Update spaCy pipeline

.gitattributes

@@ -32,3 +32,6 @@ 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
+xx_pipeline-any-py3-none-any.whl filter=lfs diff=lfs merge=lfs -text
+vocab/strings.json filter=lfs diff=lfs merge=lfs -text
+transformer/model filter=lfs diff=lfs merge=lfs -text

.ipynb_checkpoints/XX-LeetSpeakNER-paraphrase-multilingual-mpnet-base-v2_test_IT-checkpoint.csv

@@ -0,0 +1,6 @@
+Model,Dataset,lang,P-INV_CAM,R-INV_CAM,F1-INV_CAM,TP-INV_CAM,FN-INV_CAM,FP-INV_CAM,P-LEETSPEAK,R-LEETSPEAK,F1-LEETSPEAK,TP-LEETSPEAK,FN-LEETSPEAK,FP-LEETSPEAK,P-MIX,R-MIX,F1-MIX,TP-MIX,FN-MIX,FP-MIX,P-O,R-O,F1-O,TP-O,FN-O,FP-O,P-PUNCT_CAM,R-PUNCT_CAM,F1-PUNCT_CAM,TP-PUNCT_CAM,FN-PUNCT_CAM,FP-PUNCT_CAM,F1-Macro,F1-Micro,F1-Weighted
+XX-LeetSpeakNER-paraphrase-multilingual-mpnet-base-v2,overall,IT,0.9056304520222046,0.9217110573042776,0.9136,1142,119,97,0.9893648018648019,0.976279470960322,0.9827785817655571,6791,73,165,0.9748310810810811,0.8860740058344849,0.9283358803185072,5771,149,742,0.9983891261247522,0.9980942035200061,0.9982416430392413,104743,169,200,0.8497516556291391,0.9922667955534075,0.9154960981047937,4106,726,32,0.9476904406456198,0.990015267915566,0.8958518228704071
+XX-LeetSpeakNER-paraphrase-multilingual-mpnet-base-v2,WikiMatrix,IT,0.9264305177111717,0.947075208913649,0.9366391184573003,340,27,19,0.9895201323772752,0.980327868852459,0.984902552841065,1794,19,36,0.9759181216134859,0.8724434876210979,0.92128445581131,1621,40,237,0.9989164506017569,0.9981053282808754,0.9985107247161673,25813,28,49,0.8376852505292872,0.9974789915966387,0.9106252397391639,1187,230,3,0.9503924183130014,0.9889385510788128,0.9003312569168942
+XX-LeetSpeakNER-paraphrase-multilingual-mpnet-base-v2,TED2020,IT,0.9192708333333334,0.9514824797843666,0.9350993377483445,353,31,18,0.9943705220061413,0.9724724724724725,0.9832995951417004,1943,11,55,0.9665450121654501,0.902328222600795,0.9333333333333333,1589,55,172,0.9986299081035923,0.9983296585822142,0.9984797607711454,29884,41,50,0.8722466960352423,0.9858921161825727,0.925594078691079,1188,174,17,0.9551612211371205,0.9911537043862882,0.9087880971884397
+XX-LeetSpeakNER-paraphrase-multilingual-mpnet-base-v2,OPUS_ParaCrawl,IT,0.8801571709233792,0.8818897637795275,0.8810226155358898,448,61,60,0.9857992073976222,0.9761281883584042,0.980939861978311,2985,43,73,0.9796623177283192,0.8870743571924948,0.9310722100656456,2553,53,325,0.9979772544324961,0.9979978533685601,0.9979875537942351,48351,98,97,0.8470993117010817,0.9936562860438293,0.9145435244161357,1723,311,11,0.9411131531580434,0.9900045915303924,0.8850525078969678
+XX-LeetSpeakNER-paraphrase-multilingual-mpnet-base-v2,OPUS_News_Commentary,IT,1.0,1.0,1.0,1,0,0,1.0,1.0,1.0,27,0,0,1.0,0.5333333333333333,0.6956521739130436,8,0,7,1.0,1.0,1.0,373,0,0,0.5333333333333333,1.0,0.6956521739130436,8,7,0,0.8782608695652174,0.9834905660377359,0.8133333333333332

README.md

@@ -0,0 +1,56 @@
+---
+tags:
+- spacy
+- token-classification
+language:
+- multilingual
+model-index:
+- name: xx_pipeline
+  results:
+  - task:
+      name: NER
+      type: token-classification
+    metrics:
+    - name: NER Precision
+      type: precision
+      value: 0.9200034895
+    - name: NER Recall
+      type: recall
+      value: 0.918641115
+    - name: NER F Score
+      type: f_score
+      value: 0.9193217975
+---
+| Feature | Description |
+| --- | --- |
+| **Name** | `xx_pipeline` |
+| **Version** | `0.0.0` |
+| **spaCy** | `>=3.4.3,<3.5.0` |
+| **Default Pipeline** | `transformer`, `ner` |
+| **Components** | `transformer`, `ner` |
+| **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
+| **Sources** | n/a |
+| **License** | n/a |
+| **Author** | [n/a]() |
+
+### Label Scheme
+
+<details>
+
+<summary>View label scheme (4 labels for 1 components)</summary>
+
+| Component | Labels |
+| --- | --- |
+| **`ner`** | `INV_CAMO`, `LEETSPEAK`, `MIX`, `PUNCT_CAMO` |
+
+</details>
+
+### Accuracy
+
+| Type | Score |
+| --- | --- |
+| `ENTS_F` | 91.93 |
+| `ENTS_P` | 92.00 |
+| `ENTS_R` | 91.86 |
+| `TRANSFORMER_LOSS` | 382037.26 |
+| `NER_LOSS` | 320041.67 |

XX-LeetSpeakNER-paraphrase-multilingual-mpnet-base-v2_test_DE.csv

@@ -0,0 +1,6 @@
+Model,Dataset,lang,P-INV_CAM,R-INV_CAM,F1-INV_CAM,TP-INV_CAM,FN-INV_CAM,FP-INV_CAM,P-LEETSPEAK,R-LEETSPEAK,F1-LEETSPEAK,TP-LEETSPEAK,FN-LEETSPEAK,FP-LEETSPEAK,P-MIX,R-MIX,F1-MIX,TP-MIX,FN-MIX,FP-MIX,P-O,R-O,F1-O,TP-O,FN-O,FP-O,P-PUNCT_CAM,R-PUNCT_CAM,F1-PUNCT_CAM,TP-PUNCT_CAM,FN-PUNCT_CAM,FP-PUNCT_CAM,F1-Macro,F1-Micro,F1-Weighted
+XX-LeetSpeakNER-paraphrase-multilingual-mpnet-base-v2,overall,DE,0.9593908629441624,0.9402985074626866,0.949748743718593,1134,48,72,0.9802671523983,0.9236270022883295,0.9511045655375553,6458,130,534,0.9136866059817945,0.9160691003911343,0.9148763020833333,5621,531,515,0.9988433462421604,0.9983215872988688,0.9985823986158043,116581,135,196,0.9015554242961212,0.9941380807642206,0.9455859576664946,4579,500,27,0.9519795935243561,0.9900970401644599,0.9058705176113871
+XX-LeetSpeakNER-paraphrase-multilingual-mpnet-base-v2,WikiMatrix,DE,0.9575971731448764,0.9377162629757786,0.9475524475524476,271,12,18,0.9799291617473436,0.9211986681465039,0.9496567505720824,1660,34,142,0.9075682382133995,0.8760479041916168,0.8915295551492992,1463,149,207,0.9987062309586411,0.9982063154382013,0.9984562106229398,23930,31,43,0.8513097072419107,0.9919210053859964,0.9162520729684909,1105,193,9,0.940689407373052,0.985475596228508,0.8848545038575294
+XX-LeetSpeakNER-paraphrase-multilingual-mpnet-base-v2,TED2020,DE,0.9610778443113772,0.9610778443113772,0.9610778443113772,321,13,13,0.9796027911969941,0.9138708062093139,0.9455958549222798,1825,38,172,0.8917618761274805,0.9362373737373737,0.9134585771481367,1483,180,101,0.9995092907615808,0.9984314238096794,0.9989700665369714,30553,15,48,0.928937728937729,0.9929522317932654,0.9598788796366389,1268,97,9,0.9557962445110808,0.990417120666052,0.9109428130752214
+XX-LeetSpeakNER-paraphrase-multilingual-mpnet-base-v2,OPUS_ParaCrawl,DE,0.9597069597069597,0.9274336283185841,0.9432943294329433,524,22,41,0.9805858310626703,0.9314137819475897,0.955367512858802,2879,57,212,0.9301907160849227,0.9275206315034087,0.9288537549407114,2585,194,202,0.9985411140583554,0.9982928648379878,0.9984169740168249,60232,88,103,0.9117773019271949,0.9957904583723106,0.9519338251732619,2129,206,9,0.9555732792845086,0.9917725927215741,0.9142058342563086
+XX-LeetSpeakNER-paraphrase-multilingual-mpnet-base-v2,OPUS_News_Commentary,DE,0.9473684210526315,1.0,0.972972972972973,18,1,0,0.9894736842105263,0.9215686274509803,0.9543147208121827,94,1,8,0.9183673469387755,0.9473684210526315,0.9326424870466321,90,8,5,0.9994643813604713,0.9989293361884368,0.9991967871485944,1866,1,2,0.9506172839506173,1.0,0.9746835443037974,77,4,0,0.966762102456836,0.9930555555555556,0.929550840124867

XX-LeetSpeakNER-paraphrase-multilingual-mpnet-base-v2_test_EN.csv

@@ -0,0 +1,6 @@
+Model,Dataset,lang,P-INV_CAM,R-INV_CAM,F1-INV_CAM,TP-INV_CAM,FN-INV_CAM,FP-INV_CAM,P-LEETSPEAK,R-LEETSPEAK,F1-LEETSPEAK,TP-LEETSPEAK,FN-LEETSPEAK,FP-LEETSPEAK,P-MIX,R-MIX,F1-MIX,TP-MIX,FN-MIX,FP-MIX,P-O,R-O,F1-O,TP-O,FN-O,FP-O,P-PUNCT_CAM,R-PUNCT_CAM,F1-PUNCT_CAM,TP-PUNCT_CAM,FN-PUNCT_CAM,FP-PUNCT_CAM,F1-Macro,F1-Micro,F1-Weighted
+XX-LeetSpeakNER-paraphrase-multilingual-mpnet-base-v2,overall,EN,0.9295154185022027,0.8991477272727273,0.9140794223826715,633,48,71,0.9817336965229931,0.862836220250669,0.9184530055463949,6127,114,974,0.8228949858088931,0.8135054246165357,0.8181732668610666,4349,936,997,0.9981404078937078,0.998669773426768,0.998405020491358,114865,214,153,0.7638535841382816,0.9849229760734185,0.8604151753758054,3005,929,46,0.9019051781314593,0.9829218106995885,0.8156754939669992
+XX-LeetSpeakNER-paraphrase-multilingual-mpnet-base-v2,WikiMatrix,EN,0.9289099526066351,0.8949771689497716,0.9116279069767441,196,15,23,0.985838779956427,0.8614945264159923,0.9194818389636779,1810,26,291,0.8194186765615337,0.8312421580928482,0.8252880722516349,1325,292,269,0.9980703176257189,0.9986484399135002,0.9983592950759551,25861,50,35,0.8004846526655897,0.9880358923230309,0.8844265952699687,991,247,12,0.9078367417075961,0.9795540843150619,0.8267880489582179
+XX-LeetSpeakNER-paraphrase-multilingual-mpnet-base-v2,TED2020,EN,0.9701492537313433,0.9701492537313433,0.9701492537313433,195,6,6,0.9912998976458547,0.8658918194009835,0.9243617275113338,1937,17,300,0.8032890575585073,0.8540685944855414,0.8279009126466753,1270,311,217,0.9993485727821865,0.9994669509594882,0.9994077583654131,33750,22,18,0.8263157894736842,0.9863874345549738,0.8992840095465393,942,198,13,0.924220732360261,0.9856654936866073,0.8528804595032835
+XX-LeetSpeakNER-paraphrase-multilingual-mpnet-base-v2,OPUS_ParaCrawl,EN,0.8992248062015504,0.8467153284671532,0.8721804511278195,232,26,42,0.9699279966116052,0.8612260248213615,0.9123505976095618,2290,71,369,0.8416873449131513,0.7702089009990918,0.8043632914394118,1696,319,506,0.9973565657693882,0.9981555659059153,0.9977559058784092,53576,142,99,0.6821499668214996,0.9799809342230696,0.8043818466353678,1028,479,21,0.8782064185381142,0.9826759551612957,0.7780101082718855
+XX-LeetSpeakNER-paraphrase-multilingual-mpnet-base-v2,OPUS_News_Commentary,EN,0.9090909090909091,1.0,0.9523809523809523,10,1,0,1.0,0.8653846153846154,0.9278350515463918,90,0,14,0.8055555555555556,0.9206349206349206,0.8592592592592592,58,14,5,1.0,0.9994044073853484,0.9997021149836164,1678,0,1,0.8979591836734694,1.0,0.9462365591397849,44,5,0,0.9370827874620009,0.9894736842105263,0.8670401820993752

XX-LeetSpeakNER-paraphrase-multilingual-mpnet-base-v2_test_ES.csv

@@ -0,0 +1,6 @@
+Model,Dataset,lang,P-INV_CAM,R-INV_CAM,F1-INV_CAM,TP-INV_CAM,FN-INV_CAM,FP-INV_CAM,P-LEETSPEAK,R-LEETSPEAK,F1-LEETSPEAK,TP-LEETSPEAK,FN-LEETSPEAK,FP-LEETSPEAK,P-MIX,R-MIX,F1-MIX,TP-MIX,FN-MIX,FP-MIX,P-O,R-O,F1-O,TP-O,FN-O,FP-O,P-PUNCT_CAM,R-PUNCT_CAM,F1-PUNCT_CAM,TP-PUNCT_CAM,FN-PUNCT_CAM,FP-PUNCT_CAM,F1-Macro,F1-Micro,F1-Weighted
+XX-LeetSpeakNER-paraphrase-multilingual-mpnet-base-v2,overall,ES,0.9283429302623161,0.9283429302623161,0.9283429302623161,1451,112,112,0.9885572726200307,0.9713689579228005,0.9798877455565949,8380,97,247,0.9657499363381716,0.8870307566366507,0.9247180737580005,7585,269,966,0.9987828034471007,0.9986647193824327,0.9987237579243505,143598,175,192,0.8546575992408667,0.9899248946693534,0.9173315226616873,5404,919,55,0.94980080603259,0.9906423001369129,0.90101092918534
+XX-LeetSpeakNER-paraphrase-multilingual-mpnet-base-v2,WikiMatrix,ES,0.9293785310734464,0.9138888888888889,0.9215686274509804,329,25,31,0.9903948772678762,0.9631551634665283,0.9765851091817943,1856,18,71,0.9575087310826542,0.8496900826446281,0.9003831417624522,1645,73,291,0.998149316508938,0.9982752818441865,0.9982122952026415,23731,44,41,0.8016759776536313,0.9913644214162349,0.8864864864864865,1148,284,10,0.936647132016871,0.9847700065173396,0.8785711094177607
+XX-LeetSpeakNER-paraphrase-multilingual-mpnet-base-v2,TED2020,ES,0.9333333333333333,0.9357326478149101,0.9345314505776636,364,26,25,0.9919393077287814,0.9712163416898792,0.981468449448745,2092,17,62,0.964984552008239,0.9141463414634147,0.9388777555110221,1874,68,176,0.9989075131878765,0.9987516384745022,0.99882956974984,32002,35,40,0.8821917808219178,0.9884881043745203,0.932319942091929,1288,172,15,0.9572054334758399,0.9916179028941958,0.9144024740191629
+XX-LeetSpeakNER-paraphrase-multilingual-mpnet-base-v2,OPUS_ParaCrawl,ES,0.9172932330827067,0.9277566539923955,0.9224952741020794,488,44,38,0.9884856943475226,0.9755509641873278,0.9819757365684576,2833,33,71,0.9742457689477557,0.8871021775544389,0.9286340522532,2648,70,337,0.9987801158889905,0.9987801158889905,0.9987801158889905,55675,68,68,0.8574640287769785,0.9906493506493507,0.9192576524463727,1907,317,18,0.9502285662518201,0.9916982663108781,0.901475505326671
+XX-LeetSpeakNER-paraphrase-multilingual-mpnet-base-v2,OPUS_News_Commentary,ES,0.9407665505226481,0.9375,0.9391304347826087,270,17,18,0.9821867321867321,0.9738124238733252,0.9779816513761468,1599,29,43,0.9596774193548387,0.9037974683544304,0.9308996088657105,1428,60,152,0.9994410979320624,0.9986039152421431,0.999022331196946,32188,18,45,0.8790389395194698,0.9888164026095061,0.9307017543859649,1061,146,12,0.9555471561214753,0.9926662320730117,0.9108026989948275

XX-LeetSpeakNER-paraphrase-multilingual-mpnet-base-v2_test_FR.csv

@@ -0,0 +1,6 @@
+Model,Dataset,lang,P-INV_CAM,R-INV_CAM,F1-INV_CAM,TP-INV_CAM,FN-INV_CAM,FP-INV_CAM,P-LEETSPEAK,R-LEETSPEAK,F1-LEETSPEAK,TP-LEETSPEAK,FN-LEETSPEAK,FP-LEETSPEAK,P-MIX,R-MIX,F1-MIX,TP-MIX,FN-MIX,FP-MIX,P-O,R-O,F1-O,TP-O,FN-O,FP-O,P-PUNCT_CAM,R-PUNCT_CAM,F1-PUNCT_CAM,TP-PUNCT_CAM,FN-PUNCT_CAM,FP-PUNCT_CAM,F1-Macro,F1-Micro,F1-Weighted
+XX-LeetSpeakNER-paraphrase-multilingual-mpnet-base-v2,overall,FR,0.9451152579582875,0.9399563318777293,0.9425287356321839,861,50,55,0.9893436293436293,0.8920763124912965,0.9381956649091974,6406,69,775,0.864655020292924,0.891395306530835,0.8778215693299893,4900,767,597,0.9990071704357418,0.9991961288085368,0.9991016406877965,126784,126,102,0.8773920783266578,0.991450842343475,0.9309408570416716,3943,551,34,0.9377176935201679,0.9891801712620365,0.8785837713017278
+XX-LeetSpeakNER-paraphrase-multilingual-mpnet-base-v2,WikiMatrix,FR,0.9422222222222222,0.9592760180995475,0.9506726457399103,212,13,9,0.9867708959711365,0.882258064516129,0.9315923928470053,1641,22,219,0.8617724867724867,0.8374035989717223,0.8494132985658409,1303,209,253,0.9991585067319462,0.9986619260618572,0.9989101546815549,26122,22,35,0.7905236907730673,0.9979013641133263,0.8821892393320964,951,252,2,0.9225555462332817,0.9831528279181708,0.8484950471190542
+XX-LeetSpeakNER-paraphrase-multilingual-mpnet-base-v2,TED2020,FR,0.9449152542372882,0.9291666666666667,0.9369747899159665,223,13,17,0.9913444893248702,0.8901554404145078,0.938028938028938,1718,15,212,0.8554216867469879,0.9070262597586941,0.8804684808818463,1278,216,131,0.9990731014027066,0.9993509905120994,0.9992120266365897,32336,30,21,0.9071661237785016,0.9937555753791257,0.9484887186036611,1114,114,7,0.9406345908134004,0.9895296435221416,0.8854332232254306
+XX-LeetSpeakNER-paraphrase-multilingual-mpnet-base-v2,OPUS_ParaCrawl,FR,0.9472477064220184,0.9343891402714932,0.9407744874715261,413,23,29,0.9901728227719417,0.8974201474201474,0.9415176413726439,2922,29,334,0.871824480369515,0.9184914841849149,0.8945497630331753,2265,333,201,0.9990791896869244,0.9993507277888506,0.9992149402901701,66185,61,43,0.9097744360902256,0.9896401308615049,0.9480282057978584,1815,180,19,0.9448170075930747,0.9915662975237788,0.8928177435363803
+XX-LeetSpeakNER-paraphrase-multilingual-mpnet-base-v2,OPUS_News_Commentary,FR,0.9285714285714286,1.0,0.962962962962963,13,1,0,1.0,0.868421052631579,0.9295774647887324,66,0,10,0.8412698412698413,0.9298245614035088,0.8833333333333334,53,10,4,1.0,0.9993730407523511,0.9996864220758859,1594,0,1,0.9402985074626866,1.0,0.9692307692307692,63,4,0,0.9489581904783367,0.9916851441241685,0.8955863439721619

XX-LeetSpeakNER-paraphrase-multilingual-mpnet-base-v2_test_IT.csv

@@ -0,0 +1,6 @@
+Model,Dataset,lang,P-INV_CAM,R-INV_CAM,F1-INV_CAM,TP-INV_CAM,FN-INV_CAM,FP-INV_CAM,P-LEETSPEAK,R-LEETSPEAK,F1-LEETSPEAK,TP-LEETSPEAK,FN-LEETSPEAK,FP-LEETSPEAK,P-MIX,R-MIX,F1-MIX,TP-MIX,FN-MIX,FP-MIX,P-O,R-O,F1-O,TP-O,FN-O,FP-O,P-PUNCT_CAM,R-PUNCT_CAM,F1-PUNCT_CAM,TP-PUNCT_CAM,FN-PUNCT_CAM,FP-PUNCT_CAM,F1-Macro,F1-Micro,F1-Weighted
+XX-LeetSpeakNER-paraphrase-multilingual-mpnet-base-v2,overall,IT,0.9056304520222046,0.9217110573042776,0.9136,1142,119,97,0.9893648018648019,0.976279470960322,0.9827785817655571,6791,73,165,0.9748310810810811,0.8860740058344849,0.9283358803185072,5771,149,742,0.9983891261247522,0.9980942035200061,0.9982416430392413,104743,169,200,0.8497516556291391,0.9922667955534075,0.9154960981047937,4106,726,32,0.9476904406456198,0.990015267915566,0.8958518228704071
+XX-LeetSpeakNER-paraphrase-multilingual-mpnet-base-v2,WikiMatrix,IT,0.9264305177111717,0.947075208913649,0.9366391184573003,340,27,19,0.9895201323772752,0.980327868852459,0.984902552841065,1794,19,36,0.9759181216134859,0.8724434876210979,0.92128445581131,1621,40,237,0.9989164506017569,0.9981053282808754,0.9985107247161673,25813,28,49,0.8376852505292872,0.9974789915966387,0.9106252397391639,1187,230,3,0.9503924183130014,0.9889385510788128,0.9003312569168942
+XX-LeetSpeakNER-paraphrase-multilingual-mpnet-base-v2,TED2020,IT,0.9192708333333334,0.9514824797843666,0.9350993377483445,353,31,18,0.9943705220061413,0.9724724724724725,0.9832995951417004,1943,11,55,0.9665450121654501,0.902328222600795,0.9333333333333333,1589,55,172,0.9986299081035923,0.9983296585822142,0.9984797607711454,29884,41,50,0.8722466960352423,0.9858921161825727,0.925594078691079,1188,174,17,0.9551612211371205,0.9911537043862882,0.9087880971884397
+XX-LeetSpeakNER-paraphrase-multilingual-mpnet-base-v2,OPUS_ParaCrawl,IT,0.8801571709233792,0.8818897637795275,0.8810226155358898,448,61,60,0.9857992073976222,0.9761281883584042,0.980939861978311,2985,43,73,0.9796623177283192,0.8870743571924948,0.9310722100656456,2553,53,325,0.9979772544324961,0.9979978533685601,0.9979875537942351,48351,98,97,0.8470993117010817,0.9936562860438293,0.9145435244161357,1723,311,11,0.9411131531580434,0.9900045915303924,0.8850525078969678
+XX-LeetSpeakNER-paraphrase-multilingual-mpnet-base-v2,OPUS_News_Commentary,IT,1.0,1.0,1.0,1,0,0,1.0,1.0,1.0,27,0,0,1.0,0.5333333333333333,0.6956521739130436,8,0,7,1.0,1.0,1.0,373,0,0,0.5333333333333333,1.0,0.6956521739130436,8,7,0,0.8782608695652174,0.9834905660377359,0.8133333333333332

config.cfg

@@ -0,0 +1,150 @@
+[paths]
+train = "./Data/XX/11-18-22_17-51/NER_TRAIN_DATA.spacy"
+dev = "./Data/XX/11-18-22_17-51/NER_DEV_DATA.spacy"
+vectors = null
+init_tok2vec = null
+
+[system]
+gpu_allocator = "pytorch"
+seed = 0
+
+[nlp]
+lang = "xx"
+pipeline = ["transformer","ner"]
+batch_size = 128
+disabled = []
+before_creation = null
+after_creation = null
+after_pipeline_creation = null
+tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
+
+[components]
+
+[components.ner]
+factory = "ner"
+incorrect_spans_key = null
+moves = null
+scorer = {"@scorers":"spacy.ner_scorer.v1"}
+update_with_oracle_cut_size = 100
+
+[components.ner.model]
+@architectures = "spacy.TransitionBasedParser.v2"
+state_type = "ner"
+extra_state_tokens = false
+hidden_width = 64
+maxout_pieces = 2
+use_upper = false
+nO = null
+
+[components.ner.model.tok2vec]
+@architectures = "spacy-transformers.TransformerListener.v1"
+grad_factor = 1.0
+pooling = {"@layers":"reduce_mean.v1"}
+upstream = "*"
+
+[components.transformer]
+factory = "transformer"
+max_batch_items = 4096
+set_extra_annotations = {"@annotation_setters":"spacy-transformers.null_annotation_setter.v1"}
+
+[components.transformer.model]
+@architectures = "spacy-transformers.TransformerModel.v3"
+name = "sentence-transformers/paraphrase-multilingual-mpnet-base-v2"
+mixed_precision = false
+
+[components.transformer.model.get_spans]
+@span_getters = "spacy-transformers.strided_spans.v1"
+window = 128
+stride = 96
+
+[components.transformer.model.grad_scaler_config]
+
+[components.transformer.model.tokenizer_config]
+use_fast = true
+
+[components.transformer.model.transformer_config]
+
+[corpora]
+
+[corpora.dev]
+@readers = "spacy.Corpus.v1"
+path = ${paths.dev}
+max_length = 0
+gold_preproc = false
+limit = 0
+augmenter = null
+
+[corpora.train]
+@readers = "spacy.Corpus.v1"
+path = ${paths.train}
+max_length = 0
+gold_preproc = false
+limit = 0
+augmenter = null
+
+[training]
+accumulate_gradient = 3
+dev_corpus = "corpora.dev"
+train_corpus = "corpora.train"
+seed = ${system.seed}
+gpu_allocator = ${system.gpu_allocator}
+dropout = 0.1
+patience = 1600
+max_epochs = 0
+max_steps = 20000
+eval_frequency = 200
+frozen_components = []
+annotating_components = []
+before_to_disk = null
+
+[training.batcher]
+@batchers = "spacy.batch_by_padded.v1"
+discard_oversize = true
+size = 2000
+buffer = 256
+get_length = null
+
+[training.logger]
+@loggers = "spacy.WandbLogger.v3"
+project_name = "ASOC-LeetSpeakNER-full-XX-MultiNER"
+remove_config_values = ["paths.train","paths.dev","corpora.train.path","corpora.dev.path"]
+model_log_interval = null
+log_dataset_dir = null
+entity = null
+run_name = null
+
+[training.optimizer]
+@optimizers = "Adam.v1"
+beta1 = 0.9
+beta2 = 0.999
+L2_is_weight_decay = true
+L2 = 0.01
+grad_clip = 1.0
+use_averages = false
+eps = 0.00000001
+
+[training.optimizer.learn_rate]
+@schedules = "warmup_linear.v1"
+warmup_steps = 250
+total_steps = 20000
+initial_rate = 0.00005
+
+[training.score_weights]
+ents_f = 1.0
+ents_p = 0.0
+ents_r = 0.0
+ents_per_type = null
+
+[pretraining]
+
+[initialize]
+vectors = ${paths.vectors}
+init_tok2vec = ${paths.init_tok2vec}
+vocab_data = null
+lookups = null
+before_init = null
+after_init = null
+
+[initialize.components]
+
+[initialize.tokenizer]

meta.json

@@ -0,0 +1,72 @@
+{
+  "lang":"xx",
+  "name":"pipeline",
+  "version":"0.0.0",
+  "description":"",
+  "author":"",
+  "email":"",
+  "url":"",
+  "license":"",
+  "spacy_version":">=3.4.3,<3.5.0",
+  "spacy_git_version":"Unknown",
+  "vectors":{
+    "width":0,
+    "vectors":0,
+    "keys":0,
+    "name":null
+  },
+  "labels":{
+    "transformer":[
+
+    ],
+    "ner":[
+      "INV_CAMO",
+      "LEETSPEAK",
+      "MIX",
+      "PUNCT_CAMO"
+    ]
+  },
+  "pipeline":[
+    "transformer",
+    "ner"
+  ],
+  "components":[
+    "transformer",
+    "ner"
+  ],
+  "disabled":[
+
+  ],
+  "performance":{
+    "ents_f":0.9193217975,
+    "ents_p":0.9200034895,
+    "ents_r":0.918641115,
+    "ents_per_type":{
+      "LEETSPEAK":{
+        "p":0.9071114662,
+        "r":0.9820076986,
+        "f":0.9430749102
+      },
+      "MIX":{
+        "p":0.8874027994,
+        "r":0.865489625,
+        "f":0.8763092423
+      },
+      "PUNCT_CAMO":{
+        "p":0.9893371246,
+        "r":0.8676069508,
+        "f":0.9244820858
+      },
+      "INV_CAMO":{
+        "p":0.9334140436,
+        "r":0.9319097502,
+        "f":0.9326612903
+      }
+    },
+    "transformer_loss":3820.3726315295,
+    "ner_loss":3200.4167286961
+  },
+  "requirements":[
+    "spacy-transformers>=1.1.8,<1.2.0"
+  ]
+}

ner/cfg

@@ -0,0 +1,13 @@
+{
+  "moves":null,
+  "update_with_oracle_cut_size":100,
+  "multitasks":[
+
+  ],
+  "min_action_freq":1,
+  "learn_tokens":false,
+  "beam_width":1,
+  "beam_density":0.0,
+  "beam_update_prob":0.0,
+  "incorrect_spans_key":null
+}

ner/moves

@@ -0,0 +1 @@
+��moves�
D{"0":{},"1":{"LEETSPEAK":278858,"MIX":249011,"PUNCT_CAMO":200301,"INV_CAMO":44687},"2":{"LEETSPEAK":278858,"MIX":249011,"PUNCT_CAMO":200301,"INV_CAMO":44687},"3":{"LEETSPEAK":278858,"MIX":249011,"PUNCT_CAMO":200301,"INV_CAMO":44687},"4":{"LEETSPEAK":278858,"MIX":249011,"PUNCT_CAMO":200301,"INV_CAMO":44687,"":1},"5":{"":1}}�cfg��neg_key�

plots/.ipynb_checkpoints/TEST_XX-LeetSpeakNER-mstsb-paraphrase-multilingual-mpnet-base-v2_Overall_confusion_matrix-checkpoint.pdf

@@ -0,0 +1,269 @@
-V뷫�i��jv
+%PDF-1.4
+%����
+1 0 obj
+<</Creator (Chromium)
+/Producer (Skia/PDF m88)
+/CreationDate (D:20221124144321+00'00')
+/ModDate (D:20221124144321+00'00')>>
+endobj
+3 0 obj
+<</ca 1
+/BM /Normal>>
+endobj
+4 0 obj
+<</CA 1
+/ca 1
+/LC 0
+/LJ 0
+/LW 1
+/ML 4
+/SA true
+/BM /Normal>>
+endobj
+5 0 obj
+<</Type /XObject
+/Subtype /Image
+/Width 394
+/Height 365
+/ColorSpace /DeviceRGB
+/BitsPerComponent 8
+/Filter /FlateDecode
+/Length 2961>> stream
+x���1��E�A:[+q""b^��8lEѤH�8�r�
+endstream
+endobj
+7 0 obj
+<</Type /Pattern
+/PatternType 2
+/Matrix [22.5 0 0 -258.75 459 326.37]
+/Shading <</Function <</Domain [0 1]
+/FunctionType 3
+/Encode [0 1 0 1 0 1 0 1 0 1 0 1]
+/Bounds [.166666672 .33333334 .5 .66666669 .83333331]
+/Functions [<</C0 [.996 .965 .71]
+/C1 [1 .867 .604]
+/Domain [0 1]
+/FunctionType 2
+/N 1>> <</C0 [1 .867 .604]
+/C1 [1 .761 .522]
+/Domain [0 1]
+/FunctionType 2
+/N 1>> <</C0 [1 .761 .522]
+/C1 [1 .651 .475]
+/Domain [0 1]
+/FunctionType 2
+/N 1>> <</C0 [1 .651 .475]
+/C1 [.98 .541 .463]
+/Domain [0 1]
+/FunctionType 2
+/N 1>> <</C0 [.98 .541 .463]
+/C1 [.945 .427 .478]
+/Domain [0 1]
+/FunctionType 2
+/N 1>> <</C0 [.945 .427 .478]
+/C1 [.882 .325 .514]
+/Domain [0 1]
+/FunctionType 2
+/N 1>>]>>
+/Extend [true true]
+/Coords [0 1 0 0]
+/ShadingType 2
+/ColorSpace /DeviceRGB>>>>
+endobj
+9 0 obj
+<</Filter /FlateDecode
+/Length 1134>> stream
+x���Ko�8���</P���
��ɭh7��E�-Pl�h���Iɖ-�"-m�Ж%��͛�ҟP�z#G_�#�A<<v?�x�w��&������x�k�E���ߤE|�y'����nsg���4�SJ��[��_��>x!�E�M��CJ��� {:�Cߟa�;��|�# (�ow��P�Քm�U*i/��[��%w:0�ߪ���Kdm���+����قS���5&sR���H�Tv%2�$�%6����2�|��h��>l��2\J����nfKʮN	������.ȿ��:��tZp��阆���<��v�[ˁ+���T�al��y�6�l���>vo�������T`y W���G�a[��ka�A=������p�3�iL�q�C	���E�GD\&˖�.b�����<iK�j>5��DŽ�క����.��>���J�Z��ʐ�ePm�*��2���E�yJ�)4�A���ZP�f�T����7��$iG�O��kM��#�E
+0{O�A��5*�,~�}�̈́���ڒ�19ȴ��Y�P�c��Gl��|����Tԃ���������E	�[52��:�&����\��ԏ����0�Ȫ�?C؋
+�R��w���qU.�lW-f�XdCQ�	G��}[/uh��w[l޶�Qo��� ,j9��r_�EB~�V=�QlDŽ��ͤ!��hA��ທZs��%
+endstream
+endobj
+2 0 obj
+<</Type /Page
+/Resources <</ProcSet [/PDF /Text /ImageB /ImageC /ImageI]
+/ExtGState <</G3 3 0 R
+/G4 4 0 R>>
+/Pattern <</P7 7 0 R>>
+/XObject <</X5 5 0 R>>
+/Font <</F6 6 0 R
+/F8 8 0 R>>>>
+/MediaBox [0 0 525.12 375.12]
+/Contents 9 0 R
+/StructParents 0
+/Parent 10 0 R>>
+endobj
+10 0 obj
+<</Type /Pages
+/Count 1
+/Kids [2 0 R]>>
+endobj
+11 0 obj
+<</Type /Catalog
+/Pages 10 0 R>>
+endobj
+12 0 obj
+<</Length1 15376
+/Filter /FlateDecode
+/Length 10844>> stream
+x��{@T׵�^{�33g�a����03��d@�#�P0|D@A>~@
�h*�OM��51�j�����hLb���޼~n�ۦ��Mۘ��mS���4�M��gŤ��9�s�^{�u�^{}�BLd�0��,뜸�
!��b�?gW��B �-�7��
+������_^���U��?Bg����csߏ=!B�RB�bGk_/�#!���_�شs�/G�/������ֶ��>��u���D@t�����+XO��ܿ����a����M=�[�~x⫈o
+��Ѕ���ʯ;�!��?w�*�7�Z:E�'h_%�#���$y���&�ϓ��;GBw����W��(+3!�o�i}�|����a��|����S(����t%�B�����a���"ǰy�Z����(
+���J��r�'Ȯ�d~�,W��z���
+���ejYHU+F���8�U�Y�
+A��,��9\�R��.�%��v}�,rQo��
K�tO�EH/�@��
+.R�3�׆XJYk[�������v�gͪE{J�&R��iJBZ����N��.�>zE&�Z�Qm���5u!֊c�Y���!�7��)
+Y���Pu]��"�����ևho�j��򖡩���[<�����CBJE��y|�54�婛/�GE�p{�-fW��^��B�*ں\!1ق��@I�C�e��q�1����-�|��x�<e-���q���5+T�
+��J��]e�-�a8.Ouݫ$0y�b���b���R�9��*�l��mC���hCM��s�CJ=.p�����r(�:�έ�1DKj�*Wy*���E	7ptBJ�g�x�a4(r!]��UG�;�p��Y4�!m�/�B��.����d�2\e���~�~R��SI�6
+Z�P����ɡ��KhIˢ����V��}�
+�ʁ����i%Vtjǫ
+!Cj�����+@T�n
+d���S0�0!ST?p��:��h��\m|}v�w��s'1���x��;���@5Q!��}Q��Y���^�k8\��
1�5kpX.��%.+�.�'��	`l�c;�t~��zh}�e���⩻O�2<?�|�uF�N<��%5J����_ӿf��r����3�g���<e:%/��us��r���z�M;��#k���
+o#֪�?	���4ҫTէt�Р{�{���vlp��خX*X`�����46RCt�S{XK�����d�2b;k�����-�z������>1�����i,A�ES����M���h���
�˵A '	,�\�̌�v[
+
+|NH�hD4�cu��L5�THT��ڮ����D�lH/k/n����V1k�¼ؐ����9�G�w=�]�t��s����B��fp���+f�3Rl��S򔁯q)�h`2�G.(�G�03C�]Z�y����6Jk<m�~���6�&�K*K�r ���,��|�$�%�%$1	`�ِ���3)t$R
+���[d�KO��Tš��'f�\�q}���vj7is#�#Ф�/�ۨ��;z�J�7�Ya5s���hT7�~Ϋ�����uepA���m/�B����f�^��&k�����=^I.��n��Wv/Z�Q�
+ow_ܳx�E�'_��lI*�R�l�����梁�{+���J\ؽt�mY��ܪu�v~/�&�J֠a�@�Мl�hHU�Q�(eh�1��(���M��~�F�J�'޴��V�>i�Tj��&й�<��}ih��U�.����M�d�ߺ|� |���1S=�j�jY@��Ue�@��t:�>�����3�@܁8:;K��V:��a�k�[\[�^Fk+�+i���4w�=s�Ӕ�\���;��̦"gu�����"(Z5T�UE�l*��_�H�.�D�E���R������c�ؔi����sJ;�r���<���&�}f���]�����w�~��|���9�M���ޯo�;�3�]ܴ`A��Y�r�U,^W<#�`CUm�\�gFi��=e��l�^�[���RT����e;�ɓ��{���[�_�~����{D	��{vХyu�Oq]^f]��W^7�D��"+kIk��23�mF�k�ձDt�J׹4x�_�z*��7�I3�{�{h�k�븋
+Gcm���%
G��7�v-�x����
+t�w��>(��|p���r}���������A�w��{��Z|P�E�'�@���7��7}������q��A��ys��"��˻>:��>��K}m>~S�5���Zxs����wp�a�bUc���|a�}�G>����=��~�0WY�[ur|D������k>��i%'�֧>x2<�!0_���NJ9\>��XCf(3�v��n��,[���DV�Ę�f�����N�9�:��fn���
+H)��
+��T2�L���*Tݫ=�
+��-��пx!!N^6�ۜ���m�;X��۵�H�i�A�����&��N�}sb�pP�ݧ�w���+�w2p���!e��I��u���A�ez�7(���r�²-#��v�r�r��,�!�
�c�q�q�!8�Ēѩ�V��b�Ȏ�gD��x����UÌ�D�Hj�����eV7y������{F��Z�����k_^s5ÑU+�R�ͦ�?����0�{���/���j9���n}��w-�yIh���d��Ғ���hV&�
+�;j�S���4h�1�c���x���'���4	�	�d
�
��NRHa�'��h�)�T�q���e����r1�.4ݲ�rZ�Q��,ʟK��U�\�X�miAƎ"kE�L��D��B���;�;f
�[y��|W�~�7wc�I;gn`Ǣ�3����ASRT�1*:*�����+�ޓ�����f�I��^�s�{��5TP(@�
*I#�<�����T:�R	�Nc�z.
=h�1zڤ��:��
+uT����J
+�5�s��rѼ��>2�
+U�*y��G�v�������x���Ȧ]����Q�a���T��kA$O�)�ᦁ�85!���
F��<�E�KS��2��2d�b�:�ɨ�]`W�;L`۴��-��hO|y��"�D���x��u��&u}^@�A��8'�Z��pL�U������uV?�6v��ˮ�g�<�������1��0��}?�H��9��}j��4c|�x"��&���	#%V�-t���ר�71�&�@�g5�fh�¹��������B���$�,$_Urv.8���:Ei�d,׋	"��aP)ΰϠ))IA�'���3��<6�dȶX�"l��v{�b'�]2ZBϖ@	op%y����1�Ւ�h���v�Fm6SU��T��3��%e��������"'��ꎪ�p���c�b���k��l�	�̙k�l�z�Y���fv[|�'��=s���QpOanMQ��u���S[����BSR�̒�@�/�i��xV�����m�k�=wb���IT(,Y[�0��������.N���֫�9�V�ɭ)t=P��?�^sNCE]�$�W����4���wʰ3֧�z��ө��qCY�Ę�S��t�qs��\�٥��
+A�s��v�.�0��XJײ�������[�\��I^Xױ�����j���e���l:���sST����}{���
+�j*+	��N� h�1��ڃZ�T2�1�
+p�yx�bv:��E-e�7W��.�\Ԣ8_�l��9
+���K�F%zF�^���I�T$��<3�|���&�NV
�3�e�꽳�c��
��k^��pi_�|Yt=��'ׅ�O��unoE*e=J.��ƿ�$��$��\o��}�>-=#B�8$R���M.��}8="L��G�k�u�"�U��Q�n�F6n�/�o}���8�jq��I��tٞm�v�;��	
+Ss�u$>s��(��5���o���Vu���N���@�T3k�|�5?��<0��[P��n�d'�37��\�� 6��(�V�X��eO��������9'o�LqZ^���h��$X�����K��M�&a�pZxN�U��'��Dc��t���ZA+ŁISſ�K&kXW��nR?���c���~�g|������g����
�'b�ifF����oގ�}/P�0;Qg0���hߟ��o�vy�N�gp�͇B
��N���w����⣃��p�@����a��iC|?�F2%�rrv��dA�
+�Y(�f�L��4PU�h�-��T9c��(b�

OF8��"����+,��O�Ԛ� 6��X�H�^&���P��;�pM�P0�rE�BGV�}մ���3+K����B�i^�5#��|�ZB��p�2mT檶�$�$� 9Ah�i��>n�.�N�aF�e�~	�o��=�X4��xT�5J7ɲW�%SA��o|�p�|\~S~Wֽ'Ý��A�A'3�QLh#���`qX�[���r�r���{ݤ޴�k�g-��r�B[,Pj��`X��f�߽~��F�Q3U��o��xW8�1A#�a���{k����g�w���L�V�N��Go�ïUև_��;�M���;�鳍�����l�ZL�$���^ ��މoo�O��N�%ӺF2`�[e�F�a�Nm���[U���\����h�O&���Z�ͬ�Xmv��WQZ����b���o��o4�E�I�nt�e�#]���������3������?(��!��*�N�Ձ�r��x�ī�.���j�g8��D�?+�3Rfz;���q=�9O����h�I�T_^�r�����W�,E���1�D��/q�WOէ�.�����=�=�J��@\Z��
+���z��x��B��?��Zo6c���>���>o_?�����#��b�����G���
+endstream
+endobj
+13 0 obj
+<</Type /FontDescriptor
+/FontName /LiberationSans
+/Flags 4
+/Ascent 905.27344
+/Descent -211.91406
+/StemV 45.898438
+/CapHeight 687.98828
+/ItalicAngle 0
+/FontBBox [-203.125 -303.22266 1050.29297 910.15625]
+/FontFile2 12 0 R>>
+endobj
+14 0 obj
+<</Type /Font
+/FontDescriptor 13 0 R
+/BaseFont /LiberationSans
+/Subtype /CIDFontType2
+/CIDToGIDMap /Identity
+/CIDSystemInfo <</Registry (Adobe)
+/Ordering (Identity)
+/Supplement 0>>
+/W [0 [365.23438 0 0 277.83203] 19 28 556.15234 36 [666.99219 0 722.16797 0 666.99219 0 0 0 277.83203 0 666.99219 556.15234 833.00781 722.16797 777.83203 666.99219 0 722.16797 666.99219 610.83984 722.16797 666.99219 0 666.99219] 66 68 556.15234 70 [500 556.15234 556.15234] 76 79 222.16797 85 [333.00781 0 277.83203 556.15234 500]]
+/DW 0>>
+endobj
+15 0 obj
+<</Filter /FlateDecode
+/Length 323>> stream
+x�]��j�0��y���E���������n�M�m�����o��-4����o�M&Q�<5Z9��Q��h���0��@�pS�$�J%�F�CgH���29ݏ�((�>|trv��G9^�DoV�U�Fw�U빝���
��1)K*���^:��
+endstream
+endobj
+6 0 obj
+<</Type /Font
+/Subtype /Type0
+/BaseFont /LiberationSans
+/Encoding /Identity-H
+/DescendantFonts [14 0 R]
+/ToUnicode 15 0 R>>
+endobj
+16 0 obj
+<</Length1 6608
+/Filter /FlateDecode
+/Length 4242>> stream
+x��9p[Uv缧'ɟHO�,d�=���,+�'��c˶$�qY��G����'�#'%|6��L�o�`KJX:�3��N��,a�;�)�0t��[�� n������yOr��v��t����{���sϽ�>�0
 c
+CR~��0��>8�	U�&Z�oxv%gtc���ޅi�,8��7����J�Дv��[-�O�>�c����,,@|
+o������5Q$�J,B'�c�~��-3�B3ə�h�=p>���W�	x
>�E�<���9��q���4��aK�%���0��E�cE�b.P�����"j�8,�q��"cs�4���%<�>ϐ��T��jL�Y�MA���[,>��g��ͼ��W0? �@Zq�\����G���W];{7��\��
߅��F�t3l��/�/�����m�W���2�2�5g��$��
+���t��۶n�������zZ[��M��6n��}����k\U���Ғb��.�XL�Ѱ*#=M��r�A��J��(�FdM����Tp)J��u��,�w��,FT1�FI7I�Iҝ�t_�D^l�g��D�=�$.��@����%ުšRYE��N�7g�#�����H�񐽹��V�u8�Y	s�f$�KsXވ*��{7�1�_�+�%���z=6�=��
+��"y�14*�\)����W�LQT⼊�JvK6��d�%2���J�H���H��r�#���A��!�M��wn��4�Z�Q��|�K��-R���T���U���li���Ғ]^�2��G<I[R xj�s���L
+U!*�� ��nB����]�U�F%�����_�!�Z`�4~��M���U�Rh�rF(�t~{�!e}��#!%��J�?�Qj��H�s�h3�ti�EΐZz�BoJҵ
+]G��VtV����g�u��U��t@��)�7���s�~p*������^���|�[�r�B����Ѐ��2����w���+�����R3N<�q}D�A���a^�)X���r5̳�0�*dN!�봅�m�G�^c��J�&�����{�#\߯_�h�#�C�K�l�Iȅ���]���;g��!'�N��t9#�cN�YS�1�ь撁U��@��S5����IhZjZBWxr����$uk�`u!�e���F*�b�j׭od����΀YkMu#���j����ϾGz�0sa�W���g'i�B�����=/�ߝ�Ӟ}v�Y:nM��d੟<�vt���vz����U��O~5;�����΢�s���2V�]������'.i�k���n��#٘a������:o��쯭����[��|��������~�����Wx�\�&��r�r�2k�Z��B��|�|��+/ϗU�������73��EwA���\W��o��7��
+��;ծ0�N8<	�׻��y��+��7������s��A���y�]�P**U�+�d�5M��RI	wI#[SmUւU"_��T�[��
+Lˠ������j�|}w�m�m)un���ޤ��gcA�zg����S����[����,yy:Cn�����)�+(h�6�2ym��h��z7
+�=c���u���:--����5B����{B��|�������d���e�Ŧ�u��ʊ5ъm�����m�L�`�32Ŷ�eȗ!�u�Eʎ��*�P�-[�bێY/X����d�[Y+\.�m�6^�#cw�ɰdg�&+�>�l��+^�VS�ʻ�j4�Zrf_
+��:ؖ�9ȇ��%Hna�A�'oz�1pB�c��E	�]p�*KɊtK��5���گ�&^�'^�'�`��x�Hk/q]�F�������m�>
�;
+w�I�PNZ�W�ܔى�M���v�F�:�^��"���������
+���R��RW��''ʄgN�LNDN0�'�8���L���q��m�����J�Ǿ[*}�T�U�0�̌��I�h�3��}�G��j��7�=	a��r���:E5F�u��� ;9.mFa��P�Ü�ܚ�>]
+:�Ꞡ)u�C�`��`�
+-��Tljlʑ,H�}�Q�9V�1�Al��Wy1G�A"*����~�
�ݟ�T���(#k1�1�Zۿ"�P�I�)���O!c��
+endstream
+endobj
+17 0 obj
+<</Type /FontDescriptor
+/FontName /LiberationSans-BoldItalic
+/Flags 68
+/Ascent 905.27344
+/Descent -211.91406
+/StemV 137.207031
+/CapHeight 687.98828
+/ItalicAngle -12
+/FontBBox [-208.98438 -303.22266 1128.41797 1029.78516]
+/FontFile2 16 0 R>>
+endobj
+18 0 obj
+<</Type /Font
+/FontDescriptor 17 0 R
+/BaseFont /LiberationSans-BoldItalic
+/Subtype /CIDFontType2
+/CIDToGIDMap /Identity
+/CIDSystemInfo <</Registry (Adobe)
+/Ordering (Identity)
+/Supplement 0>>
+/W [0 [365.23438 0 0 277.83203] 50 [777.83203] 68 72 556.15234 79 [277.83203] 85 [389.16016 0 0 0 556.15234]]
+/DW 0>>
+endobj
+19 0 obj
+<</Filter /FlateDecode
+/Length 259>> stream
+x�]��j�0���s��X���vA�b���}���6P��o��,[�@3'�sh�?�J:��V�
LR	���,Gq����ݍ��f��a_.��4�k�ừ�;����7+�J5��<�1?��r���
��酙W� �(;����ۏ^�7��"r���Z�jG�Ԍ��|5Pw��J��_�j��7�q�䧳�Ț@�"R�E*�H�<�c�*Q���TU�.E�k�s���W�%dv7�7k��l4lI���6A�/�*�
+endstream
+endobj
+8 0 obj
+<</Type /Font
+/Subtype /Type0
+/BaseFont /LiberationSans-BoldItalic
+/Encoding /Identity-H
+/DescendantFonts [18 0 R]
+/ToUnicode 19 0 R>>
+endobj
+xref
+0 20
+0000000000 65535 f 
+0000000015 00000 n 
+0000005387 00000 n 
+0000000154 00000 n 
+0000000191 00000 n 
+0000000267 00000 n 
+0000017875 00000 n 
+0000003396 00000 n 
+0000023255 00000 n 
+0000004182 00000 n 
+0000005668 00000 n 
+0000005724 00000 n 
+0000005773 00000 n 
+0000016705 00000 n 
+0000016944 00000 n 
+0000017481 00000 n 
+0000018014 00000 n 
+0000022342 00000 n 
+0000022599 00000 n 
+0000022925 00000 n 
+trailer
+<</Size 20
+/Root 11 0 R
+/Info 1 0 R>>
+startxref
+23405
+%%EOF

tokenizer

@@ -0,0 +1,3 @@
+��prefix_search�~^§|^%|^=|^—|^–|^\+(?![0-9])|^…|^……|^,|^:|^;|^\!|^\?|^¿|^؟|^¡|^\(|^\)|^\[|^\]|^\{|^\}|^<|^>|^_|^#|^\*|^&|^。|^？|^！|^，|^、|^；|^：|^～|^·|^।|^،|^۔|^؛|^٪|^\.\.+|^…|^\'|^"|^”|^“|^`|^‘|^´|^’|^‚|^,|^„|^»|^«|^「|^」|^『|^』|^（|^）|^〔|^〕|^【|^】|^《|^》|^〈|^〉|^\$|^£|^€|^¥|^฿|^US\$|^C\$|^A\$|^₽|^﷼|^₴|^₠|^₡|^₢|^₣|^₤|^₥|^₦|^₧|^₨|^₩|^₪|^₫|^€|^₭|^₮|^₯|^₰|^₱|^₲|^₳|^₴|^₵|^₶|^₷|^₸|^₹|^₺|^₻|^₼|^₽|^₾|^₿|^[\u00A6\u00A9\u00AE\u00B0\u0482\u058D\u058E\u060E\u060F\u06DE\u06E9\u06FD\u06FE\u07F6\u09FA\u0B70\u0BF3-\u0BF8\u0BFA\u0C7F\u0D4F\u0D79\u0F01-\u0F03\u0F13\u0F15-\u0F17\u0F1A-\u0F1F\u0F34\u0F36\u0F38\u0FBE-\u0FC5\u0FC7-\u0FCC\u0FCE\u0FCF\u0FD5-\u0FD8\u109E\u109F\u1390-\u1399\u1940\u19DE-\u19FF\u1B61-\u1B6A\u1B74-\u1B7C\u2100\u2101\u2103-\u2106\u2108\u2109\u2114\u2116\u2117\u211E-\u2123\u2125\u2127\u2129\u212E\u213A\u213B\u214A\u214C\u214D\u214F\u218A\u218B\u2195-\u2199\u219C-\u219F\u21A1\u21A2\u21A4\u21A5\u21A7-\u21AD\u21AF-\u21CD\u21D0\u21D1\u21D3\u21D5-\u21F3\u2300-\u2307\u230C-\u231F\u2322-\u2328\u232B-\u237B\u237D-\u239A\u23B4-\u23DB\u23E2-\u2426\u2440-\u244A\u249C-\u24E9\u2500-\u25B6\u25B8-\u25C0\u25C2-\u25F7\u2600-\u266E\u2670-\u2767\u2794-\u27BF\u2800-\u28FF\u2B00-\u2B2F\u2B45\u2B46\u2B4D-\u2B73\u2B76-\u2B95\u2B98-\u2BC8\u2BCA-\u2BFE\u2CE5-\u2CEA\u2E80-\u2E99\u2E9B-\u2EF3\u2F00-\u2FD5\u2FF0-\u2FFB\u3004\u3012\u3013\u3020\u3036\u3037\u303E\u303F\u3190\u3191\u3196-\u319F\u31C0-\u31E3\u3200-\u321E\u322A-\u3247\u3250\u3260-\u327F\u328A-\u32B0\u32C0-\u32FE\u3300-\u33FF\u4DC0-\u4DFF\uA490-\uA4C6\uA828-\uA82B\uA836\uA837\uA839\uAA77-\uAA79\uFDFD\uFFE4\uFFE8\uFFED\uFFEE\uFFFC\uFFFD\U00010137-\U0001013F\U00010179-\U00010189\U0001018C-\U0001018E\U00010190-\U0001019B\U000101A0\U000101D0-\U000101FC\U00010877\U00010878\U00010AC8\U0001173F\U00016B3C-\U00016B3F\U00016B45\U0001BC9C\U0001D000-\U0001D0F5\U0001D100-\U0001D126\U0001D129-\U0001D164\U0001D16A-\U0001D16C\U0001D183\U0001D184\U0001D18C-\U0001D1A9\U0001D1AE-\U0001D1E8\U0001D200-\U0001D241\U0001D245\U0001D300-\U0001D356\U0001D800-\U0001D9FF\U0001DA37-\U0001DA3A\U0001DA6D-\U0001DA74\U0001DA76-\U0001DA83\U0001DA85\U0001DA86\U0001ECAC\U0001F000-\U0001F02B\U0001F030-\U0001F093\U0001F0A0-\U0001F0AE\U0001F0B1-\U0001F0BF\U0001F0C1-\U0001F0CF\U0001F0D1-\U0001F0F5\U0001F110-\U0001F16B\U0001F170-\U0001F1AC\U0001F1E6-\U0001F202\U0001F210-\U0001F23B\U0001F240-\U0001F248\U0001F250\U0001F251\U0001F260-\U0001F265\U0001F300-\U0001F3FA\U0001F400-\U0001F6D4\U0001F6E0-\U0001F6EC\U0001F6F0-\U0001F6F9\U0001F700-\U0001F773\U0001F780-\U0001F7D8\U0001F800-\U0001F80B\U0001F810-\U0001F847\U0001F850-\U0001F859\U0001F860-\U0001F887\U0001F890-\U0001F8AD\U0001F900-\U0001F90B\U0001F910-\U0001F93E\U0001F940-\U0001F970\U0001F973-\U0001F976\U0001F97A\U0001F97C-\U0001F9A2\U0001F9B0-\U0001F9B9\U0001F9C0-\U0001F9C2\U0001F9D0-\U0001F9FF\U0001FA60-\U0001FA6D]�suffix_search�2y…$|……$|,$|:$|;$|\!$|\?$|¿$|؟$|¡$|\($|\)$|\[$|\]$|\{$|\}$|<$|>$|_$|#$|\*$|&$|。$|？$|！$|，$|、$|；$|：$|～$|·$|।$|،$|۔$|؛$|٪$|\.\.+$|…$|\'$|"$|”$|“$|`$|‘$|´$|’$|‚$|,$|„$|»$|«$|「$|」$|『$|』$|（$|）$|〔$|〕$|【$|】$|《$|》$|〈$|〉$|[\u00A6\u00A9\u00AE\u00B0\u0482\u058D\u058E\u060E\u060F\u06DE\u06E9\u06FD\u06FE\u07F6\u09FA\u0B70\u0BF3-\u0BF8\u0BFA\u0C7F\u0D4F\u0D79\u0F01-\u0F03\u0F13\u0F15-\u0F17\u0F1A-\u0F1F\u0F34\u0F36\u0F38\u0FBE-\u0FC5\u0FC7-\u0FCC\u0FCE\u0FCF\u0FD5-\u0FD8\u109E\u109F\u1390-\u1399\u1940\u19DE-\u19FF\u1B61-\u1B6A\u1B74-\u1B7C\u2100\u2101\u2103-\u2106\u2108\u2109\u2114\u2116\u2117\u211E-\u2123\u2125\u2127\u2129\u212E\u213A\u213B\u214A\u214C\u214D\u214F\u218A\u218B\u2195-\u2199\u219C-\u219F\u21A1\u21A2\u21A4\u21A5\u21A7-\u21AD\u21AF-\u21CD\u21D0\u21D1\u21D3\u21D5-\u21F3\u2300-\u2307\u230C-\u231F\u2322-\u2328\u232B-\u237B\u237D-\u239A\u23B4-\u23DB\u23E2-\u2426\u2440-\u244A\u249C-\u24E9\u2500-\u25B6\u25B8-\u25C0\u25C2-\u25F7\u2600-\u266E\u2670-\u2767\u2794-\u27BF\u2800-\u28FF\u2B00-\u2B2F\u2B45\u2B46\u2B4D-\u2B73\u2B76-\u2B95\u2B98-\u2BC8\u2BCA-\u2BFE\u2CE5-\u2CEA\u2E80-\u2E99\u2E9B-\u2EF3\u2F00-\u2FD5\u2FF0-\u2FFB\u3004\u3012\u3013\u3020\u3036\u3037\u303E\u303F\u3190\u3191\u3196-\u319F\u31C0-\u31E3\u3200-\u321E\u322A-\u3247\u3250\u3260-\u327F\u328A-\u32B0\u32C0-\u32FE\u3300-\u33FF\u4DC0-\u4DFF\uA490-\uA4C6\uA828-\uA82B\uA836\uA837\uA839\uAA77-\uAA79\uFDFD\uFFE4\uFFE8\uFFED\uFFEE\uFFFC\uFFFD\U00010137-\U0001013F\U00010179-\U00010189\U0001018C-\U0001018E\U00010190-\U0001019B\U000101A0\U000101D0-\U000101FC\U00010877\U00010878\U00010AC8\U0001173F\U00016B3C-\U00016B3F\U00016B45\U0001BC9C\U0001D000-\U0001D0F5\U0001D100-\U0001D126\U0001D129-\U0001D164\U0001D16A-\U0001D16C\U0001D183\U0001D184\U0001D18C-\U0001D1A9\U0001D1AE-\U0001D1E8\U0001D200-\U0001D241\U0001D245\U0001D300-\U0001D356\U0001D800-\U0001D9FF\U0001DA37-\U0001DA3A\U0001DA6D-\U0001DA74\U0001DA76-\U0001DA83\U0001DA85\U0001DA86\U0001ECAC\U0001F000-\U0001F02B\U0001F030-\U0001F093\U0001F0A0-\U0001F0AE\U0001F0B1-\U0001F0BF\U0001F0C1-\U0001F0CF\U0001F0D1-\U0001F0F5\U0001F110-\U0001F16B\U0001F170-\U0001F1AC\U0001F1E6-\U0001F202\U0001F210-\U0001F23B\U0001F240-\U0001F248\U0001F250\U0001F251\U0001F260-\U0001F265\U0001F300-\U0001F3FA\U0001F400-\U0001F6D4\U0001F6E0-\U0001F6EC\U0001F6F0-\U0001F6F9\U0001F700-\U0001F773\U0001F780-\U0001F7D8\U0001F800-\U0001F80B\U0001F810-\U0001F847\U0001F850-\U0001F859\U0001F860-\U0001F887\U0001F890-\U0001F8AD\U0001F900-\U0001F90B\U0001F910-\U0001F93E\U0001F940-\U0001F970\U0001F973-\U0001F976\U0001F97A\U0001F97C-\U0001F9A2\U0001F9B0-\U0001F9B9\U0001F9C0-\U0001F9C2\U0001F9D0-\U0001F9FF\U0001FA60-\U0001FA6D]$|'s$|'S$|’s$|’S$|—$|–$|(?<=[0-9])\+$|(?<=°[FfCcKk])\.$|(?<=[0-9])(?:\$|£|€|¥|฿|US\$|C\$|A\$|₽|﷼|₴|₠|₡|₢|₣|₤|₥|₦|₧|₨|₩|₪|₫|€|₭|₮|₯|₰|₱|₲|₳|₴|₵|₶|₷|₸|₹|₺|₻|₼|₽|₾|₿)$|(?<=[0-9])(?:km|km²|km³|m|m²|m³|dm|dm²|dm³|cm|cm²|cm³|mm|mm²|mm³|ha|µm|nm|yd|in|ft|kg|g|mg|µg|t|lb|oz|m/s|km/h|kmh|mph|hPa|Pa|mbar|mb|MB|kb|KB|gb|GB|tb|TB|T|G|M|K|%|км|км²|км³|м|м²|м³|дм|дм²|дм³|см|см²|см³|мм|мм²|мм³|нм|кг|г|мг|м/с|км/ч|кПа|Па|мбар|Кб|КБ|кб|Мб|МБ|мб|Гб|ГБ|гб|Тб|ТБ|тбكم|كم²|كم³|م|م²|م³|سم|سم²|سم³|مم|مم²|مم³|كم|غرام|جرام|جم|كغ|ملغ|كوب|اكواب)$|(?<=[0-9a-z\uFF41-\uFF5A\u00DF-\u00F6\u00F8-\u00FF\u0101\u0103\u0105\u0107\u0109\u010B\u010D\u010F\u0111\u0113\u0115\u0117\u0119\u011B\u011D\u011F\u0121\u0123\u0125\u0127\u0129\u012B\u012D\u012F\u0131\u0133\u0135\u0137\u0138\u013A\u013C\u013E\u0140\u0142\u0144\u0146\u0148\u0149\u014B\u014D\u014F\u0151\u0153\u0155\u0157\u0159\u015B\u015D\u015F\u0161\u0163\u0165\u0167\u0169\u016B\u016D\u016F\u0171\u0173\u0175\u0177\u017A\u017C\u017E\u017F\u0180\u0183\u0185\u0188\u018C\u018D\u0192\u0195\u0199-\u019B\u019E\u01A1\u01A3\u01A5\u01A8\u01AA\u01AB\u01AD\u01B0\u01B4\u01B6\u01B9\u01BA\u01BD-\u01BF\u01C6\u01C9\u01CC\u01CE\u01D0\u01D2\u01D4\u01D6\u01D8\u01DA\u01DC\u01DD\u01DF\u01E1\u01E3\u01E5\u01E7\u01E9\u01EB\u01ED\u01EF\u01F0\u01F3\u01F5\u01F9\u01FB\u01FD\u01FF\u0201\u0203\u0205\u0207\u0209\u020B\u020D\u020F\u0211\u0213\u0215\u0217\u0219\u021B\u021D\u021F\u0221\u0223\u0225\u0227\u0229\u022B\u022D\u022F\u0231\u0233-\u0239\u023C\u023F\u0240\u0242\u0247\u0249\u024B\u024D\u024F\u2C61\u2C65\u2C66\u2C68\u2C6A\u2C6C\u2C71\u2C73\u2C74\u2C76-\u2C7B\uA723\uA725\uA727\uA729\uA72B\uA72D\uA72F-\uA731\uA733\uA735\uA737\uA739\uA73B\uA73D\uA73F\uA741\uA743\uA745\uA747\uA749\uA74B\uA74D\uA74F\uA751\uA753\uA755\uA757\uA759\uA75B\uA75D\uA75F\uA761\uA763\uA765\uA767\uA769\uA76B\uA76D\uA76F\uA771-\uA778\uA77A\uA77C\uA77F\uA781\uA783\uA785\uA787\uA78C\uA78E\uA791\uA793-\uA795\uA797\uA799\uA79B\uA79D\uA79F\uA7A1\uA7A3\uA7A5\uA7A7\uA7A9\uA7AF\uA7B5\uA7B7\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E01\u1E03\u1E05\u1E07\u1E09\u1E0B\u1E0D\u1E0F\u1E11\u1E13\u1E15\u1E17\u1E19\u1E1B\u1E1D\u1E1F\u1E21\u1E23\u1E25\u1E27\u1E29\u1E2B\u1E2D\u1E2F\u1E31\u1E33\u1E35\u1E37\u1E39\u1E3B\u1E3D\u1E3F\u1E41\u1E43\u1E45\u1E47\u1E49\u1E4B\u1E4D\u1E4F\u1E51\u1E53\u1E55\u1E57\u1E59\u1E5B\u1E5D\u1E5F\u1E61\u1E63\u1E65\u1E67\u1E69\u1E6B\u1E6D\u1E6F\u1E71\u1E73\u1E75\u1E77\u1E79\u1E7B\u1E7D\u1E7F\u1E81\u1E83\u1E85\u1E87\u1E89\u1E8B\u1E8D\u1E8F\u1E91\u1E93\u1E95-\u1E9D\u1E9F\u1EA1\u1EA3\u1EA5\u1EA7\u1EA9\u1EAB\u1EAD\u1EAF\u1EB1\u1EB3\u1EB5\u1EB7\u1EB9\u1EBB\u1EBD\u1EBF\u1EC1\u1EC3\u1EC5\u1EC7\u1EC9\u1ECB\u1ECD\u1ECF\u1ED1\u1ED3\u1ED5\u1ED7\u1ED9\u1EDB\u1EDD\u1EDF\u1EE1\u1EE3\u1EE5\u1EE7\u1EE9\u1EEB\u1EED\u1EEF\u1EF1\u1EF3\u1EF5\u1EF7\u1EF9\u1EFB\u1EFD\u1EFFёа-яәөүҗңһα-ωάέίόώήύа-щюяіїєґѓѕјљњќѐѝ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F%²\-\+…|……|,|:|;|\!|\?|¿|؟|¡|\(|\)|\[|\]|\{|\}|<|>|_|#|\*|&|。|？|！|，|、|；|：|～|·|।|،|۔|؛|٪(?:\'"”“`‘´’‚,„»«「」『』（）〔〕【】《》〈〉)])\.$|(?<=[A-Z\uFF21-\uFF3A\u00C0-\u00D6\u00D8-\u00DE\u0100\u0102\u0104\u0106\u0108\u010A\u010C\u010E\u0110\u0112\u0114\u0116\u0118\u011A\u011C\u011E\u0120\u0122\u0124\u0126\u0128\u012A\u012C\u012E\u0130\u0132\u0134\u0136\u0139\u013B\u013D\u013F\u0141\u0143\u0145\u0147\u014A\u014C\u014E\u0150\u0152\u0154\u0156\u0158\u015A\u015C\u015E\u0160\u0162\u0164\u0166\u0168\u016A\u016C\u016E\u0170\u0172\u0174\u0176\u0178\u0179\u017B\u017D\u0181\u0182\u0184\u0186\u0187\u0189-\u018B\u018E-\u0191\u0193\u0194\u0196-\u0198\u019C\u019D\u019F\u01A0\u01A2\u01A4\u01A6\u01A7\u01A9\u01AC\u01AE\u01AF\u01B1-\u01B3\u01B5\u01B7\u01B8\u01BC\u01C4\u01C7\u01CA\u01CD\u01CF\u01D1\u01D3\u01D5\u01D7\u01D9\u01DB\u01DE\u01E0\u01E2\u01E4\u01E6\u01E8\u01EA\u01EC\u01EE\u01F1\u01F4\u01F6-\u01F8\u01FA\u01FC\u01FE\u0200\u0202\u0204\u0206\u0208\u020A\u020C\u020E\u0210\u0212\u0214\u0216\u0218\u021A\u021C\u021E\u0220\u0222\u0224\u0226\u0228\u022A\u022C\u022E\u0230\u0232\u023A\u023B\u023D\u023E\u0241\u0243-\u0246\u0248\u024A\u024C\u024E\u2C60\u2C62-\u2C64\u2C67\u2C69\u2C6B\u2C6D-\u2C70\u2C72\u2C75\u2C7E\u2C7F\uA722\uA724\uA726\uA728\uA72A\uA72C\uA72E\uA732\uA734\uA736\uA738\uA73A\uA73C\uA73E\uA740\uA742\uA744\uA746\uA748\uA74A\uA74C\uA74E\uA750\uA752\uA754\uA756\uA758\uA75A\uA75C\uA75E\uA760\uA762\uA764\uA766\uA768\uA76A\uA76C\uA76E\uA779\uA77B\uA77D\uA77E\uA780\uA782\uA784\uA786\uA78B\uA78D\uA790\uA792\uA796\uA798\uA79A\uA79C\uA79E\uA7A0\uA7A2\uA7A4\uA7A6\uA7A8\uA7AA-\uA7AE\uA7B0-\uA7B4\uA7B6\uA7B8\u1E00\u1E02\u1E04\u1E06\u1E08\u1E0A\u1E0C\u1E0E\u1E10\u1E12\u1E14\u1E16\u1E18\u1E1A\u1E1C\u1E1E\u1E20\u1E22\u1E24\u1E26\u1E28\u1E2A\u1E2C\u1E2E\u1E30\u1E32\u1E34\u1E36\u1E38\u1E3A\u1E3C\u1E3E\u1E40\u1E42\u1E44\u1E46\u1E48\u1E4A\u1E4C\u1E4E\u1E50\u1E52\u1E54\u1E56\u1E58\u1E5A\u1E5C\u1E5E\u1E60\u1E62\u1E64\u1E66\u1E68\u1E6A\u1E6C\u1E6E\u1E70\u1E72\u1E74\u1E76\u1E78\u1E7A\u1E7C\u1E7E\u1E80\u1E82\u1E84\u1E86\u1E88\u1E8A\u1E8C\u1E8E\u1E90\u1E92\u1E94\u1E9E\u1EA0\u1EA2\u1EA4\u1EA6\u1EA8\u1EAA\u1EAC\u1EAE\u1EB0\u1EB2\u1EB4\u1EB6\u1EB8\u1EBA\u1EBC\u1EBE\u1EC0\u1EC2\u1EC4\u1EC6\u1EC8\u1ECA\u1ECC\u1ECE\u1ED0\u1ED2\u1ED4\u1ED6\u1ED8\u1EDA\u1EDC\u1EDE\u1EE0\u1EE2\u1EE4\u1EE6\u1EE8\u1EEA\u1EEC\u1EEE\u1EF0\u1EF2\u1EF4\u1EF6\u1EF8\u1EFA\u1EFC\u1EFEЁА-ЯӘӨҮҖҢҺΑ-ΩΆΈΊΌΏΉΎА-ЩЮЯІЇЄҐЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F][A-Z\uFF21-\uFF3A\u00C0-\u00D6\u00D8-\u00DE\u0100\u0102\u0104\u0106\u0108\u010A\u010C\u010E\u0110\u0112\u0114\u0116\u0118\u011A\u011C\u011E\u0120\u0122\u0124\u0126\u0128\u012A\u012C\u012E\u0130\u0132\u0134\u0136\u0139\u013B\u013D\u013F\u0141\u0143\u0145\u0147\u014A\u014C\u014E\u0150\u0152\u0154\u0156\u0158\u015A\u015C\u015E\u0160\u0162\u0164\u0166\u0168\u016A\u016C\u016E\u0170\u0172\u0174\u0176\u0178\u0179\u017B\u017D\u0181\u0182\u0184\u0186\u0187\u0189-\u018B\u018E-\u0191\u0193\u0194\u0196-\u0198\u019C\u019D\u019F\u01A0\u01A2\u01A4\u01A6\u01A7\u01A9\u01AC\u01AE\u01AF\u01B1-\u01B3\u01B5\u01B7\u01B8\u01BC\u01C4\u01C7\u01CA\u01CD\u01CF\u01D1\u01D3\u01D5\u01D7\u01D9\u01DB\u01DE\u01E0\u01E2\u01E4\u01E6\u01E8\u01EA\u01EC\u01EE\u01F1\u01F4\u01F6-\u01F8\u01FA\u01FC\u01FE\u0200\u0202\u0204\u0206\u0208\u020A\u020C\u020E\u0210\u0212\u0214\u0216\u0218\u021A\u021C\u021E\u0220\u0222\u0224\u0226\u0228\u022A\u022C\u022E\u0230\u0232\u023A\u023B\u023D\u023E\u0241\u0243-\u0246\u0248\u024A\u024C\u024E\u2C60\u2C62-\u2C64\u2C67\u2C69\u2C6B\u2C6D-\u2C70\u2C72\u2C75\u2C7E\u2C7F\uA722\uA724\uA726\uA728\uA72A\uA72C\uA72E\uA732\uA734\uA736\uA738\uA73A\uA73C\uA73E\uA740\uA742\uA744\uA746\uA748\uA74A\uA74C\uA74E\uA750\uA752\uA754\uA756\uA758\uA75A\uA75C\uA75E\uA760\uA762\uA764\uA766\uA768\uA76A\uA76C\uA76E\uA779\uA77B\uA77D\uA77E\uA780\uA782\uA784\uA786\uA78B\uA78D\uA790\uA792\uA796\uA798\uA79A\uA79C\uA79E\uA7A0\uA7A2\uA7A4\uA7A6\uA7A8\uA7AA-\uA7AE\uA7B0-\uA7B4\uA7B6\uA7B8\u1E00\u1E02\u1E04\u1E06\u1E08\u1E0A\u1E0C\u1E0E\u1E10\u1E12\u1E14\u1E16\u1E18\u1E1A\u1E1C\u1E1E\u1E20\u1E22\u1E24\u1E26\u1E28\u1E2A\u1E2C\u1E2E\u1E30\u1E32\u1E34\u1E36\u1E38\u1E3A\u1E3C\u1E3E\u1E40\u1E42\u1E44\u1E46\u1E48\u1E4A\u1E4C\u1E4E\u1E50\u1E52\u1E54\u1E56\u1E58\u1E5A\u1E5C\u1E5E\u1E60\u1E62\u1E64\u1E66\u1E68\u1E6A\u1E6C\u1E6E\u1E70\u1E72\u1E74\u1E76\u1E78\u1E7A\u1E7C\u1E7E\u1E80\u1E82\u1E84\u1E86\u1E88\u1E8A\u1E8C\u1E8E\u1E90\u1E92\u1E94\u1E9E\u1EA0\u1EA2\u1EA4\u1EA6\u1EA8\u1EAA\u1EAC\u1EAE\u1EB0\u1EB2\u1EB4\u1EB6\u1EB8\u1EBA\u1EBC\u1EBE\u1EC0\u1EC2\u1EC4\u1EC6\u1EC8\u1ECA\u1ECC\u1ECE\u1ED0\u1ED2\u1ED4\u1ED6\u1ED8\u1EDA\u1EDC\u1EDE\u1EE0\u1EE2\u1EE4\u1EE6\u1EE8\u1EEA\u1EEC\u1EEE\u1EF0\u1EF2\u1EF4\u1EF6\u1EF8\u1EFA\u1EFC\u1EFEЁА-ЯӘӨҮҖҢҺΑ-ΩΆΈΊΌΏΉΎА-ЩЮЯІЇЄҐЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])\.$�infix_finditer�>�\.\.+|…|[\u00A6\u00A9\u00AE\u00B0\u0482\u058D\u058E\u060E\u060F\u06DE\u06E9\u06FD\u06FE\u07F6\u09FA\u0B70\u0BF3-\u0BF8\u0BFA\u0C7F\u0D4F\u0D79\u0F01-\u0F03\u0F13\u0F15-\u0F17\u0F1A-\u0F1F\u0F34\u0F36\u0F38\u0FBE-\u0FC5\u0FC7-\u0FCC\u0FCE\u0FCF\u0FD5-\u0FD8\u109E\u109F\u1390-\u1399\u1940\u19DE-\u19FF\u1B61-\u1B6A\u1B74-\u1B7C\u2100\u2101\u2103-\u2106\u2108\u2109\u2114\u2116\u2117\u211E-\u2123\u2125\u2127\u2129\u212E\u213A\u213B\u214A\u214C\u214D\u214F\u218A\u218B\u2195-\u2199\u219C-\u219F\u21A1\u21A2\u21A4\u21A5\u21A7-\u21AD\u21AF-\u21CD\u21D0\u21D1\u21D3\u21D5-\u21F3\u2300-\u2307\u230C-\u231F\u2322-\u2328\u232B-\u237B\u237D-\u239A\u23B4-\u23DB\u23E2-\u2426\u2440-\u244A\u249C-\u24E9\u2500-\u25B6\u25B8-\u25C0\u25C2-\u25F7\u2600-\u266E\u2670-\u2767\u2794-\u27BF\u2800-\u28FF\u2B00-\u2B2F\u2B45\u2B46\u2B4D-\u2B73\u2B76-\u2B95\u2B98-\u2BC8\u2BCA-\u2BFE\u2CE5-\u2CEA\u2E80-\u2E99\u2E9B-\u2EF3\u2F00-\u2FD5\u2FF0-\u2FFB\u3004\u3012\u3013\u3020\u3036\u3037\u303E\u303F\u3190\u3191\u3196-\u319F\u31C0-\u31E3\u3200-\u321E\u322A-\u3247\u3250\u3260-\u327F\u328A-\u32B0\u32C0-\u32FE\u3300-\u33FF\u4DC0-\u4DFF\uA490-\uA4C6\uA828-\uA82B\uA836\uA837\uA839\uAA77-\uAA79\uFDFD\uFFE4\uFFE8\uFFED\uFFEE\uFFFC\uFFFD\U00010137-\U0001013F\U00010179-\U00010189\U0001018C-\U0001018E\U00010190-\U0001019B\U000101A0\U000101D0-\U000101FC\U00010877\U00010878\U00010AC8\U0001173F\U00016B3C-\U00016B3F\U00016B45\U0001BC9C\U0001D000-\U0001D0F5\U0001D100-\U0001D126\U0001D129-\U0001D164\U0001D16A-\U0001D16C\U0001D183\U0001D184\U0001D18C-\U0001D1A9\U0001D1AE-\U0001D1E8\U0001D200-\U0001D241\U0001D245\U0001D300-\U0001D356\U0001D800-\U0001D9FF\U0001DA37-\U0001DA3A\U0001DA6D-\U0001DA74\U0001DA76-\U0001DA83\U0001DA85\U0001DA86\U0001ECAC\U0001F000-\U0001F02B\U0001F030-\U0001F093\U0001F0A0-\U0001F0AE\U0001F0B1-\U0001F0BF\U0001F0C1-\U0001F0CF\U0001F0D1-\U0001F0F5\U0001F110-\U0001F16B\U0001F170-\U0001F1AC\U0001F1E6-\U0001F202\U0001F210-\U0001F23B\U0001F240-\U0001F248\U0001F250\U0001F251\U0001F260-\U0001F265\U0001F300-\U0001F3FA\U0001F400-\U0001F6D4\U0001F6E0-\U0001F6EC\U0001F6F0-\U0001F6F9\U0001F700-\U0001F773\U0001F780-\U0001F7D8\U0001F800-\U0001F80B\U0001F810-\U0001F847\U0001F850-\U0001F859\U0001F860-\U0001F887\U0001F890-\U0001F8AD\U0001F900-\U0001F90B\U0001F910-\U0001F93E\U0001F940-\U0001F970\U0001F973-\U0001F976\U0001F97A\U0001F97C-\U0001F9A2\U0001F9B0-\U0001F9B9\U0001F9C0-\U0001F9C2\U0001F9D0-\U0001F9FF\U0001FA60-\U0001FA6D]|(?<=[0-9])[+\-\*^](?=[0-9-])|(?<=[a-z\uFF41-\uFF5A\u00DF-\u00F6\u00F8-\u00FF\u0101\u0103\u0105\u0107\u0109\u010B\u010D\u010F\u0111\u0113\u0115\u0117\u0119\u011B\u011D\u011F\u0121\u0123\u0125\u0127\u0129\u012B\u012D\u012F\u0131\u0133\u0135\u0137\u0138\u013A\u013C\u013E\u0140\u0142\u0144\u0146\u0148\u0149\u014B\u014D\u014F\u0151\u0153\u0155\u0157\u0159\u015B\u015D\u015F\u0161\u0163\u0165\u0167\u0169\u016B\u016D\u016F\u0171\u0173\u0175\u0177\u017A\u017C\u017E\u017F\u0180\u0183\u0185\u0188\u018C\u018D\u0192\u0195\u0199-\u019B\u019E\u01A1\u01A3\u01A5\u01A8\u01AA\u01AB\u01AD\u01B0\u01B4\u01B6\u01B9\u01BA\u01BD-\u01BF\u01C6\u01C9\u01CC\u01CE\u01D0\u01D2\u01D4\u01D6\u01D8\u01DA\u01DC\u01DD\u01DF\u01E1\u01E3\u01E5\u01E7\u01E9\u01EB\u01ED\u01EF\u01F0\u01F3\u01F5\u01F9\u01FB\u01FD\u01FF\u0201\u0203\u0205\u0207\u0209\u020B\u020D\u020F\u0211\u0213\u0215\u0217\u0219\u021B\u021D\u021F\u0221\u0223\u0225\u0227\u0229\u022B\u022D\u022F\u0231\u0233-\u0239\u023C\u023F\u0240\u0242\u0247\u0249\u024B\u024D\u024F\u2C61\u2C65\u2C66\u2C68\u2C6A\u2C6C\u2C71\u2C73\u2C74\u2C76-\u2C7B\uA723\uA725\uA727\uA729\uA72B\uA72D\uA72F-\uA731\uA733\uA735\uA737\uA739\uA73B\uA73D\uA73F\uA741\uA743\uA745\uA747\uA749\uA74B\uA74D\uA74F\uA751\uA753\uA755\uA757\uA759\uA75B\uA75D\uA75F\uA761\uA763\uA765\uA767\uA769\uA76B\uA76D\uA76F\uA771-\uA778\uA77A\uA77C\uA77F\uA781\uA783\uA785\uA787\uA78C\uA78E\uA791\uA793-\uA795\uA797\uA799\uA79B\uA79D\uA79F\uA7A1\uA7A3\uA7A5\uA7A7\uA7A9\uA7AF\uA7B5\uA7B7\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E01\u1E03\u1E05\u1E07\u1E09\u1E0B\u1E0D\u1E0F\u1E11\u1E13\u1E15\u1E17\u1E19\u1E1B\u1E1D\u1E1F\u1E21\u1E23\u1E25\u1E27\u1E29\u1E2B\u1E2D\u1E2F\u1E31\u1E33\u1E35\u1E37\u1E39\u1E3B\u1E3D\u1E3F\u1E41\u1E43\u1E45\u1E47\u1E49\u1E4B\u1E4D\u1E4F\u1E51\u1E53\u1E55\u1E57\u1E59\u1E5B\u1E5D\u1E5F\u1E61\u1E63\u1E65\u1E67\u1E69\u1E6B\u1E6D\u1E6F\u1E71\u1E73\u1E75\u1E77\u1E79\u1E7B\u1E7D\u1E7F\u1E81\u1E83\u1E85\u1E87\u1E89\u1E8B\u1E8D\u1E8F\u1E91\u1E93\u1E95-\u1E9D\u1E9F\u1EA1\u1EA3\u1EA5\u1EA7\u1EA9\u1EAB\u1EAD\u1EAF\u1EB1\u1EB3\u1EB5\u1EB7\u1EB9\u1EBB\u1EBD\u1EBF\u1EC1\u1EC3\u1EC5\u1EC7\u1EC9\u1ECB\u1ECD\u1ECF\u1ED1\u1ED3\u1ED5\u1ED7\u1ED9\u1EDB\u1EDD\u1EDF\u1EE1\u1EE3\u1EE5\u1EE7\u1EE9\u1EEB\u1EED\u1EEF\u1EF1\u1EF3\u1EF5\u1EF7\u1EF9\u1EFB\u1EFD\u1EFFёа-яәөүҗңһα-ωάέίόώήύа-щюяіїєґѓѕјљњќѐѝ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F\'"”“`‘´’‚,„»«「」『』（）〔〕【】《》〈〉])\.(?=[A-Z\uFF21-\uFF3A\u00C0-\u00D6\u00D8-\u00DE\u0100\u0102\u0104\u0106\u0108\u010A\u010C\u010E\u0110\u0112\u0114\u0116\u0118\u011A\u011C\u011E\u0120\u0122\u0124\u0126\u0128\u012A\u012C\u012E\u0130\u0132\u0134\u0136\u0139\u013B\u013D\u013F\u0141\u0143\u0145\u0147\u014A\u014C\u014E\u0150\u0152\u0154\u0156\u0158\u015A\u015C\u015E\u0160\u0162\u0164\u0166\u0168\u016A\u016C\u016E\u0170\u0172\u0174\u0176\u0178\u0179\u017B\u017D\u0181\u0182\u0184\u0186\u0187\u0189-\u018B\u018E-\u0191\u0193\u0194\u0196-\u0198\u019C\u019D\u019F\u01A0\u01A2\u01A4\u01A6\u01A7\u01A9\u01AC\u01AE\u01AF\u01B1-\u01B3\u01B5\u01B7\u01B8\u01BC\u01C4\u01C7\u01CA\u01CD\u01CF\u01D1\u01D3\u01D5\u01D7\u01D9\u01DB\u01DE\u01E0\u01E2\u01E4\u01E6\u01E8\u01EA\u01EC\u01EE\u01F1\u01F4\u01F6-\u01F8\u01FA\u01FC\u01FE\u0200\u0202\u0204\u0206\u0208\u020A\u020C\u020E\u0210\u0212\u0214\u0216\u0218\u021A\u021C\u021E\u0220\u0222\u0224\u0226\u0228\u022A\u022C\u022E\u0230\u0232\u023A\u023B\u023D\u023E\u0241\u0243-\u0246\u0248\u024A\u024C\u024E\u2C60\u2C62-\u2C64\u2C67\u2C69\u2C6B\u2C6D-\u2C70\u2C72\u2C75\u2C7E\u2C7F\uA722\uA724\uA726\uA728\uA72A\uA72C\uA72E\uA732\uA734\uA736\uA738\uA73A\uA73C\uA73E\uA740\uA742\uA744\uA746\uA748\uA74A\uA74C\uA74E\uA750\uA752\uA754\uA756\uA758\uA75A\uA75C\uA75E\uA760\uA762\uA764\uA766\uA768\uA76A\uA76C\uA76E\uA779\uA77B\uA77D\uA77E\uA780\uA782\uA784\uA786\uA78B\uA78D\uA790\uA792\uA796\uA798\uA79A\uA79C\uA79E\uA7A0\uA7A2\uA7A4\uA7A6\uA7A8\uA7AA-\uA7AE\uA7B0-\uA7B4\uA7B6\uA7B8\u1E00\u1E02\u1E04\u1E06\u1E08\u1E0A\u1E0C\u1E0E\u1E10\u1E12\u1E14\u1E16\u1E18\u1E1A\u1E1C\u1E1E\u1E20\u1E22\u1E24\u1E26\u1E28\u1E2A\u1E2C\u1E2E\u1E30\u1E32\u1E34\u1E36\u1E38\u1E3A\u1E3C\u1E3E\u1E40\u1E42\u1E44\u1E46\u1E48\u1E4A\u1E4C\u1E4E\u1E50\u1E52\u1E54\u1E56\u1E58\u1E5A\u1E5C\u1E5E\u1E60\u1E62\u1E64\u1E66\u1E68\u1E6A\u1E6C\u1E6E\u1E70\u1E72\u1E74\u1E76\u1E78\u1E7A\u1E7C\u1E7E\u1E80\u1E82\u1E84\u1E86\u1E88\u1E8A\u1E8C\u1E8E\u1E90\u1E92\u1E94\u1E9E\u1EA0\u1EA2\u1EA4\u1EA6\u1EA8\u1EAA\u1EAC\u1EAE\u1EB0\u1EB2\u1EB4\u1EB6\u1EB8\u1EBA\u1EBC\u1EBE\u1EC0\u1EC2\u1EC4\u1EC6\u1EC8\u1ECA\u1ECC\u1ECE\u1ED0\u1ED2\u1ED4\u1ED6\u1ED8\u1EDA\u1EDC\u1EDE\u1EE0\u1EE2\u1EE4\u1EE6\u1EE8\u1EEA\u1EEC\u1EEE\u1EF0\u1EF2\u1EF4\u1EF6\u1EF8\u1EFA\u1EFC\u1EFEЁА-ЯӘӨҮҖҢҺΑ-ΩΆΈΊΌΏΉΎА-ЩЮЯІЇЄҐЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F\'"”“`‘´’‚,„»«「」『』（）〔〕【】《》〈〉])|(?<=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F]),(?=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])|(?<=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])(?:-|–|—|--|---|——|~)(?=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])|(?<=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F0-9])[:<>=/](?=[A-Za-z\uFF21-\uFF3A\uFF41-\uFF5A\u00C0-\u00D6\u00D8-\u00F6\u00F8-\u00FF\u0100-\u017F\u0180-\u01BF\u01C4-\u024F\u2C60-\u2C7B\u2C7E\u2C7F\uA722-\uA76F\uA771-\uA787\uA78B-\uA78E\uA790-\uA7B9\uA7FA\uAB30-\uAB5A\uAB60-\uAB64\u0250-\u02AF\u1D00-\u1D25\u1D6B-\u1D77\u1D79-\u1D9A\u1E00-\u1EFFёа-яЁА-ЯәөүҗңһӘӨҮҖҢҺα-ωάέίόώήύΑ-ΩΆΈΊΌΏΉΎа-щюяіїєґА-ЩЮЯІЇЄҐѓѕјљњќѐѝЃЅЈЉЊЌЀЍ\u1200-\u137F\u0980-\u09FF\u0591-\u05F4\uFB1D-\uFB4F\u0620-\u064A\u066E-\u06D5\u06E5-\u06FF\u0750-\u077F\u08A0-\u08BD\uFB50-\uFBB1\uFBD3-\uFD3D\uFD50-\uFDC7\uFDF0-\uFDFB\uFE70-\uFEFC\U0001EE00-\U0001EEBB\u0D80-\u0DFF\u0900-\u097F\u0C80-\u0CFF\u0B80-\u0BFF\u0C00-\u0C7F\uAC00-\uD7AF\u1100-\u11FF\u3040-\u309F\u30A0-\u30FFー\u4E00-\u62FF\u6300-\u77FF\u7800-\u8CFF\u8D00-\u9FFF\u3400-\u4DBF\U00020000-\U000215FF\U00021600-\U000230FF\U00023100-\U000245FF\U00024600-\U000260FF\U00026100-\U000275FF\U00027600-\U000290FF\U00029100-\U0002A6DF\U0002A700-\U0002B73F\U0002B740-\U0002B81F\U0002B820-\U0002CEAF\U0002CEB0-\U0002EBEF\u2E80-\u2EFF\u2F00-\u2FDF\u2FF0-\u2FFF\u3000-\u303F\u31C0-\u31EF\u3200-\u32FF\u3300-\u33FF\uF900-\uFAFF\uFE30-\uFE4F\U0001F200-\U0001F2FF\U0002F800-\U0002FA1F])�token_match��url_match�
+��A�
+� ��A� �'��A�'�''��A�''�(*_*)��A�(*_*)�(-8��A�(-8�(-:��A�(-:�(-;��A�(-;�(-_-)��A�(-_-)�(._.)��A�(._.)�(:��A�(:�(;��A�(;�(=��A�(=�(>_<)��A�(>_<)�(^_^)��A�(^_^)�(o:��A�(o:�(¬_¬)��A�(¬_¬)�(ಠ_ಠ)��A�(ಠ_ಠ)�(╯°□°）╯︵┻━┻��A�(╯°□°）╯︵┻━┻�)-:��A�)-:�):��A�):�-_-��A�-_-�-__-��A�-__-�._.��A�._.�0.0��A�0.0�0.o��A�0.o�0_0��A�0_0�0_o��A�0_o�8)��A�8)�8-)��A�8-)�8-D��A�8-D�8D��A�8D�:'(��A�:'(�:')��A�:')�:'-(��A�:'-(�:'-)��A�:'-)�:(��A�:(�:((��A�:((�:(((��A�:(((�:()��A�:()�:)��A�:)�:))��A�:))�:)))��A�:)))�:*��A�:*�:-(��A�:-(�:-((��A�:-((�:-(((��A�:-(((�:-)��A�:-)�:-))��A�:-))�:-)))��A�:-)))�:-*��A�:-*�:-/��A�:-/�:-0��A�:-0�:-3��A�:-3�:->��A�:->�:-D��A�:-D�:-O��A�:-O�:-P��A�:-P�:-X��A�:-X�:-]��A�:-]�:-o��A�:-o�:-p��A�:-p�:-x��A�:-x�:-|��A�:-|�:-}��A�:-}�:/��A�:/�:0��A�:0�:1��A�:1�:3��A�:3�:>��A�:>�:D��A�:D�:O��A�:O�:P��A�:P�:X��A�:X�:]��A�:]�:o��A�:o�:o)��A�:o)�:p��A�:p�:x��A�:x�:|��A�:|�:}��A�:}�;)��A�;)�;-)��A�;-)�;-D��A�;-D�;D��A�;D�;_;��A�;_;�<.<��A�<.<�</3��A�</3�<3��A�<3�<33��A�<33�<333��A�<333�<space>��A�<space>�=(��A�=(�=)��A�=)�=/��A�=/�=3��A�=3�=D��A�=D�=[��A�=[�=]��A�=]�=|��A�=|�>.<��A�>.<�>.>��A�>.>�>:(��A�>:(�>:o��A�>:o�><(((*>��A�><(((*>�@_@��A�@_@�C++��A�C++�O.O��A�O.O�O.o��A�O.o�O_O��A�O_O�O_o��A�O_o�V.V��A�V.V�V_V��A�V_V�XD��A�XD�XDD��A�XDD�[-:��A�[-:�[:��A�[:�[=��A�[=�\")��A�\")�\n��A�\n�\t��A�\t�]=��A�]=�^_^��A�^_^�^__^��A�^__^�^___^��A�^___^�a.��A�a.�b.��A�b.�c.��A�c.�d.��A�d.�e.��A�e.�f.��A�f.�g.��A�g.�h.��A�h.�i.��A�i.�j.��A�j.�k.��A�k.�l.��A�l.�m.��A�m.�n.��A�n.�o.��A�o.�o.0��A�o.0�o.O��A�o.O�o.o��A�o.o�o_0��A�o_0�o_O��A�o_O�o_o��A�o_o�p.��A�p.�q.��A�q.�r.��A�r.�s.��A�s.�t.��A�t.�u.��A�u.�v.��A�v.�v.v��A�v.v�v_v��A�v_v�w.��A�w.�x.��A�x.�xD��A�xD�xDD��A�xDD�y.��A�y.�z.��A�z.� ��A� C�  �¯\(ツ)/¯��A�¯\(ツ)/¯�°C.��A�°�A�C�A�.�°F.��A�°�A�F�A�.�°K.��A�°�A�K�A�.�°c.��A�°�A�c�A�.�°f.��A�°�A�f�A�.�°k.��A�°�A�k�A�.�ä.��A�ä.�ö.��A�ö.�ü.��A�ü.�ಠ_ಠ��A�ಠ_ಠ�ಠ︵ಠ��A�ಠ︵ಠ�—��A�—�faster_heuristics�

transformer/cfg

@@ -0,0 +1,3 @@
+{
+  "max_batch_items":4096
+}

transformer/model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5982917e5a22ef833c1b3c4aa1d491facf793e9831fd35d4322d5e8283a0878
+size 1134411414

vocab/key2row

@@ -0,0 +1 @@
+�

vocab/lookups.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76be8b528d0075f7aae98d6fa57a6d3c83ae480a8469e668d7b0af968995ac71
+size 1

vocab/strings.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f821bae84c6dc3934ba189b4ccad8870917ae2ede66c14c74413a11bcdcab0b2
+size 16326872

vocab/vectors.cfg

@@ -0,0 +1,3 @@
+{
+  "mode":"default"
+}

xx_pipeline-any-py3-none-any.whl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d039e768a6467b34e112428a18f8877bfcb348e566fa191719079b3bb7c9099
+size 1021523182