Add BERTopic model

ctfidf.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c7737d0ebc987d81b8c5b2d1b12c3338ae016158e88eaa8e82b51a42a9ebe39
-size 343348
+oid sha256:74c020b28cb478ead05778d20662c73e6c8345d73abda5be9c0aa0f4255ce89a
+size 342612

ctfidf_config.json

@@ -25,28 +25,28 @@
     },
     "vocab": {
       "ensure": 650,
-      "work": 2071,
+      "work": 2070,
       "requirements": 1560,
       "specie": 1755,
       "ed": 618,
       "identify": 877,
-      "ways": 2041,
+      "ways": 2040,
       "optimism": 1245,
-      "usage": 1982,
+      "usage": 1981,
       "material": 1114,
       "resources": 1569,
       "like": 1038,
       "items": 966,
       "electricity": 623,
-      "water": 2037,
-      "various": 2002,
+      "water": 2036,
+      "various": 2001,
       "tasks": 1868,
       "activities": 31,
       "processes": 1408,
       "check": 289,
       "pills": 1322,
       "leakage": 1012,
-      "workstation": 2077,
+      "workstation": 2076,
       "potential": 1363,
       "risk": 1596,
       "electrical": 622,
@@ -57,17 +57,17 @@
       "appliances": 97,
       "properly": 1434,
       "sanctioning": 1626,
-      "turned": 1961,
-      "use": 1983,
+      "turned": 1960,
+      "use": 1982,
       "recyclable": 1506,
       "non": 1205,
-      "waste": 2034,
+      "waste": 2033,
       "generate": 784,
       "aggregate": 65,
       "respective": 1572,
       "categories": 260,
       "communicate": 347,
-      "timely": 1914,
+      "timely": 1913,
       "clearly": 315,
       "colleagues": 334,
       "customers": 472,
@@ -81,9 +81,9 @@
       "accounts": 15,
       "accessories": 6,
       "smooth": 1729,
-      "working": 2073,
-      "verbal": 2010,
-      "written": 2082,
+      "working": 2072,
+      "verbal": 2009,
+      "written": 2081,
       "organisation": 1251,
       "policies": 1348,
       "procedures": 1406,
@@ -118,12 +118,12 @@
       "list": 1044,
       "new": 1202,
       "schemes": 1642,
-      "vehicle": 2006,
+      "vehicle": 2005,
       "advice": 58,
       "interact": 945,
       "superior": 1831,
       "competent": 354,
-      "user": 1985,
+      "user": 1984,
       "individual": 908,
       "job": 968,
       "able": 1,
@@ -139,7 +139,7 @@
       "manager": 1093,
       "appropriate": 107,
       "action": 27,
-      "update": 1980,
+      "update": 1979,
       "regarding": 1518,
       "overall": 1267,
       "process": 1407,
@@ -148,7 +148,7 @@
       "brief": 216,
       "handle": 829,
       "leads": 1010,
-      "walk": 2024,
+      "walk": 2023,
       "marketing": 1107,
       "standard": 1771,
       "operating": 1236,
@@ -163,7 +163,7 @@
       "features": 726,
       "advantages": 57,
       "far": 717,
-      "vehicles": 2007,
+      "vehicles": 2006,
       "demonstration": 510,
       "physical": 1315,
       "operation": 1237,
@@ -179,7 +179,7 @@
       "current": 470,
       "available": 153,
       "record": 1500,
-      "track": 1928,
+      "track": 1927,
       "delivered": 503,
       "management": 1092,
       "force": 740,
@@ -232,8 +232,8 @@
       "area": 111,
       "kept": 976,
       "clean": 309,
-      "tidy": 1907,
-      "works": 2075,
+      "tidy": 1906,
+      "works": 2074,
       "assigned": 134,
       "agreed": 67,
       "quality": 1458,
@@ -242,16 +242,16 @@
       "taken": 1857,
       "implement": 886,
       "guide": 820,
-      "time": 1912,
+      "time": 1911,
       "cost": 445,
       "actively": 30,
-      "train": 1931,
+      "train": 1930,
       "skill": 1723,
       "level": 1026,
       "develop": 531,
-      "understand": 1967,
+      "understand": 1966,
       "completion": 362,
-      "validity": 1993,
+      "validity": 1992,
       "problem": 1403,
       "accurately": 18,
       "di": 539,
@@ -265,7 +265,7 @@
       "supervise": 1833,
       "routine": 1612,
       "cleaning": 311,
-      "tools": 1920,
+      "tools": 1919,
       "machine": 1072,
       "equipment": 661,
       "periodically": 1302,
@@ -277,7 +277,7 @@
       "disposal": 563,
       "healthy": 846,
       "hygienic": 874,
-      "workplace": 2074,
+      "workplace": 2073,
       "ordinated": 1250,
       "members": 1134,
       "integrate": 942,
@@ -320,7 +320,7 @@
       "establish": 668,
       "direct": 547,
       "contact": 412,
-      "withthe": 2070,
+      "withthe": 2069,
       "incorporate": 903,
       "methods": 1145,
       "following": 738,
@@ -328,11 +328,11 @@
       "bank": 168,
       "er": 662,
       "plan": 1331,
-      "workshop": 2076,
+      "workshop": 2075,
       "inform": 913,
       "existing": 687,
       "promote": 1427,
-      "value": 1994,
+      "value": 1993,
       "services": 1685,
       "program": 1421,
       "assistance": 136,
@@ -387,7 +387,7 @@
       "calling": 235,
       "companies": 351,
       "terence": 1887,
-      "using": 1987,
+      "using": 1986,
       "internal": 948,
       "engine": 644,
       "ice": 875,
@@ -443,7 +443,7 @@
       "forms": 748,
       "reference": 1512,
       "regular": 1521,
-      "training": 1932,
+      "training": 1931,
       "planned": 1332,
       "conducted": 383,
       "recorded": 1501,
@@ -495,7 +495,7 @@
       "sign": 1708,
       "cancer": 238,
       "constitutional": 405,
-      "values": 1995,
+      "values": 1994,
       "rights": 1592,
       "duties": 607,
       "citizenship": 303,
@@ -512,7 +512,7 @@
       "knowledge": 988,
       "communicating": 349,
       "public": 1448,
-      "writing": 2081,
+      "writing": 2080,
       "select": 1665,
       "reliable": 1535,
       "products": 1419,
@@ -521,7 +521,7 @@
       "cards": 248,
       "loans": 1052,
       "online": 1230,
-      "transactions": 1933,
+      "transactions": 1932,
       "network": 1201,
       "collaboration": 332,
       "entrepreneurship": 656,
@@ -532,12 +532,12 @@
       "agencies": 61,
       "enquire": 649,
       "plans": 1334,
-      "used": 1984,
+      "used": 1983,
       "seek": 1662,
       "permission": 1303,
       "reason": 1485,
       "need": 1197,
-      "unique": 1974,
+      "unique": 1973,
       "joints": 972,
       "pre": 1372,
       "post": 1361,
@@ -548,7 +548,7 @@
       "highlight": 856,
       "create": 457,
       "cut": 473,
-      "yes": 2085,
+      "yes": 2084,
       "detailed": 526,
       "documents": 575,
       "actual": 34,
@@ -574,7 +574,7 @@
       "seating": 1655,
       "model": 1160,
       "hand": 826,
-      "transfer": 1934,
+      "transfer": 1933,
       "administrative": 52,
       "sta": 1766,
       "checklist": 292,
@@ -598,7 +598,7 @@
       "preparing": 1379,
       "task": 1867,
       "execution": 683,
-      "variety": 2001,
+      "variety": 2000,
       "applications": 100,
       "draw": 588,
       "facilitate": 710,
@@ -624,12 +624,12 @@
       "creative": 460,
       "learn": 1013,
       "extract": 700,
-      "warranty": 2029,
+      "warranty": 2028,
       "replacement": 1548,
       "requirement": 1559,
       "history": 858,
       "previous": 1389,
-      "visit": 2017,
+      "visit": 2016,
       "prior": 1398,
       "schelling": 1639,
       "initial": 918,
@@ -674,7 +674,7 @@
       "company": 352,
       "costs": 446,
       "processing": 1409,
-      "vendor": 2008,
+      "vendor": 2007,
       "design": 518,
       "structure": 1813,
       "results": 1583,
@@ -683,7 +683,6 @@
       "functions": 770,
       "identity": 879,
       "breaches": 212,
-      "thedesignated": 1897,
       "stress": 1809,
       "responsible": 1579,
       "platform": 1340,
@@ -701,12 +700,12 @@
       "placement": 1328,
       "auto": 148,
       "component": 365,
-      "visual": 2019,
+      "visual": 2018,
       "inspection": 928,
       "impact": 885,
       "bend": 186,
       "leak": 1011,
-      "wear": 2043,
+      "wear": 2042,
       "tear": 1873,
       "carefully": 251,
       "damage": 481,
@@ -720,9 +719,9 @@
       "lids": 1030,
       "cooling": 432,
       "minor": 1152,
-      "wheels": 2056,
+      "wheels": 2055,
       "brake": 210,
-      "wheel": 2055,
+      "wheel": 2054,
       "sneering": 1731,
       "pollution": 1351,
       "control": 421,
@@ -773,8 +772,8 @@
       "root": 1607,
       "cause": 262,
       "fault": 721,
-      "troubleshooting": 1954,
-      "tool": 1919,
+      "troubleshooting": 1953,
+      "tool": 1918,
       "substances": 1821,
       "environment": 658,
       "supplier": 1836,
@@ -790,7 +789,7 @@
       "publication": 1449,
       "loose": 1063,
       "pins": 1325,
-      "wiring": 2065,
+      "wiring": 2064,
       "harness": 836,
       "connections": 395,
       "connection": 394,
@@ -803,10 +802,10 @@
       "did": 541,
       "determine": 530,
       "symptoms": 1852,
-      "video": 2015,
+      "video": 2014,
       "recording": 1502,
       "environmental": 659,
-      "units": 1976,
+      "units": 1975,
       "observations": 1215,
       "suggest": 1825,
       "require": 1557,
@@ -814,12 +813,12 @@
       "faulty": 723,
       "nd": 1192,
       "failure": 714,
-      "verify": 2011,
+      "verify": 2010,
       "forth": 751,
       "remove": 1539,
       "removal": 1538,
       "cleanliness": 312,
-      "transmission": 1937,
+      "transmission": 1936,
       "breaking": 215,
       "axillary": 159,
       "removed": 1540,
@@ -840,10 +839,10 @@
       "estimate": 670,
       "replace": 1546,
       "cutting": 476,
-      "wedding": 2046,
+      "wedding": 2045,
       "structural": 1812,
       "constables": 404,
-      "wearing": 2044,
+      "wearing": 2043,
       "method": 1143,
       "glass": 791,
       "seat": 1654,
@@ -858,15 +857,15 @@
       "corrosive": 444,
       "coating": 328,
       "ligament": 1034,
-      "thing": 1904,
+      "thing": 1903,
       "sealing": 1652,
       "replaced": 1547,
-      "weather": 2045,
+      "weather": 2044,
       "activity": 32,
       "dispose": 564,
       "materials": 1115,
       "boxes": 209,
-      "tube": 1958,
+      "tube": 1957,
       "scrap": 1645,
       "malfunction": 1087,
       "steel": 1785,
@@ -879,16 +878,16 @@
       "standing": 1773,
       "grinding": 811,
       "prevention": 1387,
-      "treatment": 1946,
+      "treatment": 1945,
       "sealed": 1651,
       "gun": 823,
       "suction": 1824,
       "es": 665,
       "prepared": 1378,
       "assistant": 137,
-      "type": 1963,
+      "type": 1962,
       "cloth": 322,
-      "wipe": 2062,
+      "wipe": 2061,
       "manufacture": 1099,
       "dry": 602,
       "stages": 1769,
@@ -896,7 +895,7 @@
       "defect": 498,
       "stage": 1768,
       "applying": 103,
-      "wish": 2067,
+      "wish": 2066,
       "abrasion": 2,
       "paper": 1273,
       "protective": 1440,
@@ -922,14 +921,14 @@
       "computer": 370,
       "mode": 1159,
       "cylinder": 478,
-      "turn": 1960,
+      "turn": 1959,
       "fuel": 767,
       "pump": 1452,
       "batteries": 176,
       "causing": 264,
-      "went": 2052,
+      "went": 2051,
       "hammer": 825,
-      "washed": 2031,
+      "washed": 2030,
       "grooving": 813,
       "getting": 788,
       "ready": 1482,
@@ -956,17 +955,17 @@
       "people": 1292,
       "designed": 520,
       "install": 930,
-      "things": 1905,
+      "things": 1904,
       "tent": 1885,
       "plug": 1342,
       "covers": 453,
       "joint": 971,
       "pressure": 1385,
       "soap": 1733,
-      "unit": 1975,
+      "unit": 1974,
       "quantity": 1460,
       "oil": 1226,
-      "tied": 1909,
+      "tied": 1908,
       "testing": 1892,
       "device": 537,
       "theater": 1896,
@@ -975,18 +974,18 @@
       "laws": 1004,
       "legal": 1020,
       "segments": 1663,
-      "washing": 2032,
+      "washing": 2031,
       "agent": 62,
-      "vacuum": 1992,
+      "vacuum": 1991,
       "composition": 368,
       "soak": 1732,
       "rise": 1595,
-      "transport": 1938,
+      "transport": 1937,
       "left": 1019,
       "inside": 924,
       "deposit": 515,
       "surfaces": 1844,
-      "wash": 2030,
+      "wash": 2029,
       "debris": 495,
       "container": 413,
       "policy": 1349,
@@ -1006,20 +1005,20 @@
       "taking": 1859,
       "battery": 177,
       "advance": 55,
-      "typical": 1965,
+      "typical": 1964,
       "sheets": 1697,
       "ration": 1475,
       "consultation": 409,
       "status": 1781,
       "close": 319,
-      "voice": 2020,
+      "voice": 2019,
       "experience": 691,
       "pass": 1284,
       "aspen": 126,
       "slaveholders": 1725,
       "criterion": 463,
-      "verifying": 2012,
-      "usually": 1988,
+      "verifying": 2011,
+      "usually": 1987,
       "car": 245,
       "science": 1643,
       "series": 1682,
@@ -1040,7 +1039,7 @@
       "discuss": 557,
       "le": 1007,
       "aggregation": 66,
-      "types": 1964,
+      "types": 1963,
       "box": 208,
       "smaller": 1727,
       "store": 1799,
@@ -1055,16 +1054,16 @@
       "proof": 1432,
       "raging": 1466,
       "loading": 1050,
-      "transportation": 1939,
+      "transportation": 1938,
       "rejection": 1527,
-      "voltage": 2022,
+      "voltage": 2021,
       "isolation": 961,
       "motor": 1174,
       "possessing": 1359,
       "choose": 299,
       "kit": 983,
       "perorganizational": 1304,
-      "trial": 1949,
+      "trial": 1948,
       "modes": 1163,
       "obtaining": 1221,
       "micro": 1146,
@@ -1078,7 +1077,7 @@
       "multi": 1183,
       "changing": 283,
       "tension": 1884,
-      "true": 1956,
+      "true": 1955,
       "heads": 844,
       "dressing": 592,
       "chain": 274,
@@ -1102,7 +1101,7 @@
       "occupational": 1222,
       "clothing": 324,
       "recommendations": 1498,
-      "way": 2040,
+      "way": 2039,
       "suppliers": 1837,
       "count": 448,
       "refer": 1511,
@@ -1123,7 +1122,7 @@
       "execute": 682,
       "pull": 1450,
       "base": 170,
-      "unloading": 1978,
+      "unloading": 1977,
       "tall": 1860,
       "notice": 1209,
       "inventor": 954,
@@ -1151,12 +1150,12 @@
       "opportunities": 1242,
       "improving": 895,
       "celebrate": 266,
-      "timelines": 1913,
+      "timelines": 1912,
       "major": 1084,
-      "varnish": 2003,
-      "worn": 2078,
+      "varnish": 2002,
+      "worn": 2077,
       "modify": 1164,
-      "treat": 1945,
+      "treat": 1944,
       "acted": 25,
       "multiple": 1184,
       "small": 1726,
@@ -1164,7 +1163,7 @@
       "conditions": 381,
       "changed": 281,
       "circular": 301,
-      "understanding": 1968,
+      "understanding": 1967,
       "setting": 1689,
       "adjusting": 49,
       "layout": 1006,
@@ -1174,15 +1173,15 @@
       "square": 1764,
       "gas": 777,
       "observe": 1216,
-      "tolerable": 1917,
+      "tolerable": 1916,
       "conformance": 388,
-      "warning": 2028,
+      "warning": 2027,
       "spots": 1762,
       "piece": 1319,
       "portable": 1353,
       "positions": 1357,
       "heat": 847,
-      "valves": 1996,
+      "valves": 1995,
       "desired": 522,
       "samples": 1625,
       "operator": 1240,
@@ -1192,10 +1191,10 @@
       "auxiliaries": 151,
       "mentally": 1136,
       "chains": 275,
-      "wishing": 2069,
-      "unload": 1977,
+      "wishing": 2068,
+      "unload": 1976,
       "right": 1591,
-      "trolley": 1953,
+      "trolley": 1952,
       "storing": 1803,
       "remarked": 1536,
       "shapes": 1694,
@@ -1235,11 +1234,11 @@
       "start": 1774,
       "optical": 1244,
       "resource": 1568,
-      "utilization": 1990,
+      "utilization": 1989,
       "man": 1090,
       "planning": 1333,
       "actions": 28,
-      "wastage": 2033,
+      "wastage": 2032,
       "discharge": 554,
       "engineer": 645,
       "improvement": 893,
@@ -1259,14 +1258,14 @@
       "stops": 1797,
       "random": 1470,
       "smiling": 1728,
-      "wished": 2068,
+      "wished": 2067,
       "aware": 156,
       "sanitation": 1628,
       "reproduction": 1554,
-      "theory": 1900,
-      "wastes": 2035,
+      "theory": 1899,
+      "wastes": 2034,
       "accuracy": 16,
-      "write": 2080,
+      "write": 2079,
       "departments": 513,
       "achieved": 20,
       "authorized": 147,
@@ -1283,7 +1282,7 @@
       "positive": 1358,
       "inappropriate": 896,
       "outcome": 1261,
-      "updated": 1981,
+      "updated": 1980,
       "focus": 734,
       "evaluation": 675,
       "monitoring": 1171,
@@ -1298,9 +1297,9 @@
       "producing": 1415,
       "angle": 90,
       "holding": 860,
-      "wire": 2063,
+      "wire": 2062,
       "feed": 727,
-      "travel": 1941,
+      "travel": 1940,
       "speed": 1756,
       "doubts": 582,
       "participants": 1276,
@@ -1319,8 +1318,8 @@
       "stop": 1795,
       "produce": 1413,
       "advanced": 56,
-      "tie": 1908,
-      "uniform": 1971,
+      "tie": 1907,
+      "uniform": 1970,
       "fundamentals": 771,
       "starting": 1776,
       "heated": 848,
@@ -1338,18 +1337,18 @@
       "cool": 431,
       "instruct": 935,
       "mixed": 1157,
-      "turning": 1962,
+      "turning": 1961,
       "additions": 39,
       "quantities": 1459,
       "feeding": 729,
       "core": 439,
       "tank": 1861,
-      "till": 1911,
+      "till": 1910,
       "coated": 327,
-      "zone": 2087,
+      "zone": 2086,
       "dust": 605,
       "particles": 1278,
-      "unwanted": 1979,
+      "unwanted": 1978,
       "mould": 1175,
       "die": 542,
       "solid": 1742,
@@ -1368,7 +1367,7 @@
       "moist": 1166,
       "nation": 1187,
       "al": 71,
-      "thickness": 1903,
+      "thickness": 1902,
       "match": 1112,
       "points": 1347,
       "bath": 175,
@@ -1386,7 +1385,7 @@
       "caps": 243,
       "pin": 1324,
       "stone": 1793,
-      "wet": 2054,
+      "wet": 2053,
       "humidity": 872,
       "oven": 1266,
       "break": 213,
@@ -1405,7 +1404,7 @@
       "situation": 1719,
       "matches": 1113,
       "deals": 494,
-      "transfers": 1935,
+      "transfers": 1934,
       "locations": 1055,
       "cuts": 475,
       "covering": 452,
@@ -1419,13 +1418,13 @@
       "selecting": 1667,
       "burns": 228,
       "king": 982,
-      "thespeci": 1902,
+      "thespeci": 1901,
       "hands": 832,
       "depth": 516,
       "orientation": 1259,
       "programming": 1422,
       "controlled": 422,
-      "years": 2084,
+      "years": 2083,
       "rate": 1473,
       "drilling": 595,
       "length": 1022,
@@ -1466,7 +1465,7 @@
       "similar": 1714,
       "diese": 543,
       "led": 1018,
-      "volume": 2023,
+      "volume": 2022,
       "laboring": 995,
       "print": 1396,
       "chamber": 278,
@@ -1478,7 +1477,7 @@
       "stoppage": 1796,
       "display": 562,
       "marking": 1108,
-      "wires": 2064,
+      "wires": 2063,
       "connected": 393,
       "clearance": 314,
       "injury": 921,
@@ -1490,7 +1489,7 @@
       "ones": 1229,
       "sort": 1745,
       "rays": 1477,
-      "workers": 2072,
+      "workers": 2071,
       "easy": 614,
       "levelling": 1027,
       "glasses": 792,
@@ -1503,8 +1502,8 @@
       "labels": 993,
       "sizes": 1722,
       "lifting": 1033,
-      "tubes": 1959,
-      "tray": 1944,
+      "tubes": 1958,
+      "tray": 1943,
       "peter": 1311,
       "detection": 529,
       "chalk": 276,
@@ -1514,7 +1513,7 @@
       "mind": 1149,
       "module": 1165,
       "operated": 1235,
-      "winding": 2059,
+      "winding": 2058,
       "joining": 970,
       "tables": 1855,
       "creeping": 462,
@@ -1528,7 +1527,7 @@
       "incise": 899,
       "plant": 1335,
       "boards": 200,
-      "thoroughly": 1906,
+      "thoroughly": 1905,
       "pertaining": 1309,
       "parallel": 1274,
       "book": 205,
@@ -1542,7 +1541,7 @@
       "real": 1483,
       "fabrication": 707,
       "seizing": 1664,
-      "trials": 1950,
+      "trials": 1949,
       "deviations": 536,
       "copper": 438,
       "sample": 1624,
@@ -1556,7 +1555,7 @@
       "extrusion": 703,
       "agents": 63,
       "examine": 679,
-      "thermal": 1901,
+      "thermal": 1900,
       "passing": 1285,
       "compression": 369,
       "bad": 161,
@@ -1576,18 +1575,18 @@
       "identifying": 878,
       "descriptions": 517,
       "importance": 890,
-      "trend": 1948,
+      "trend": 1947,
       "sector": 1658,
       "export": 694,
       "decide": 496,
-      "view": 2016,
+      "view": 2015,
       "alternative": 83,
       "global": 795,
       "domestic": 578,
       "stimulation": 1791,
       "prototype": 1443,
       "dynamic": 609,
-      "watering": 2038,
+      "watering": 2037,
       "exhaust": 684,
       "containing": 414,
       "phase": 1313,
@@ -1604,7 +1603,7 @@
       "electronically": 627,
       "instrument": 939,
       "productivity": 1418,
-      "variation": 1999,
+      "variation": 1998,
       "studies": 1816,
       "discard": 553,
       "implements": 889,
@@ -1612,10 +1611,10 @@
       "leader": 1009,
       "endings": 641,
       "obtained": 1220,
-      "tra": 1925,
+      "tra": 1924,
       "adhered": 45,
       "built": 224,
-      "timing": 1916,
+      "timing": 1915,
       "mitigate": 1155,
       "adequately": 43,
       "matter": 1116,
@@ -1643,7 +1642,7 @@
       "protocol": 1442,
       "fro": 764,
       "alert": 75,
-      "west": 2053,
+      "west": 2052,
       "ply": 1344,
       "industrial": 910,
       "considered": 400,
@@ -1659,7 +1658,7 @@
       "appearance": 96,
       "decisions": 497,
       "associated": 139,
-      "variable": 1997,
+      "variable": 1996,
       "addition": 37,
       "consider": 397,
       "interface": 947,
@@ -1667,7 +1666,7 @@
       "alcohol": 74,
       "sanitizers": 1631,
       "laboratory": 994,
-      "traceability": 1927,
+      "traceability": 1926,
       "section": 1657,
       "carrying": 256,
       "frequent": 760,
@@ -1675,9 +1674,9 @@
       "associate": 138,
       "ending": 640,
       "duty": 608,
-      "vibration": 2013,
+      "vibration": 2012,
       "period": 1299,
-      "utilised": 1989,
+      "utilised": 1988,
       "induration": 909,
       "responsibilities": 1577,
       "culture": 469,
@@ -1687,7 +1686,7 @@
       "statutory": 1782,
       "incidents": 898,
       "aid": 69,
-      "trips": 1952,
+      "trips": 1951,
       "cheese": 294,
       "harp": 837,
       "kill": 978,
@@ -1706,13 +1705,13 @@
       "soil": 1740,
       "acid": 22,
       "solar": 1741,
-      "wind": 2058,
+      "wind": 2057,
       "short": 1703,
       "integrated": 943,
       "continuity": 418,
       "procure": 1410,
       "recognise": 1494,
-      "unable": 1966,
+      "unable": 1965,
       "approve": 110,
       "fresh": 762,
       "important": 891,
@@ -1730,7 +1729,7 @@
       "alternate": 82,
       "project": 1425,
       "schematic": 1640,
-      "weight": 2050,
+      "weight": 2049,
       "screen": 1646,
       "conveyed": 426,
       "commissioning": 344,
@@ -1742,7 +1741,7 @@
       "distinguish": 568,
       "cracking": 454,
       "consult": 408,
-      "times": 1915,
+      "times": 1914,
       "sites": 1718,
       "estimated": 671,
       "organize": 1257,
@@ -1753,7 +1752,7 @@
       "advise": 59,
       "conform": 387,
       "iron": 958,
-      "undertake": 1969,
+      "undertake": 1968,
       "larger": 1000,
       "arranged": 114,
       "measured": 1122,
@@ -1767,7 +1766,7 @@
       "kind": 980,
       "come": 341,
       "informed": 915,
-      "utter": 1991,
+      "utter": 1990,
       "states": 1779,
       "capacity": 241,
       "stability": 1767,
@@ -1775,17 +1774,17 @@
       "applied": 101,
       "cells": 269,
       "attitude": 143,
-      "trip": 1951,
+      "trip": 1950,
       "enhance": 648,
       "food": 739,
       "money": 1169,
       "destination": 525,
       "cash": 259,
       "gets": 787,
-      "wise": 2066,
+      "wise": 2065,
       "expenses": 690,
       "patterns": 1288,
-      "trace": 1926,
+      "trace": 1925,
       "hours": 868,
       "conjunction": 391,
       "prompt": 1430,
@@ -1794,22 +1793,22 @@
       "entering": 653,
       "contract": 420,
       "leave": 1015,
-      "ventilator": 2009,
+      "ventilator": 2008,
       "rescue": 1561,
       "belt": 184,
       "exposed": 695,
-      "whipped": 2057,
+      "whipped": 2056,
       "jumping": 973,
       "cylinders": 479,
-      "warm": 2027,
+      "warm": 2026,
       "minutes": 1153,
       "lower": 1067,
       "balance": 167,
-      "tollers": 1918,
+      "tollers": 1917,
       "lowered": 1068,
-      "week": 2047,
+      "week": 2046,
       "course": 449,
-      "walls": 2026,
+      "walls": 2025,
       "charges": 286,
       "privacy": 1401,
       "extinguished": 698,
@@ -1817,11 +1816,11 @@
       "machineries": 1073,
       "clair": 305,
       "fruits": 766,
-      "vegetables": 2005,
+      "vegetables": 2004,
       "cities": 302,
       "cap": 240,
       "ingredient": 917,
-      "weigh": 2049,
+      "weigh": 2048,
       "revolving": 1588,
       "rotation": 1609,
       "formulation": 750,
@@ -1832,8 +1831,8 @@
       "bottles": 207,
       "bottle": 206,
       "concerns": 377,
-      "weekly": 2048,
-      "yield": 2086,
+      "weekly": 2047,
+      "yield": 2085,
       "microbiological": 1147,
       "acids": 23,
       "favor": 724,
@@ -1866,7 +1865,7 @@
       "late": 1001,
       "fossa": 753,
       "administer": 51,
-      "victims": 2014,
+      "victims": 2013,
       "bleeding": 196,
       "disinfectant": 560,
       "disinfect": 559,
@@ -1879,19 +1878,19 @@
       "agricultural": 68,
       "attached": 141,
       "rings": 1594,
-      "trading": 1929,
+      "trading": 1928,
       "mesh": 1140,
-      "wrap": 2079,
+      "wrap": 2078,
       "deal": 492,
       "density": 511,
       "enterprises": 654,
       "concentration": 371,
       "polymer": 1352,
-      "wines": 2060,
+      "wines": 2059,
       "pest": 1310,
       "consumer": 410,
       "recipe": 1493,
-      "weakness": 2042,
+      "weakness": 2041,
       "portion": 1355,
       "bringing": 218,
       "grass": 806,
@@ -1904,11 +1903,11 @@
       "rice": 1590,
       "boiler": 202,
       "cop": 437,
-      "variance": 1998,
+      "variance": 1997,
       "absence": 3,
       "june": 974,
       "hemp": 853,
-      "uniformity": 1972,
+      "uniformity": 1971,
       "consistent": 403,
       "earth": 612,
       "cone": 386,
@@ -1926,7 +1925,7 @@
       "conversion": 425,
       "condiments": 378,
       "cream": 456,
-      "trying": 1957,
+      "trying": 1956,
       "implementing": 888,
       "recycle": 1507,
       "scale": 1635,
@@ -1941,23 +1940,23 @@
       "reasoning": 1486,
       "baked": 165,
       "butter": 230,
-      "thee": 1898,
+      "thee": 1897,
       "directly": 550,
       "away": 158,
       "knife": 985,
       "drainage": 587,
       "lot": 1065,
-      "theme": 1899,
+      "theme": 1898,
       "spinning": 1758,
       "sea": 1650,
       "eyes": 705,
       "integrity": 944,
       "buttons": 232,
       "glazed": 794,
-      "trough": 1955,
+      "trough": 1954,
       "biscuits": 193,
       "names": 1186,
-      "ve": 2004,
+      "ve": 2003,
       "rolling": 1604,
       "baker": 166,
       "premises": 1375,
@@ -1967,29 +1966,29 @@
       "eat": 615,
       "isa": 959,
       "hair": 824,
-      "trenches": 1947,
+      "trenches": 1946,
       "exist": 686,
       "arrival": 118,
       "raising": 1469,
       "glassware": 793,
       "negotiate": 1200,
       "shortage": 1704,
-      "voices": 2021,
-      "trap": 1940,
-      "variations": 2000,
+      "voices": 2020,
+      "trap": 1939,
+      "variations": 1999,
       "exile": 685,
       "te": 1871,
       "compile": 355,
-      "ties": 1910,
+      "ties": 1909,
       "drink": 596,
       "dates": 489,
       "highly": 857,
-      "toxic": 1924,
+      "toxic": 1923,
       "survey": 1846,
-      "uniformly": 1973,
+      "uniformly": 1972,
       "beverage": 189,
       "snack": 1730,
-      "traditional": 1930,
+      "traditional": 1929,
       "green": 807,
       "accounting": 14,
       "kitchen": 984,
@@ -1998,10 +1997,10 @@
       "district": 570,
       "industries": 911,
       "allotted": 80,
-      "undertaking": 1970,
+      "undertaking": 1969,
       "routes": 1611,
       "surroundings": 1845,
-      "welcome": 2051,
+      "welcome": 2050,
       "tackle": 1856,
       "promotions": 1429,
       "arrive": 119,
@@ -2024,16 +2023,16 @@
       "indian": 906,
       "landing": 997,
       "overview": 1269,
-      "transformer": 1936,
+      "transformer": 1935,
       "erection": 663,
-      "uses": 1986,
+      "uses": 1985,
       "electrolysis": 625,
       "savings": 1633,
       "pictures": 1318,
       "itching": 964,
       "feedstock": 730,
       "giving": 790,
-      "watching": 2036,
+      "watching": 2035,
       "la": 989,
       "bills": 190,
       "amiable": 84,
@@ -2041,7 +2040,7 @@
       "prices": 1391,
       "sustainability": 1847,
       "concerning": 376,
-      "wall": 2025,
+      "wall": 2024,
       "roads": 1599,
       "cms": 325,
       "farmers": 718,
@@ -2061,7 +2060,7 @@
       "periodical": 1301,
       "stay": 1783,
       "danger": 485,
-      "visiting": 2018,
+      "visiting": 2017,
       "sponge": 1760,
       "looks": 1061,
       "handed": 827,
@@ -2071,7 +2070,7 @@
       "accountable": 13,
       "textile": 1894,
       "rope": 1608,
-      "yarn": 2083,
+      "yarn": 2082,
       "knitting": 986,
       "sal": 1620,
       "beams": 178,
@@ -2083,17 +2082,17 @@
       "badges": 162,
       "dining": 546,
       "sanitisers": 1629,
-      "winter": 2061,
-      "traveling": 1942,
+      "winter": 2060,
+      "traveling": 1941,
       "pocket": 1345,
       "sobbing": 1734,
       "patrol": 1287,
-      "traveller": 1943,
+      "traveller": 1942,
       "autoconer": 149,
       "gape": 775,
       "grm": 812,
       "paintings": 1271,
-      "tourism": 1922,
+      "tourism": 1921,
       "hospitality": 863,
       "guest": 817,
       "guests": 818,
@@ -2103,15 +2102,15 @@
       "dissatisfaction": 566,
       "purchases": 1455,
       "sundry": 1830,
-      "tourist": 1923,
+      "tourist": 1922,
       "chef": 295,
       "dishes": 558,
       "answer": 93,
-      "tour": 1921,
+      "tour": 1920,
       "stories": 1802,
       "students": 1815,
       "expedition": 689,
-      "waters": 2039
+      "waters": 2038
     }
   }
 }

topic_embeddings.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18011c043fbc681c88c4095ef7dd808b12affc5457480827f31aaa0604db112e
-size 1626208
+oid sha256:33b54606ed4c58d68e9df7133336bb92e51f8414507d3104f804c1f9cabea440
+size 1605728