing",
+  "programme": "program",
+  "programmes": "programs",
+  "prologue": "prolog",
+  "prologues": "prologs",
+  "propagandise": "propagandize",
+  "propagandised": "propagandized",
+  "propagandises": "propagandizes",
+  "propagandising": "propagandizing",
+  "proselytise": "proselytize",
+  "proselytised": "proselytized",
+  "proselytiser": "proselytizer",
+  "proselytisers": "proselytizers",
+  "proselytises": "proselytizes",
+  "proselytising": "proselytizing",
+  "psychoanalyse": "psychoanalyze",
+  "psychoanalysed": "psychoanalyzed",
+  "psychoanalyses": "psychoanalyzes",
+  "psychoanalysing": "psychoanalyzing",
+  "publicise": "publicize",
+  "publicised": "publicized",
+  "publicises": "publicizes",
+  "publicising": "publicizing",
+  "pulverisation": "pulverization",
+  "pulverise": "pulverize",
+  "pulverised": "pulverized",
+  "pulverises": "pulverizes",
+  "pulverising": "pulverizing",
+  "pummelled": "pummel",
+  "pummelling": "pummeled",
+  "pyjama": "pajama",
+  "pyjamas": "pajamas",
+  "pzazz": "pizzazz",
+  "quarrelled": "quarreled",
+  "quarrelling": "quarreling",
+  "radicalise": "radicalize",
+  "radicalised": "radicalized",
+  "radicalises": "radicalizes",
+  "radicalising": "radicalizing",
+  "rancour": "rancor",
+  "randomise": "randomize",
+  "randomised": "randomized",
+  "randomises": "randomizes",
+  "randomising": "randomizing",
+  "rationalisation": "rationalization",
+  "rationalisations": "rationalizations",
+  "rationalise": "rationalize",
+  "rationalised": "rationalized",
+  "rationalises": "rationalizes",
+  "rationalising": "rationalizing",
+  "ravelled": "raveled",
+  "ravelling": "raveling",
+  "realisable": "realizable",
+  "realisation": "realization",
+  "realisations": "realizations",
+  "realise": "realize",
+  "realised": "realized",
+  "realises": "realizes",
+  "realising": "realizing",
+  "recognisable": "recognizable",
+  "recognisably": "recognizably",
+  "recognisance": "recognizance",
+  "recognise": "recognize",
+  "recognised": "recognized",
+  "recognises": "recognizes",
+  "recognising": "recognizing",
+  "reconnoitre": "reconnoiter",
+  "reconnoitred": "reconnoitered",
+  "reconnoitres": "reconnoiters",
+  "reconnoitring": "reconnoitering",
+  "refuelled": "refueled",
+  "refuelling": "refueling",
+  "regularisation": "regularization",
+  "regularise": "regularize",
+  "regularised": "regularized",
+  "regularises": "regularizes",
+  "regularising": "regularizing",
+  "remodelled": "remodeled",
+  "remodelling": "remodeling",
+  "remould": "remold",
+  "remoulded": "remolded",
+  "remoulding": "remolding",
+  "remoulds": "remolds",
+  "reorganisation": "reorganization",
+  "reorganisations": "reorganizations",
+  "reorganise": "reorganize",
+  "reorganised": "reorganized",
+  "reorganises": "reorganizes",
+  "reorganising": "reorganizing",
+  "revelled": "reveled",
+  "reveller": "reveler",
+  "revellers": "revelers",
+  "revelling": "reveling",
+  "revitalise": "revitalize",
+  "revitalised": "revitalized",
+  "revitalises": "revitalizes",
+  "revitalising": "revitalizing",
+  "revolutionise": "revolutionize",
+  "revolutionised": "revolutionized",
+  "revolutionises": "revolutionizes",
+  "revolutionising": "revolutionizing",
+  "rhapsodise": "rhapsodize",
+  "rhapsodised": "rhapsodized",
+  "rhapsodises": "rhapsodizes",
+  "rhapsodising": "rhapsodizing",
+  "rigour": "rigor",
+  "rigours": "rigors",
+  "ritualised": "ritualized",
+  "rivalled": "rivaled",
+  "rivalling": "rivaling",
+  "romanticise": "romanticize",
+  "romanticised": "romanticized",
+  "romanticises": "romanticizes",
+  "romanticising": "romanticizing",
+  "rumour": "rumor",
+  "rumoured": "rumored",
+  "rumours": "rumors",
+  "sabre": "saber",
+  "sabres": "sabers",
+  "saltpetre": "saltpeter",
+  "sanitise": "sanitize",
+  "sanitised": "sanitized",
+  "sanitises": "sanitizes",
+  "sanitising": "sanitizing",
+  "satirise": "satirize",
+  "satirised": "satirized",
+  "satirises": "satirizes",
+  "satirising": "satirizing",
+  "saviour": "savior",
+  "saviours": "saviors",
+  "savour": "savor",
+  "savoured": "savored",
+  "savouries": "savories",
+  "savouring": "savoring",
+  "savours": "savors",
+  "savoury": "savory",
+  "scandalise": "scandalize",
+  "scandalised": "scandalized",
+  "scandalises": "scandalizes",
+  "scandalising": "scandalizing",
+  "sceptic": "skeptic",
+  "sceptical": "skeptical",
+  "sceptically": "skeptically",
+  "scepticism": "skepticism",
+  "sceptics": "skeptics",
+  "sceptre": "scepter",
+  "sceptres": "scepters",
+  "scrutinise": "scrutinize",
+  "scrutinised": "scrutinized",
+  "scrutinises": "scrutinizes",
+  "scrutinising": "scrutinizing",
+  "secularisation": "secularization",
+  "secularise": "secularize",
+  "secularised": "secularized",
+  "secularises": "secularizes",
+  "secularising": "secularizing",
+  "sensationalise": "sensationalize",
+  "sensationalised": "sensationalized",
+  "sensationalises": "sensationalizes",
+  "sensationalising": "sensationalizing",
+  "sensitise": "sensitize",
+  "sensitised": "sensitized",
+  "sensitises": "sensitizes",
+  "sensitising": "sensitizing",
+  "sentimentalise": "sentimentalize",
+  "sentimentalised": "sentimentalized",
+  "sentimentalises": "sentimentalizes",
+  "sentimentalising": "sentimentalizing",
+  "sepulchre": "sepulcher",
+  "sepulchres": "sepulchers",
+  "serialisation": "serialization",
+  "serialisations": "serializations",
+  "serialise": "serialize",
+  "serialised": "serialized",
+  "serialises": "serializes",
+  "serialising": "serializing",
+  "sermonise": "sermonize",
+  "sermonised": "sermonized",
+  "sermonises": "sermonizes",
+  "sermonising": "sermonizing",
+  "sheikh": "sheik",
+  "shovelled": "shoveled",
+  "shovelling": "shoveling",
+  "shrivelled": "shriveled",
+  "shrivelling": "shriveling",
+  "signalise": "signalize",
+  "signalised": "signalized",
+  "signalises": "signalizes",
+  "signalising": "signalizing",
+  "signalled": "signaled",
+  "signalling": "signaling",
+  "smoulder": "smolder",
+  "smouldered": "smoldered",
+  "smouldering": "smoldering",
+  "smoulders": "smolders",
+  "snivelled": "sniveled",
+  "snivelling": "sniveling",
+  "snorkelled": "snorkeled",
+  "snorkelling": "snorkeling",
+  "snowplough": "snowplow",
+  "snowploughs": "snowplow",
+  "socialisation": "socialization",
+  "socialise": "socialize",
+  "socialised": "socialized",
+  "socialises": "socializes",
+  "socialising": "socializing",
+  "sodomise": "sodomize",
+  "sodomised": "sodomized",
+  "sodomises": "sodomizes",
+  "sodomising": "sodomizing",
+  "solemnise": "solemnize",
+  "solemnised": "solemnized",
+  "solemnises": "solemnizes",
+  "solemnising": "solemnizing",
+  "sombre": "somber",
+  "specialisation": "specialization",
+  "specialisations": "specializations",
+  "specialise": "specialize",
+  "specialised": "specialized",
+  "specialises": "specializes",
+  "specialising": "specializing",
+  "spectre": "specter",
+  "spectres": "specters",
+  "spiralled": "spiraled",
+  "spiralling": "spiraling",
+  "splendour": "splendor",
+  "splendours": "splendors",
+  "squirrelled": "squirreled",
+  "squirrelling": "squirreling",
+  "stabilisation": "stabilization",
+  "stabilise": "stabilize",
+  "stabilised": "stabilized",
+  "stabiliser": "stabilizer",
+  "stabilisers": "stabilizers",
+  "stabilises": "stabilizes",
+  "stabilising": "stabilizing",
+  "standardisation": "standardization",
+  "standardise": "standardize",
+  "standardised": "standardized",
+  "standardises": "standardizes",
+  "standardising": "standardizing",
+  "stencilled": "stenciled",
+  "stencilling": "stenciling",
+  "sterilisation": "sterilization",
+  "sterilisations": "sterilizations",
+  "sterilise": "sterilize",
+  "sterilised": "sterilized",
+  "steriliser": "sterilizer",
+  "sterilisers": "sterilizers",
+  "sterilises": "sterilizes",
+  "sterilising": "sterilizing",
+  "stigmatisation": "stigmatization",
+  "stigmatise": "stigmatize",
+  "stigmatised": "stigmatized",
+  "stigmatises": "stigmatizes",
+  "stigmatising": "stigmatizing",
+  "storey": "story",
+  "storeys": "stories",
+  "subsidisation": "subsidization",
+  "subsidise": "subsidize",
+  "subsidised": "subsidized",
+  "subsidiser": "subsidizer",
+  "subsidisers": "subsidizers",
+  "subsidises": "subsidizes",
+  "subsidising": "subsidizing",
+  "succour": "succor",
+  "succoured": "succored",
+  "succouring": "succoring",
+  "succours": "succors",
+  "sulphate": "sulfate",
+  "sulphates": "sulfates",
+  "sulphide": "sulfide",
+  "sulphides": "sulfides",
+  "sulphur": "sulfur",
+  "sulphurous": "sulfurous",
+  "summarise": "summarize",
+  "summarised": "summarized",
+  "summarises": "summarizes",
+  "summarising": "summarizing",
+  "swivelled": "swiveled",
+  "swivelling": "swiveling",
+  "symbolise": "symbolize",
+  "symbolised": "symbolized",
+  "symbolises": "symbolizes",
+  "symbolising": "symbolizing",
+  "sympathise": "sympathize",
+  "sympathised": "sympathized",
+  "sympathiser": "sympathizer",
+  "sympathisers": "sympathizers",
+  "sympathises": "sympathizes",
+  "sympathising": "sympathizing",
+  "synchronisation": "synchronization",
+  "synchronise": "synchronize",
+  "synchronised": "synchronized",
+  "synchronises": "synchronizes",
+  "synchronising": "synchronizing",
+  "synthesise": "synthesize",
+  "synthesised": "synthesized",
+  "synthesiser": "synthesizer",
+  "synthesisers": "synthesizers",
+  "synthesises": "synthesizes",
+  "synthesising": "synthesizing",
+  "syphon": "siphon",
+  "syphoned": "siphoned",
+  "syphoning": "siphoning",
+  "syphons": "siphons",
+  "systematisation": "systematization",
+  "systematise": "systematize",
+  "systematised": "systematized",
+  "systematises": "systematizes",
+  "systematising": "systematizing",
+  "tantalise": "tantalize",
+  "tantalised": "tantalized",
+  "tantalises": "tantalizes",
+  "tantalising": "tantalizing",
+  "tantalisingly": "tantalizingly",
+  "tasselled": "tasseled",
+  "technicolour": "technicolor",
+  "temporise": "temporize",
+  "temporised": "temporized",
+  "temporises": "temporizes",
+  "temporising": "temporizing",
+  "tenderise": "tenderize",
+  "tenderised": "tenderized",
+  "tenderises": "tenderizes",
+  "tenderising": "tenderizing",
+  "terrorise": "terrorize",
+  "terrorised": "terrorized",
+  "terrorises": "terrorizes",
+  "terrorising": "terrorizing",
+  "theatre": "theater",
+  "theatregoer": "theatergoer",
+  "theatregoers": "theatergoers",
+  "theatres": "theaters",
+  "theorise": "theorize",
+  "theorised": "theorized",
+  "theorises": "theorizes",
+  "theorising": "theorizing",
+  "tonne": "ton",
+  "tonnes": "tons",
+  "towelled": "toweled",
+  "towelling": "toweling",
+  "toxaemia": "toxemia",
+  "tranquillise": "tranquilize",
+  "tranquillised": "tranquilized",
+  "tranquilliser": "tranquilizer",
+  "tranquillisers": "tranquilizers",
+  "tranquillises": "tranquilizes",
+  "tranquillising": "tranquilizing",
+  "tranquillity": "tranquility",
+  "tranquillize": "tranquilize",
+  "tranquillized": "tranquilized",
+  "tranquillizer": "tranquilizer",
+  "tranquillizers": "tranquilizers",
+  "tranquillizes": "tranquilizes",
+  "tranquillizing": "tranquilizing",
+  "tranquilly": "tranquility",
+  "transistorised": "transistorized",
+  "traumatise": "traumatize",
+  "traumatised": "traumatized",
+  "traumatises": "traumatizes",
+  "traumatising": "traumatizing",
+  "travelled": "traveled",
+  "traveller": "traveler",
+  "travellers": "travelers",
+  "travelling": "traveling",
+  "travelog": "travelogue",
+  "travelogs": "travelogues",
+  "trialled": "trialed",
+  "trialling": "trialing",
+  "tricolour": "tricolor",
+  "tricolours": "tricolors",
+  "trivialise": "trivialize",
+  "trivialised": "trivialized",
+  "trivialises": "trivializes",
+  "trivialising": "trivializing",
+  "tumour": "tumor",
+  "tumours": "tumors",
+  "tunnelled": "tunneled",
+  "tunnelling": "tunneling",
+  "tyrannise": "tyrannize",
+  "tyrannised": "tyrannized",
+  "tyrannises": "tyrannizes",
+  "tyrannising": "tyrannizing",
+  "tyre": "tire",
+  "tyres": "tires",
+  "unauthorised": "unauthorized",
+  "uncivilised": "uncivilized",
+  "underutilised": "underutilized",
+  "unequalled": "unequaled",
+  "unfavourable": "unfavorable",
+  "unfavourably": "unfavorably",
+  "unionisation": "unionization",
+  "unionise": "unionize",
+  "unionised": "unionized",
+  "unionises": "unionizes",
+  "unionising": "unionizing",
+  "unorganised": "unorganized",
+  "unravelled": "unraveled",
+  "unravelling": "unraveling",
+  "unrecognisable": "unrecognizable",
+  "unrecognised": "unrecognized",
+  "unrivalled": "unrivaled",
+  "unsavoury": "unsavory",
+  "untrammelled": "untrammeled",
+  "urbanisation": "urbanization",
+  "urbanise": "urbanize",
+  "urbanised": "urbanized",
+  "urbanises": "urbanizes",
+  "urbanising": "urbanizing",
+  "utilisable": "utilizable",
+  "utilisation": "utilization",
+  "utilise": "utilize",
+  "utilised": "utilized",
+  "utilises": "utilizes",
+  "utilising": "utilizing",
+  "valour": "valor",
+  "vandalise": "vandalize",
+  "vandalised": "vandalized",
+  "vandalises": "vandalizes",
+  "vandalising": "vandalizing",
+  "vaporisation": "vaporization",
+  "vaporise": "vaporize",
+  "vaporised": "vaporized",
+  "vaporises": "vaporizes",
+  "vaporising": "vaporizing",
+  "vapour": "vapor",
+  "vapours": "vapors",
+  "verbalise": "verbalize",
+  "verbalised": "verbalized",
+  "verbalises": "verbalizes",
+  "verbalising": "verbalizing",
+  "victimisation": "victimization",
+  "victimise": "victimize",
+  "victimised": "victimized",
+  "victimises": "victimizes",
+  "victimising": "victimizing",
+  "videodisc": "videodisk",
+  "videodiscs": "videodisks",
+  "vigour": "vigor",
+  "visualisation": "visualization",
+  "visualisations": "visualizations",
+  "visualise": "visualize",
+  "visualised": "visualized",
+  "visualises": "visualizes",
+  "visualising": "visualizing",
+  "vocalisation": "vocalization",
+  "vocalisations": "vocalizations",
+  "vocalise": "vocalize",
+  "vocalised": "vocalized",
+  "vocalises": "vocalizes",
+  "vocalising": "vocalizing",
+  "vulcanised": "vulcanized",
+  "vulgarisation": "vulgarization",
+  "vulgarise": "vulgarize",
+  "vulgarised": "vulgarized",
+  "vulgarises": "vulgarizes",
+  "vulgarising": "vulgarizing",
+  "waggon": "wagon",
+  "waggons": "wagons",
+  "watercolour": "watercolor",
+  "watercolours": "watercolors",
+  "weaselled": "weaseled",
+  "weaselling": "weaseling",
+  "westernisation": "westernization",
+  "westernise": "westernize",
+  "westernised": "westernized",
+  "westernises": "westernizes",
+  "westernising": "westernizing",
+  "womanise": "womanize",
+  "womanised": "womanized",
+  "womaniser": "womanizer",
+  "womanisers": "womanizers",
+  "womanises": "womanizes",
+  "womanising": "womanizing",
+  "woollen": "woolen",
+  "woollens": "woolens",
+  "woollies": "woolies",
+  "woolly": "wooly",
+  "worshipped": "worshiped",
+  "worshipper": "worshiper",
+  "worshipping": "worshiping",
+  "yodelled": "yodeled",
+  "yodelling": "yodeling",
+  "yoghourt": "yogurt",
+  "yoghourts": "yogurts",
+  "yoghurt": "yogurt",
+  "yoghurts": "yogurts"
+}

preprocessor_config.json

@@ -0,0 +1,26 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "MllamaImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_image_tiles": 4,
+  "processor_class": "MllamaProcessor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 560,
+    "width": 560
+  }
+}

processor_config.json

@@ -0,0 +1,10 @@
+{
+  "audio_padding": "longest",
+  "audio_placeholder": "<|audio|>",
+  "auto_map": {
+    "AutoProcessor": "bahasa_processing.BahasaProcessor"
+  },
+  "encoder_ds_factor": 320,
+  "processor_class": "BahasaProcessor",
+  "stack_factor": 8
+}

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|eot_id|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9816d43bd5347d64bccc66b7710947fb18e9818cc660215b1462061d4a44e449
+size 17210088

tokenizer_config.json

@@ -0,0 +1,2072 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|step_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128256": {
+      "content": "<|image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- if strftime_now is defined %}\n        {%- set date_string = strftime_now(\"%d %b %Y\") %}\n    {%- else %}\n        {%- set date_string = \"26 Jul 2024\" %}\n    {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- Find out if there are any images #}\n{% set image_ns = namespace(has_images=false) %}      \n{%- for message in messages %}\n    {%- if message['content'] is iterable and not message['content'] is string %}\n        {%- for content in message['content'] %}\n            {%- if content['type'] == 'image' %}\n                {%- set image_ns.has_images = true %}\n            {%- endif %}\n        {%- endfor %}\n    {%- endif %}\n{%- endfor %}\n\n{#- Always include system message, regardless of images #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n    {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n    {%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n    {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n' }}\n        {%- if message['content'] is string %}\n            {{- message['content'] }}\n        {%- else %}\n            {%- for content in message['content'] %}\n                {%- if content['type'] == 'image' %}\n                    {{- '<|image|>' }}\n                {%- elif content['type'] == 'text' %}\n                    {{- content['text'] }}\n                {%- endif %}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n        {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n        {{- '\"parameters\": ' }}\n        {{- tool_call.arguments | tojson }}\n        {{- \"}\" }}\n        {{- \"<|eot_id|>\" }}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|eot_id|>",
+  "processor_class": "MllamaProcessor",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}