Upload manifest.json with huggingface_hub

manifest.json

@@ -1,18 +1,18 @@
 {
   "encoder.embeddings.word_embeddings.weight": {
     "shape": [
-      32022,
+      32035,
       768
     ],
     "offset": 0,
-    "size": 24592896
+    "size": 24602880
   },
   "encoder.embeddings.position_embeddings.weight": {
     "shape": [
       512,
       768
     ],
-    "offset": 98371584,
+    "offset": 98411520,
     "size": 393216
   },
   "encoder.embeddings.token_type_embeddings.weight": {
@@ -20,21 +20,21 @@
       2,
       768
     ],
-    "offset": 99944448,
+    "offset": 99984384,
     "size": 1536
   },
   "encoder.embeddings.LayerNorm.weight": {
     "shape": [
       768
     ],
-    "offset": 99950592,
+    "offset": 99990528,
     "size": 768
   },
   "encoder.embeddings.LayerNorm.bias": {
     "shape": [
       768
     ],
-    "offset": 99953664,
+    "offset": 99993600,
     "size": 768
   },
   "encoder.encoder.layer.0.attention.self.query.weight": {
@@ -42,14 +42,14 @@
       768,
       768
     ],
-    "offset": 99956736,
+    "offset": 99996672,
     "size": 589824
   },
   "encoder.encoder.layer.0.attention.self.query.bias": {
     "shape": [
       768
     ],
-    "offset": 102316032,
+    "offset": 102355968,
     "size": 768
   },
   "encoder.encoder.layer.0.attention.self.key.weight": {
@@ -57,14 +57,14 @@
       768,
       768
     ],
-    "offset": 102319104,
+    "offset": 102359040,
     "size": 589824
   },
   "encoder.encoder.layer.0.attention.self.key.bias": {
     "shape": [
       768
     ],
-    "offset": 104678400,
+    "offset": 104718336,
     "size": 768
   },
   "encoder.encoder.layer.0.attention.self.value.weight": {
@@ -72,14 +72,14 @@
       768,
       768
     ],
-    "offset": 104681472,
+    "offset": 104721408,
     "size": 589824
   },
   "encoder.encoder.layer.0.attention.self.value.bias": {
     "shape": [
       768
     ],
-    "offset": 107040768,
+    "offset": 107080704,
     "size": 768
   },
   "encoder.encoder.layer.0.attention.output.dense.weight": {
@@ -87,28 +87,28 @@
       768,
       768
     ],
-    "offset": 107043840,
+    "offset": 107083776,
     "size": 589824
   },
   "encoder.encoder.layer.0.attention.output.dense.bias": {
     "shape": [
       768
     ],
-    "offset": 109403136,
+    "offset": 109443072,
     "size": 768
   },
   "encoder.encoder.layer.0.attention.output.LayerNorm.weight": {
     "shape": [
       768
     ],
-    "offset": 109406208,
+    "offset": 109446144,
     "size": 768
   },
   "encoder.encoder.layer.0.attention.output.LayerNorm.bias": {
     "shape": [
       768
     ],
-    "offset": 109409280,
+    "offset": 109449216,
     "size": 768
   },
   "encoder.encoder.layer.0.intermediate.dense.weight": {
@@ -116,14 +116,14 @@
       3072,
       768
     ],
-    "offset": 109412352,
+    "offset": 109452288,
     "size": 2359296
   },
   "encoder.encoder.layer.0.intermediate.dense.bias": {
     "shape": [
       3072
     ],
-    "offset": 118849536,
+    "offset": 118889472,
     "size": 3072
   },
   "encoder.encoder.layer.0.output.dense.weight": {
@@ -131,28 +131,28 @@
       768,
       3072
     ],
-    "offset": 118861824,
+    "offset": 118901760,
     "size": 2359296
   },
   "encoder.encoder.layer.0.output.dense.bias": {
     "shape": [
       768
     ],
-    "offset": 128299008,
+    "offset": 128338944,
     "size": 768
   },
   "encoder.encoder.layer.0.output.LayerNorm.weight": {
     "shape": [
       768
     ],
-    "offset": 128302080,
+    "offset": 128342016,
     "size": 768
   },
   "encoder.encoder.layer.0.output.LayerNorm.bias": {
     "shape": [
       768
     ],
-    "offset": 128305152,
+    "offset": 128345088,
     "size": 768
   },
   "encoder.encoder.layer.1.attention.self.query.weight": {
@@ -160,14 +160,14 @@
       768,
       768
     ],
-    "offset": 128308224,
+    "offset": 128348160,
     "size": 589824
   },
   "encoder.encoder.layer.1.attention.self.query.bias": {
     "shape": [
       768
     ],
-    "offset": 130667520,
+    "offset": 130707456,
     "size": 768
   },
   "encoder.encoder.layer.1.attention.self.key.weight": {
@@ -175,14 +175,14 @@
       768,
       768
     ],
-    "offset": 130670592,
+    "offset": 130710528,
     "size": 589824
   },
   "encoder.encoder.layer.1.attention.self.key.bias": {
     "shape": [
       768
     ],
-    "offset": 133029888,
+    "offset": 133069824,
     "size": 768
   },
   "encoder.encoder.layer.1.attention.self.value.weight": {
@@ -190,14 +190,14 @@
       768,
       768
     ],
-    "offset": 133032960,
+    "offset": 133072896,
     "size": 589824
   },
   "encoder.encoder.layer.1.attention.self.value.bias": {
     "shape": [
       768
     ],
-    "offset": 135392256,
+    "offset": 135432192,
     "size": 768
   },
   "encoder.encoder.layer.1.attention.output.dense.weight": {
@@ -205,28 +205,28 @@
       768,
       768
     ],
-    "offset": 135395328,
+    "offset": 135435264,
     "size": 589824
   },
   "encoder.encoder.layer.1.attention.output.dense.bias": {
     "shape": [
       768
     ],
-    "offset": 137754624,
+    "offset": 137794560,
     "size": 768
   },
   "encoder.encoder.layer.1.attention.output.LayerNorm.weight": {
     "shape": [
       768
     ],
-    "offset": 137757696,
+    "offset": 137797632,
     "size": 768
   },
   "encoder.encoder.layer.1.attention.output.LayerNorm.bias": {
     "shape": [
       768
     ],
-    "offset": 137760768,
+    "offset": 137800704,
     "size": 768
   },
   "encoder.encoder.layer.1.intermediate.dense.weight": {
@@ -234,14 +234,14 @@
       3072,
       768
     ],
-    "offset": 137763840,
+    "offset": 137803776,
     "size": 2359296
   },
   "encoder.encoder.layer.1.intermediate.dense.bias": {
     "shape": [
       3072
     ],
-    "offset": 147201024,
+    "offset": 147240960,
     "size": 3072
   },
   "encoder.encoder.layer.1.output.dense.weight": {
@@ -249,28 +249,28 @@
       768,
       3072
     ],
-    "offset": 147213312,
+    "offset": 147253248,
     "size": 2359296
   },
   "encoder.encoder.layer.1.output.dense.bias": {
     "shape": [
       768
     ],
-    "offset": 156650496,
+    "offset": 156690432,
     "size": 768
   },
   "encoder.encoder.layer.1.output.LayerNorm.weight": {
     "shape": [
       768
     ],
-    "offset": 156653568,
+    "offset": 156693504,
     "size": 768
   },
   "encoder.encoder.layer.1.output.LayerNorm.bias": {
     "shape": [
       768
     ],
-    "offset": 156656640,
+    "offset": 156696576,
     "size": 768
   },
   "encoder.encoder.layer.2.attention.self.query.weight": {
@@ -278,14 +278,14 @@
       768,
       768
     ],
-    "offset": 156659712,
+    "offset": 156699648,
     "size": 589824
   },
   "encoder.encoder.layer.2.attention.self.query.bias": {
     "shape": [
       768
     ],
-    "offset": 159019008,
+    "offset": 159058944,
     "size": 768
   },
   "encoder.encoder.layer.2.attention.self.key.weight": {
@@ -293,14 +293,14 @@
       768,
       768
     ],
-    "offset": 159022080,
+    "offset": 159062016,
     "size": 589824
   },
   "encoder.encoder.layer.2.attention.self.key.bias": {
     "shape": [
       768
     ],
-    "offset": 161381376,
+    "offset": 161421312,
     "size": 768
   },
   "encoder.encoder.layer.2.attention.self.value.weight": {
@@ -308,14 +308,14 @@
       768,
       768
     ],
-    "offset": 161384448,
+    "offset": 161424384,
     "size": 589824
   },
   "encoder.encoder.layer.2.attention.self.value.bias": {
     "shape": [
       768
     ],
-    "offset": 163743744,
+    "offset": 163783680,
     "size": 768
   },
   "encoder.encoder.layer.2.attention.output.dense.weight": {
@@ -323,28 +323,28 @@
       768,
       768
     ],
-    "offset": 163746816,
+    "offset": 163786752,
     "size": 589824
   },
   "encoder.encoder.layer.2.attention.output.dense.bias": {
     "shape": [
       768
     ],
-    "offset": 166106112,
+    "offset": 166146048,
     "size": 768
   },
   "encoder.encoder.layer.2.attention.output.LayerNorm.weight": {
     "shape": [
       768
     ],
-    "offset": 166109184,
+    "offset": 166149120,
     "size": 768
   },
   "encoder.encoder.layer.2.attention.output.LayerNorm.bias": {
     "shape": [
       768
     ],
-    "offset": 166112256,
+    "offset": 166152192,
     "size": 768
   },
   "encoder.encoder.layer.2.intermediate.dense.weight": {
@@ -352,14 +352,14 @@
       3072,
       768
     ],
-    "offset": 166115328,
+    "offset": 166155264,
     "size": 2359296
   },
   "encoder.encoder.layer.2.intermediate.dense.bias": {
     "shape": [
       3072
     ],
-    "offset": 175552512,
+    "offset": 175592448,
     "size": 3072
   },
   "encoder.encoder.layer.2.output.dense.weight": {
@@ -367,28 +367,28 @@
       768,
       3072
     ],
-    "offset": 175564800,
+    "offset": 175604736,
     "size": 2359296
   },
   "encoder.encoder.layer.2.output.dense.bias": {
     "shape": [
       768
     ],
-    "offset": 185001984,
+    "offset": 185041920,
     "size": 768
   },
   "encoder.encoder.layer.2.output.LayerNorm.weight": {
     "shape": [
       768
     ],
-    "offset": 185005056,
+    "offset": 185044992,
     "size": 768
   },
   "encoder.encoder.layer.2.output.LayerNorm.bias": {
     "shape": [
       768
     ],
-    "offset": 185008128,
+    "offset": 185048064,
     "size": 768
   },
   "encoder.encoder.layer.3.attention.self.query.weight": {
@@ -396,14 +396,14 @@
       768,
       768
     ],
-    "offset": 185011200,
+    "offset": 185051136,
     "size": 589824
   },
   "encoder.encoder.layer.3.attention.self.query.bias": {
     "shape": [
       768
     ],
-    "offset": 187370496,
+    "offset": 187410432,
     "size": 768
   },
   "encoder.encoder.layer.3.attention.self.key.weight": {
@@ -411,14 +411,14 @@
       768,
       768
     ],
-    "offset": 187373568,
+    "offset": 187413504,
     "size": 589824
   },
   "encoder.encoder.layer.3.attention.self.key.bias": {
     "shape": [
       768
     ],
-    "offset": 189732864,
+    "offset": 189772800,
     "size": 768
   },
   "encoder.encoder.layer.3.attention.self.value.weight": {
@@ -426,14 +426,14 @@
       768,
       768
     ],
-    "offset": 189735936,
+    "offset": 189775872,
     "size": 589824
   },
   "encoder.encoder.layer.3.attention.self.value.bias": {
     "shape": [
       768
     ],
-    "offset": 192095232,
+    "offset": 192135168,
     "size": 768
   },
   "encoder.encoder.layer.3.attention.output.dense.weight": {
@@ -441,28 +441,28 @@
       768,
       768
     ],
-    "offset": 192098304,
+    "offset": 192138240,
     "size": 589824
   },
   "encoder.encoder.layer.3.attention.output.dense.bias": {
     "shape": [
       768
     ],
-    "offset": 194457600,
+    "offset": 194497536,
     "size": 768
   },
   "encoder.encoder.layer.3.attention.output.LayerNorm.weight": {
     "shape": [
       768
     ],
-    "offset": 194460672,
+    "offset": 194500608,
     "size": 768
   },
   "encoder.encoder.layer.3.attention.output.LayerNorm.bias": {
     "shape": [
       768
     ],
-    "offset": 194463744,
+    "offset": 194503680,
     "size": 768
   },
   "encoder.encoder.layer.3.intermediate.dense.weight": {
@@ -470,14 +470,14 @@
       3072,
       768
     ],
-    "offset": 194466816,
+    "offset": 194506752,
     "size": 2359296
   },
   "encoder.encoder.layer.3.intermediate.dense.bias": {
     "shape": [
       3072
     ],
-    "offset": 203904000,
+    "offset": 203943936,
     "size": 3072
   },
   "encoder.encoder.layer.3.output.dense.weight": {
@@ -485,28 +485,28 @@
       768,
       3072
     ],
-    "offset": 203916288,
+    "offset": 203956224,
     "size": 2359296
   },
   "encoder.encoder.layer.3.output.dense.bias": {
     "shape": [
       768
     ],
-    "offset": 213353472,
+    "offset": 213393408,
     "size": 768
   },
   "encoder.encoder.layer.3.output.LayerNorm.weight": {
     "shape": [
       768
     ],
-    "offset": 213356544,
+    "offset": 213396480,
     "size": 768
   },
   "encoder.encoder.layer.3.output.LayerNorm.bias": {
     "shape": [
       768
     ],
-    "offset": 213359616,
+    "offset": 213399552,
     "size": 768
   },
   "encoder.encoder.layer.4.attention.self.query.weight": {
@@ -514,14 +514,14 @@
       768,
       768
     ],
-    "offset": 213362688,
+    "offset": 213402624,
     "size": 589824
   },
   "encoder.encoder.layer.4.attention.self.query.bias": {
     "shape": [
       768
     ],
-    "offset": 215721984,
+    "offset": 215761920,
     "size": 768
   },
   "encoder.encoder.layer.4.attention.self.key.weight": {
@@ -529,14 +529,14 @@
       768,
       768
     ],
-    "offset": 215725056,
+    "offset": 215764992,
     "size": 589824
   },
   "encoder.encoder.layer.4.attention.self.key.bias": {
     "shape": [
       768
     ],
-    "offset": 218084352,
+    "offset": 218124288,
     "size": 768
   },
   "encoder.encoder.layer.4.attention.self.value.weight": {
@@ -544,14 +544,14 @@
       768,
       768
     ],
-    "offset": 218087424,
+    "offset": 218127360,
     "size": 589824
   },
   "encoder.encoder.layer.4.attention.self.value.bias": {
     "shape": [
       768
     ],
-    "offset": 220446720,
+    "offset": 220486656,
     "size": 768
   },
   "encoder.encoder.layer.4.attention.output.dense.weight": {
@@ -559,28 +559,28 @@
       768,
       768
     ],
-    "offset": 220449792,
+    "offset": 220489728,
     "size": 589824
   },
   "encoder.encoder.layer.4.attention.output.dense.bias": {
     "shape": [
       768
     ],
-    "offset": 222809088,
+    "offset": 222849024,
     "size": 768
   },
   "encoder.encoder.layer.4.attention.output.LayerNorm.weight": {
     "shape": [
       768
     ],
-    "offset": 222812160,
+    "offset": 222852096,
     "size": 768
   },
   "encoder.encoder.layer.4.attention.output.LayerNorm.bias": {
     "shape": [
       768
     ],
-    "offset": 222815232,
+    "offset": 222855168,
     "size": 768
   },
   "encoder.encoder.layer.4.intermediate.dense.weight": {
@@ -588,14 +588,14 @@
       3072,
       768
     ],
-    "offset": 222818304,
+    "offset": 222858240,
     "size": 2359296
   },
   "encoder.encoder.layer.4.intermediate.dense.bias": {
     "shape": [
       3072
     ],
-    "offset": 232255488,
+    "offset": 232295424,
     "size": 3072
   },
   "encoder.encoder.layer.4.output.dense.weight": {
@@ -603,28 +603,28 @@
       768,
       3072
     ],
-    "offset": 232267776,
+    "offset": 232307712,
     "size": 2359296
   },
   "encoder.encoder.layer.4.output.dense.bias": {
     "shape": [
       768
     ],
-    "offset": 241704960,
+    "offset": 241744896,
     "size": 768
   },
   "encoder.encoder.layer.4.output.LayerNorm.weight": {
     "shape": [
       768
     ],
-    "offset": 241708032,
+    "offset": 241747968,
     "size": 768
   },
   "encoder.encoder.layer.4.output.LayerNorm.bias": {
     "shape": [
       768
     ],
-    "offset": 241711104,
+    "offset": 241751040,
     "size": 768
   },
   "encoder.encoder.layer.5.attention.self.query.weight": {
@@ -632,14 +632,14 @@
       768,
       768
     ],
-    "offset": 241714176,
+    "offset": 241754112,
     "size": 589824
   },
   "encoder.encoder.layer.5.attention.self.query.bias": {
     "shape": [
       768
     ],
-    "offset": 244073472,
+    "offset": 244113408,
     "size": 768
   },
   "encoder.encoder.layer.5.attention.self.key.weight": {
@@ -647,14 +647,14 @@
       768,
       768
     ],
-    "offset": 244076544,
+    "offset": 244116480,
     "size": 589824
   },
   "encoder.encoder.layer.5.attention.self.key.bias": {
     "shape": [
       768
     ],
-    "offset": 246435840,
+    "offset": 246475776,
     "size": 768
   },
   "encoder.encoder.layer.5.attention.self.value.weight": {
@@ -662,14 +662,14 @@
       768,
       768
     ],
-    "offset": 246438912,
+    "offset": 246478848,
     "size": 589824
   },
   "encoder.encoder.layer.5.attention.self.value.bias": {
     "shape": [
       768
     ],
-    "offset": 248798208,
+    "offset": 248838144,
     "size": 768
   },
   "encoder.encoder.layer.5.attention.output.dense.weight": {
@@ -677,28 +677,28 @@
       768,
       768
     ],
-    "offset": 248801280,
+    "offset": 248841216,
     "size": 589824
   },
   "encoder.encoder.layer.5.attention.output.dense.bias": {
     "shape": [
       768
     ],
-    "offset": 251160576,
+    "offset": 251200512,
     "size": 768
   },
   "encoder.encoder.layer.5.attention.output.LayerNorm.weight": {
     "shape": [
       768
     ],
-    "offset": 251163648,
+    "offset": 251203584,
     "size": 768
   },
   "encoder.encoder.layer.5.attention.output.LayerNorm.bias": {
     "shape": [
       768
     ],
-    "offset": 251166720,
+    "offset": 251206656,
     "size": 768
   },
   "encoder.encoder.layer.5.intermediate.dense.weight": {
@@ -706,14 +706,14 @@
       3072,
       768
     ],
-    "offset": 251169792,
+    "offset": 251209728,
     "size": 2359296
   },
   "encoder.encoder.layer.5.intermediate.dense.bias": {
     "shape": [
       3072
     ],
-    "offset": 260606976,
+    "offset": 260646912,
     "size": 3072
   },
   "encoder.encoder.layer.5.output.dense.weight": {
@@ -721,28 +721,28 @@
       768,
       3072
     ],
-    "offset": 260619264,
+    "offset": 260659200,
     "size": 2359296
   },
   "encoder.encoder.layer.5.output.dense.bias": {
     "shape": [
       768
     ],
-    "offset": 270056448,
+    "offset": 270096384,
     "size": 768
   },
   "encoder.encoder.layer.5.output.LayerNorm.weight": {
     "shape": [
       768
     ],
-    "offset": 270059520,
+    "offset": 270099456,
     "size": 768
   },
   "encoder.encoder.layer.5.output.LayerNorm.bias": {
     "shape": [
       768
     ],
-    "offset": 270062592,
+    "offset": 270102528,
     "size": 768
   },
   "encoder.encoder.layer.6.attention.self.query.weight": {
@@ -750,14 +750,14 @@
       768,
       768
     ],
-    "offset": 270065664,
+    "offset": 270105600,
     "size": 589824
   },
   "encoder.encoder.layer.6.attention.self.query.bias": {
     "shape": [
       768
     ],
-    "offset": 272424960,
+    "offset": 272464896,
     "size": 768
   },
   "encoder.encoder.layer.6.attention.self.key.weight": {
@@ -765,14 +765,14 @@
       768,
       768
     ],
-    "offset": 272428032,
+    "offset": 272467968,
     "size": 589824
   },
   "encoder.encoder.layer.6.attention.self.key.bias": {
     "shape": [
       768
     ],
-    "offset": 274787328,
+    "offset": 274827264,
     "size": 768
   },
   "encoder.encoder.layer.6.attention.self.value.weight": {
@@ -780,14 +780,14 @@
       768,
       768
     ],
-    "offset": 274790400,
+    "offset": 274830336,
     "size": 589824
   },
   "encoder.encoder.layer.6.attention.self.value.bias": {
     "shape": [
       768
     ],
-    "offset": 277149696,
+    "offset": 277189632,
     "size": 768
   },
   "encoder.encoder.layer.6.attention.output.dense.weight": {
@@ -795,28 +795,28 @@
       768,
       768
     ],
-    "offset": 277152768,
+    "offset": 277192704,
     "size": 589824
   },
   "encoder.encoder.layer.6.attention.output.dense.bias": {
     "shape": [
       768
     ],
-    "offset": 279512064,
+    "offset": 279552000,
     "size": 768
   },
   "encoder.encoder.layer.6.attention.output.LayerNorm.weight": {
     "shape": [
       768
     ],
-    "offset": 279515136,
+    "offset": 279555072,
     "size": 768
   },
   "encoder.encoder.layer.6.attention.output.LayerNorm.bias": {
     "shape": [
       768
     ],
-    "offset": 279518208,
+    "offset": 279558144,
     "size": 768
   },
   "encoder.encoder.layer.6.intermediate.dense.weight": {
@@ -824,14 +824,14 @@
       3072,
       768
     ],
-    "offset": 279521280,
+    "offset": 279561216,
     "size": 2359296
   },
   "encoder.encoder.layer.6.intermediate.dense.bias": {
     "shape": [
       3072
     ],
-    "offset": 288958464,
+    "offset": 288998400,
     "size": 3072
   },
   "encoder.encoder.layer.6.output.dense.weight": {
@@ -839,28 +839,28 @@
       768,
       3072
     ],
-    "offset": 288970752,
+    "offset": 289010688,
     "size": 2359296
   },
   "encoder.encoder.layer.6.output.dense.bias": {
     "shape": [
       768
     ],
-    "offset": 298407936,
+    "offset": 298447872,
     "size": 768
   },
   "encoder.encoder.layer.6.output.LayerNorm.weight": {
     "shape": [
       768
     ],
-    "offset": 298411008,
+    "offset": 298450944,
     "size": 768
   },
   "encoder.encoder.layer.6.output.LayerNorm.bias": {
     "shape": [
       768
     ],
-    "offset": 298414080,
+    "offset": 298454016,
     "size": 768
   },
   "encoder.encoder.layer.7.attention.self.query.weight": {
@@ -868,14 +868,14 @@
       768,
       768
     ],
-    "offset": 298417152,
+    "offset": 298457088,
     "size": 589824
   },
   "encoder.encoder.layer.7.attention.self.query.bias": {
     "shape": [
       768
     ],
-    "offset": 300776448,
+    "offset": 300816384,
     "size": 768
   },
   "encoder.encoder.layer.7.attention.self.key.weight": {
@@ -883,14 +883,14 @@
       768,
       768
     ],
-    "offset": 300779520,
+    "offset": 300819456,
     "size": 589824
   },
   "encoder.encoder.layer.7.attention.self.key.bias": {
     "shape": [
       768
     ],
-    "offset": 303138816,
+    "offset": 303178752,
     "size": 768
   },
   "encoder.encoder.layer.7.attention.self.value.weight": {
@@ -898,14 +898,14 @@
       768,
       768
     ],
-    "offset": 303141888,
+    "offset": 303181824,
     "size": 589824
   },
   "encoder.encoder.layer.7.attention.self.value.bias": {
     "shape": [
       768
     ],
-    "offset": 305501184,
+    "offset": 305541120,
     "size": 768
   },
   "encoder.encoder.layer.7.attention.output.dense.weight": {
@@ -913,28 +913,28 @@
       768,
       768
     ],
-    "offset": 305504256,
+    "offset": 305544192,
     "size": 589824
   },
   "encoder.encoder.layer.7.attention.output.dense.bias": {
     "shape": [
       768
     ],
-    "offset": 307863552,
+    "offset": 307903488,
     "size": 768
   },
   "encoder.encoder.layer.7.attention.output.LayerNorm.weight": {
     "shape": [
       768
     ],
-    "offset": 307866624,
+    "offset": 307906560,
     "size": 768
   },
   "encoder.encoder.layer.7.attention.output.LayerNorm.bias": {
     "shape": [
       768
     ],
-    "offset": 307869696,
+    "offset": 307909632,
     "size": 768
   },
   "encoder.encoder.layer.7.intermediate.dense.weight": {
@@ -942,14 +942,14 @@
       3072,
       768
     ],
-    "offset": 307872768,
+    "offset": 307912704,
     "size": 2359296
   },
   "encoder.encoder.layer.7.intermediate.dense.bias": {
     "shape": [
       3072
     ],
-    "offset": 317309952,
+    "offset": 317349888,
     "size": 3072
   },
   "encoder.encoder.layer.7.output.dense.weight": {
@@ -957,28 +957,28 @@
       768,
       3072
     ],
-    "offset": 317322240,
+    "offset": 317362176,
     "size": 2359296
   },
   "encoder.encoder.layer.7.output.dense.bias": {
     "shape": [
       768
     ],
-    "offset": 326759424,
+    "offset": 326799360,
     "size": 768
   },
   "encoder.encoder.layer.7.output.LayerNorm.weight": {
     "shape": [
       768
     ],
-    "offset": 326762496,
+    "offset": 326802432,
     "size": 768
   },
   "encoder.encoder.layer.7.output.LayerNorm.bias": {
     "shape": [
       768
     ],
-    "offset": 326765568,
+    "offset": 326805504,
     "size": 768
   },
   "encoder.encoder.layer.8.attention.self.query.weight": {
@@ -986,14 +986,14 @@
       768,
       768
     ],
-    "offset": 326768640,
+    "offset": 326808576,
     "size": 589824
   },
   "encoder.encoder.layer.8.attention.self.query.bias": {
     "shape": [
       768
     ],
-    "offset": 329127936,
+    "offset": 329167872,
     "size": 768
   },
   "encoder.encoder.layer.8.attention.self.key.weight": {
@@ -1001,14 +1001,14 @@
       768,
       768
     ],
-    "offset": 329131008,
+    "offset": 329170944,
     "size": 589824
   },
   "encoder.encoder.layer.8.attention.self.key.bias": {
     "shape": [
       768
     ],
-    "offset": 331490304,
+    "offset": 331530240,
     "size": 768
   },
   "encoder.encoder.layer.8.attention.self.value.weight": {
@@ -1016,14 +1016,14 @@
       768,
       768
     ],
-    "offset": 331493376,
+    "offset": 331533312,
     "size": 589824
   },
   "encoder.encoder.layer.8.attention.self.value.bias": {
     "shape": [
       768
     ],
-    "offset": 333852672,
+    "offset": 333892608,
     "size": 768
   },
   "encoder.encoder.layer.8.attention.output.dense.weight": {
@@ -1031,28 +1031,28 @@
       768,
       768
     ],
-    "offset": 333855744,
+    "offset": 333895680,
     "size": 589824
   },
   "encoder.encoder.layer.8.attention.output.dense.bias": {
     "shape": [
       768
     ],
-    "offset": 336215040,
+    "offset": 336254976,
     "size": 768
   },
   "encoder.encoder.layer.8.attention.output.LayerNorm.weight": {
     "shape": [
       768
     ],
-    "offset": 336218112,
+    "offset": 336258048,
     "size": 768
   },
   "encoder.encoder.layer.8.attention.output.LayerNorm.bias": {
     "shape": [
       768
     ],
-    "offset": 336221184,
+    "offset": 336261120,
     "size": 768
   },
   "encoder.encoder.layer.8.intermediate.dense.weight": {
@@ -1060,14 +1060,14 @@
       3072,
       768
     ],
-    "offset": 336224256,
+    "offset": 336264192,
     "size": 2359296
   },
   "encoder.encoder.layer.8.intermediate.dense.bias": {
     "shape": [
       3072
     ],
-    "offset": 345661440,
+    "offset": 345701376,
     "size": 3072
   },
   "encoder.encoder.layer.8.output.dense.weight": {
@@ -1075,28 +1075,28 @@
       768,
       3072
     ],
-    "offset": 345673728,
+    "offset": 345713664,
     "size": 2359296
   },
   "encoder.encoder.layer.8.output.dense.bias": {
     "shape": [
       768
     ],
-    "offset": 355110912,
+    "offset": 355150848,
     "size": 768
   },
   "encoder.encoder.layer.8.output.LayerNorm.weight": {
     "shape": [
       768
     ],
-    "offset": 355113984,
+    "offset": 355153920,
     "size": 768
   },
   "encoder.encoder.layer.8.output.LayerNorm.bias": {
     "shape": [
       768
     ],
-    "offset": 355117056,
+    "offset": 355156992,
     "size": 768
   },
   "encoder.encoder.layer.9.attention.self.query.weight": {
@@ -1104,14 +1104,14 @@
       768,
       768
     ],
-    "offset": 355120128,
+    "offset": 355160064,
     "size": 589824
   },
   "encoder.encoder.layer.9.attention.self.query.bias": {
     "shape": [
       768
     ],
-    "offset": 357479424,
+    "offset": 357519360,
     "size": 768
   },
   "encoder.encoder.layer.9.attention.self.key.weight": {
@@ -1119,14 +1119,14 @@
       768,
       768
     ],
-    "offset": 357482496,
+    "offset": 357522432,
     "size": 589824
   },
   "encoder.encoder.layer.9.attention.self.key.bias": {
     "shape": [
       768
     ],
-    "offset": 359841792,
+    "offset": 359881728,
     "size": 768
   },
   "encoder.encoder.layer.9.attention.self.value.weight": {
@@ -1134,14 +1134,14 @@
       768,
       768
     ],
-    "offset": 359844864,
+    "offset": 359884800,
     "size": 589824
   },
   "encoder.encoder.layer.9.attention.self.value.bias": {
     "shape": [
       768
     ],
-    "offset": 362204160,
+    "offset": 362244096,
     "size": 768
   },
   "encoder.encoder.layer.9.attention.output.dense.weight": {
@@ -1149,28 +1149,28 @@
       768,
       768
     ],
-    "offset": 362207232,
+    "offset": 362247168,
     "size": 589824
   },
   "encoder.encoder.layer.9.attention.output.dense.bias": {
     "shape": [
       768
     ],
-    "offset": 364566528,
+    "offset": 364606464,
     "size": 768
   },
   "encoder.encoder.layer.9.attention.output.LayerNorm.weight": {
     "shape": [
       768
     ],
-    "offset": 364569600,
+    "offset": 364609536,
     "size": 768
   },
   "encoder.encoder.layer.9.attention.output.LayerNorm.bias": {
     "shape": [
       768
     ],
-    "offset": 364572672,
+    "offset": 364612608,
     "size": 768
   },
   "encoder.encoder.layer.9.intermediate.dense.weight": {
@@ -1178,14 +1178,14 @@
       3072,
       768
     ],
-    "offset": 364575744,
+    "offset": 364615680,
     "size": 2359296
   },
   "encoder.encoder.layer.9.intermediate.dense.bias": {
     "shape": [
       3072
     ],
-    "offset": 374012928,
+    "offset": 374052864,
     "size": 3072
   },
   "encoder.encoder.layer.9.output.dense.weight": {
@@ -1193,28 +1193,28 @@
       768,
       3072
     ],
-    "offset": 374025216,
+    "offset": 374065152,
     "size": 2359296
   },
   "encoder.encoder.layer.9.output.dense.bias": {
     "shape": [
       768
     ],
-    "offset": 383462400,
+    "offset": 383502336,
     "size": 768
   },
   "encoder.encoder.layer.9.output.LayerNorm.weight": {
     "shape": [
       768
     ],
-    "offset": 383465472,
+    "offset": 383505408,
     "size": 768
   },
   "encoder.encoder.layer.9.output.LayerNorm.bias": {
     "shape": [
       768
     ],
-    "offset": 383468544,
+    "offset": 383508480,
     "size": 768
   },
   "encoder.encoder.layer.10.attention.self.query.weight": {
@@ -1222,14 +1222,14 @@
       768,
       768
     ],
-    "offset": 383471616,
+    "offset": 383511552,
     "size": 589824
   },
   "encoder.encoder.layer.10.attention.self.query.bias": {
     "shape": [
       768
     ],
-    "offset": 385830912,
+    "offset": 385870848,
     "size": 768
   },
   "encoder.encoder.layer.10.attention.self.key.weight": {
@@ -1237,14 +1237,14 @@
       768,
       768
     ],
-    "offset": 385833984,
+    "offset": 385873920,
     "size": 589824
   },
   "encoder.encoder.layer.10.attention.self.key.bias": {
     "shape": [
       768
     ],
-    "offset": 388193280,
+    "offset": 388233216,
     "size": 768
   },
   "encoder.encoder.layer.10.attention.self.value.weight": {
@@ -1252,14 +1252,14 @@
       768,
       768
     ],
-    "offset": 388196352,
+    "offset": 388236288,
     "size": 589824
   },
   "encoder.encoder.layer.10.attention.self.value.bias": {
     "shape": [
       768
     ],
-    "offset": 390555648,
+    "offset": 390595584,
     "size": 768
   },
   "encoder.encoder.layer.10.attention.output.dense.weight": {
@@ -1267,28 +1267,28 @@
       768,
       768
     ],
-    "offset": 390558720,
+    "offset": 390598656,
     "size": 589824
   },
   "encoder.encoder.layer.10.attention.output.dense.bias": {
     "shape": [
       768
     ],
-    "offset": 392918016,
+    "offset": 392957952,
     "size": 768
   },
   "encoder.encoder.layer.10.attention.output.LayerNorm.weight": {
     "shape": [
       768
     ],
-    "offset": 392921088,
+    "offset": 392961024,
     "size": 768
   },
   "encoder.encoder.layer.10.attention.output.LayerNorm.bias": {
     "shape": [
       768
     ],
-    "offset": 392924160,
+    "offset": 392964096,
     "size": 768
   },
   "encoder.encoder.layer.10.intermediate.dense.weight": {
@@ -1296,14 +1296,14 @@
       3072,
       768
     ],
-    "offset": 392927232,
+    "offset": 392967168,
     "size": 2359296
   },
   "encoder.encoder.layer.10.intermediate.dense.bias": {
     "shape": [
       3072
     ],
-    "offset": 402364416,
+    "offset": 402404352,
     "size": 3072
   },
   "encoder.encoder.layer.10.output.dense.weight": {
@@ -1311,28 +1311,28 @@
       768,
       3072
     ],
-    "offset": 402376704,
+    "offset": 402416640,
     "size": 2359296
   },
   "encoder.encoder.layer.10.output.dense.bias": {
     "shape": [
       768
     ],
-    "offset": 411813888,
+    "offset": 411853824,
     "size": 768
   },
   "encoder.encoder.layer.10.output.LayerNorm.weight": {
     "shape": [
       768
     ],
-    "offset": 411816960,
+    "offset": 411856896,
     "size": 768
   },
   "encoder.encoder.layer.10.output.LayerNorm.bias": {
     "shape": [
       768
     ],
-    "offset": 411820032,
+    "offset": 411859968,
     "size": 768
   },
   "encoder.encoder.layer.11.attention.self.query.weight": {
@@ -1340,14 +1340,14 @@
       768,
       768
     ],
-    "offset": 411823104,
+    "offset": 411863040,
     "size": 589824
   },
   "encoder.encoder.layer.11.attention.self.query.bias": {
     "shape": [
       768
     ],
-    "offset": 414182400,
+    "offset": 414222336,
     "size": 768
   },
   "encoder.encoder.layer.11.attention.self.key.weight": {
@@ -1355,14 +1355,14 @@
       768,
       768
     ],
-    "offset": 414185472,
+    "offset": 414225408,
     "size": 589824
   },
   "encoder.encoder.layer.11.attention.self.key.bias": {
     "shape": [
       768
     ],
-    "offset": 416544768,
+    "offset": 416584704,
     "size": 768
   },
   "encoder.encoder.layer.11.attention.self.value.weight": {
@@ -1370,14 +1370,14 @@
       768,
       768
     ],
-    "offset": 416547840,
+    "offset": 416587776,
     "size": 589824
   },
   "encoder.encoder.layer.11.attention.self.value.bias": {
     "shape": [
       768
     ],
-    "offset": 418907136,
+    "offset": 418947072,
     "size": 768
   },
   "encoder.encoder.layer.11.attention.output.dense.weight": {
@@ -1385,28 +1385,28 @@
       768,
       768
     ],
-    "offset": 418910208,
+    "offset": 418950144,
     "size": 589824
   },
   "encoder.encoder.layer.11.attention.output.dense.bias": {
     "shape": [
       768
     ],
-    "offset": 421269504,
+    "offset": 421309440,
     "size": 768
   },
   "encoder.encoder.layer.11.attention.output.LayerNorm.weight": {
     "shape": [
       768
     ],
-    "offset": 421272576,
+    "offset": 421312512,
     "size": 768
   },
   "encoder.encoder.layer.11.attention.output.LayerNorm.bias": {
     "shape": [
       768
     ],
-    "offset": 421275648,
+    "offset": 421315584,
     "size": 768
   },
   "encoder.encoder.layer.11.intermediate.dense.weight": {
@@ -1414,14 +1414,14 @@
       3072,
       768
     ],
-    "offset": 421278720,
+    "offset": 421318656,
     "size": 2359296
   },
   "encoder.encoder.layer.11.intermediate.dense.bias": {
     "shape": [
       3072
     ],
-    "offset": 430715904,
+    "offset": 430755840,
     "size": 3072
   },
   "encoder.encoder.layer.11.output.dense.weight": {
@@ -1429,28 +1429,28 @@
       768,
       3072
     ],
-    "offset": 430728192,
+    "offset": 430768128,
     "size": 2359296
   },
   "encoder.encoder.layer.11.output.dense.bias": {
     "shape": [
       768
     ],
-    "offset": 440165376,
+    "offset": 440205312,
     "size": 768
   },
   "encoder.encoder.layer.11.output.LayerNorm.weight": {
     "shape": [
       768
     ],
-    "offset": 440168448,
+    "offset": 440208384,
     "size": 768
   },
   "encoder.encoder.layer.11.output.LayerNorm.bias": {
     "shape": [
       768
     ],
-    "offset": 440171520,
+    "offset": 440211456,
     "size": 768
   },
   "encoder.pooler.dense.weight": {
@@ -1458,14 +1458,14 @@
       768,
       768
     ],
-    "offset": 440174592,
+    "offset": 440214528,
     "size": 589824
   },
   "encoder.pooler.dense.bias": {
     "shape": [
       768
     ],
-    "offset": 442533888,
+    "offset": 442573824,
     "size": 768
   },
   "classifier.1.weight": {
@@ -1473,29 +1473,29 @@
       256,
       768
     ],
-    "offset": 442536960,
+    "offset": 442576896,
     "size": 196608
   },
   "classifier.1.bias": {
     "shape": [
       256
     ],
-    "offset": 443323392,
+    "offset": 443363328,
     "size": 256
   },
   "classifier.4.weight": {
     "shape": [
-      15,
+      11,
       256
     ],
-    "offset": 443324416,
-    "size": 3840
+    "offset": 443364352,
+    "size": 2816
   },
   "classifier.4.bias": {
     "shape": [
-      15
+      11
     ],
-    "offset": 443339776,
-    "size": 15
+    "offset": 443375616,
+    "size": 11
   }
 }