Skip to content

Instantly share code, notes, and snippets.

Show Gist options
  • Select an option

  • Save yiliu30/fc680e409c682ab86035d9a19d8eafd6 to your computer and use it in GitHub Desktop.

Select an option

Save yiliu30/fc680e409c682ab86035d9a19d8eafd6 to your computer and use it in GitHub Desktop.

Revisions

  1. yiliu30 revised this gist Apr 23, 2025. 1 changed file with 25 additions and 24 deletions.
    Original file line number Diff line number Diff line change
    @@ -1,3 +1,4 @@
    // INC
    [
    {
    "0": {
    @@ -781,52 +782,52 @@
    },
    {
    "32213": {
    "logprob": -2.824495315551758,
    "logprob": -2.7726497650146484,
    "rank": 1,
    "decoded_token": "cards"
    },
    "80889": {
    "logprob": -4.011995315551758,
    "logprob": -3.9601497650146484,
    "rank": 2,
    "decoded_token": "-design"
    },
    "59079": {
    "logprob": -4.199495315551758,
    "48180": {
    "logprob": -4.272649765014648,
    "rank": 3,
    "decoded_token": " Artists"
    "decoded_token": " phylogen"
    },
    "91806": {
    "logprob": -4.261995315551758,
    "59079": {
    "logprob": -4.272649765014648,
    "rank": 4,
    "decoded_token": "voy"
    "decoded_token": " Artists"
    },
    "48180": {
    "logprob": -4.324495315551758,
    "91806": {
    "logprob": -4.272649765014648,
    "rank": 5,
    "decoded_token": " phylogen"
    "decoded_token": "voy"
    },
    "28425": {
    "logprob": -4.386995315551758,
    "75635": {
    "logprob": -4.335149765014648,
    "rank": 6,
    "decoded_token": "egy"
    "decoded_token": "anoi"
    },
    "75635": {
    "logprob": -4.386995315551758,
    "28425": {
    "logprob": -4.397649765014648,
    "rank": 7,
    "decoded_token": "anoi"
    "decoded_token": "egy"
    },
    "114941": {
    "logprob": -4.449495315551758,
    "73913": {
    "logprob": -4.585149765014648,
    "rank": 8,
    "decoded_token": "uzzi"
    "decoded_token": "-ra"
    },
    "73913": {
    "logprob": -4.511995315551758,
    "114941": {
    "logprob": -4.585149765014648,
    "rank": 9,
    "decoded_token": "-ra"
    "decoded_token": "uzzi"
    },
    "41480": {
    "logprob": -4.699495315551758,
    "logprob": -4.710149765014648,
    "rank": 10,
    "decoded_token": "gos"
    }
  2. yiliu30 created this gist Apr 23, 2025.
    Original file line number Diff line number Diff line change
    @@ -0,0 +1,834 @@
    [
    {
    "0": {
    "logprob": 0.0,
    "rank": 1,
    "decoded_token": ""
    },
    "113689": {
    "logprob": -18.8125,
    "rank": 2,
    "decoded_token": "akon"
    },
    "57899": {
    "logprob": -19.125,
    "rank": 3,
    "decoded_token": " KR"
    },
    "5248": {
    "logprob": -19.25,
    "rank": 4,
    "decoded_token": "rast"
    },
    "97599": {
    "logprob": -19.375,
    "rank": 5,
    "decoded_token": "hara"
    },
    "123724": {
    "logprob": -19.4375,
    "rank": 6,
    "decoded_token": " Kear"
    },
    "39198": {
    "logprob": -19.625,
    "rank": 7,
    "decoded_token": "alb"
    },
    "59329": {
    "logprob": -19.625,
    "rank": 8,
    "decoded_token": " Kub"
    },
    "14855": {
    "logprob": -19.8125,
    "rank": 9,
    "decoded_token": "ihan"
    },
    "90848": {
    "logprob": -19.8125,
    "rank": 10,
    "decoded_token": " Kron"
    }
    },
    {
    "71878": {
    "logprob": -2.998861312866211,
    "rank": 1,
    "decoded_token": " [...]\n\n"
    },
    "37036": {
    "logprob": -4.373861312866211,
    "rank": 2,
    "decoded_token": "rena"
    },
    "37414": {
    "logprob": -5.123861312866211,
    "rank": 3,
    "decoded_token": " [\u2026]\n\n"
    },
    "116275": {
    "logprob": -5.686361312866211,
    "rank": 4,
    "decoded_token": " Chanc"
    },
    "30283": {
    "logprob": -5.780111312866211,
    "rank": 5,
    "decoded_token": " [...]"
    },
    "81102": {
    "logprob": -6.155111312866211,
    "rank": 6,
    "decoded_token": "asking"
    },
    "32591": {
    "logprob": -6.280111312866211,
    "rank": 7,
    "decoded_token": " Hend"
    },
    "70061": {
    "logprob": -6.280111312866211,
    "rank": 8,
    "decoded_token": "imag"
    },
    "121449": {
    "logprob": -6.280111312866211,
    "rank": 9,
    "decoded_token": " Heller"
    },
    "39107": {
    "logprob": -6.311361312866211,
    "rank": 10,
    "decoded_token": " aiming"
    }
    },
    {
    "65972": {
    "logprob": -1.2981739044189453,
    "rank": 1,
    "decoded_token": "]\n\n\n"
    },
    "96430": {
    "logprob": -3.1106739044189453,
    "rank": 2,
    "decoded_token": ".]\n"
    },
    "27974": {
    "logprob": -3.4231739044189453,
    "rank": 3,
    "decoded_token": ".]"
    },
    "28881": {
    "logprob": -3.5481739044189453,
    "rank": 4,
    "decoded_token": "].\n"
    },
    "68230": {
    "logprob": -3.7356739044189453,
    "rank": 5,
    "decoded_token": "\u662f\u600e\u6837"
    },
    "19941": {
    "logprob": -3.9856739044189453,
    "rank": 6,
    "decoded_token": " ]\n\n"
    },
    "78269": {
    "logprob": -4.173173904418945,
    "rank": 7,
    "decoded_token": "++]"
    },
    "73989": {
    "logprob": -4.173173904418945,
    "rank": 8,
    "decoded_token": "\u662f\u4ec0\u9ebc"
    },
    "40329": {
    "logprob": -4.235673904418945,
    "rank": 9,
    "decoded_token": ".]\n\n"
    },
    "57263": {
    "logprob": -4.235673904418945,
    "rank": 10,
    "decoded_token": "]\uff0c"
    }
    },
    {
    "124172": {
    "logprob": -1.0986995697021484,
    "rank": 1,
    "decoded_token": "=[\n"
    },
    "65972": {
    "logprob": -4.223699569702148,
    "rank": 2,
    "decoded_token": "]\n\n\n"
    },
    "73066": {
    "logprob": -4.286199569702148,
    "rank": 3,
    "decoded_token": "\u7761\u7740\u4e86"
    },
    "10606": {
    "logprob": -4.536199569702148,
    "rank": 4,
    "decoded_token": " [\n"
    },
    "115379": {
    "logprob": -4.598699569702148,
    "rank": 5,
    "decoded_token": "\u7a33\u4f4f"
    },
    "91178": {
    "logprob": -5.036199569702148,
    "rank": 6,
    "decoded_token": "\u800c\u4eca"
    },
    "101323": {
    "logprob": -5.036199569702148,
    "rank": 7,
    "decoded_token": " [{"
    },
    "74948": {
    "logprob": -5.223699569702148,
    "rank": 8,
    "decoded_token": " geared"
    },
    "23551": {
    "logprob": -5.286199569702148,
    "rank": 9,
    "decoded_token": "=["
    },
    "46543": {
    "logprob": -5.536199569702148,
    "rank": 10,
    "decoded_token": "[\n"
    }
    },
    {
    "86669": {
    "logprob": -2.7470359802246094,
    "rank": 1,
    "decoded_token": "======\n"
    },
    "25691": {
    "logprob": -3.9345359802246094,
    "rank": 2,
    "decoded_token": "=\n\n"
    },
    "124172": {
    "logprob": -4.059535980224609,
    "rank": 3,
    "decoded_token": "=[\n"
    },
    "84263": {
    "logprob": -4.247035980224609,
    "rank": 4,
    "decoded_token": " solicit"
    },
    "24925": {
    "logprob": -4.684535980224609,
    "rank": 5,
    "decoded_token": "=\n"
    },
    "2802": {
    "logprob": -4.747035980224609,
    "rank": 6,
    "decoded_token": "===="
    },
    "65972": {
    "logprob": -4.747035980224609,
    "rank": 7,
    "decoded_token": "]\n\n\n"
    },
    "113479": {
    "logprob": -4.809535980224609,
    "rank": 8,
    "decoded_token": "Recording"
    },
    "107011": {
    "logprob": -4.809535980224609,
    "rank": 9,
    "decoded_token": "poz"
    },
    "115864": {
    "logprob": -4.809535980224609,
    "rank": 10,
    "decoded_token": " sulfuric"
    }
    },
    {
    "7127": {
    "logprob": -2.1336584091186523,
    "rank": 1,
    "decoded_token": "alam"
    },
    "66640": {
    "logprob": -2.3211584091186523,
    "rank": 2,
    "decoded_token": "alami"
    },
    "86669": {
    "logprob": -3.0711584091186523,
    "rank": 3,
    "decoded_token": "======\n"
    },
    "114611": {
    "logprob": -4.071158409118652,
    "rank": 4,
    "decoded_token": "\u0c3e\u0c32\u0c41"
    },
    "124172": {
    "logprob": -4.196158409118652,
    "rank": 5,
    "decoded_token": "=[\n"
    },
    "93904": {
    "logprob": -4.258658409118652,
    "rank": 6,
    "decoded_token": "\u0c2e\u0c41"
    },
    "25691": {
    "logprob": -4.446158409118652,
    "rank": 7,
    "decoded_token": "=\n\n"
    },
    "54719": {
    "logprob": -4.446158409118652,
    "rank": 8,
    "decoded_token": " Pseud"
    },
    "64980": {
    "logprob": -4.696158409118652,
    "rank": 9,
    "decoded_token": "\u0c3e\u0c32"
    },
    "125471": {
    "logprob": -4.696158409118652,
    "rank": 10,
    "decoded_token": "\u043f\u043b"
    }
    },
    {
    "45025": {
    "logprob": -1.203542709350586,
    "rank": 1,
    "decoded_token": "ousse"
    },
    "126949": {
    "logprob": -2.141042709350586,
    "rank": 2,
    "decoded_token": "outi"
    },
    "35334": {
    "logprob": -2.766042709350586,
    "rank": 3,
    "decoded_token": "anni"
    },
    "870": {
    "logprob": -3.078542709350586,
    "rank": 4,
    "decoded_token": "ount"
    },
    "8653": {
    "logprob": -3.078542709350586,
    "rank": 5,
    "decoded_token": "bert"
    },
    "40826": {
    "logprob": -3.828542709350586,
    "rank": 6,
    "decoded_token": "nda"
    },
    "19744": {
    "logprob": -4.141042709350586,
    "rank": 7,
    "decoded_token": "aska"
    },
    "113273": {
    "logprob": -4.141042709350586,
    "rank": 8,
    "decoded_token": "ogu"
    },
    "98009": {
    "logprob": -4.266042709350586,
    "rank": 9,
    "decoded_token": "oots"
    },
    "17643": {
    "logprob": -4.578542709350586,
    "rank": 10,
    "decoded_token": "anno"
    }
    },
    {
    "65767": {
    "logprob": -1.784780502319336,
    "rank": 1,
    "decoded_token": "hra"
    },
    "32981": {
    "logprob": -2.347280502319336,
    "rank": 2,
    "decoded_token": "oux"
    },
    "103524": {
    "logprob": -3.409780502319336,
    "rank": 3,
    "decoded_token": "hei"
    },
    "11479": {
    "logprob": -3.597280502319336,
    "rank": 4,
    "decoded_token": "uma"
    },
    "54031": {
    "logprob": -3.722280502319336,
    "rank": 5,
    "decoded_token": "jack"
    },
    "2117": {
    "logprob": -3.972280502319336,
    "rank": 6,
    "decoded_token": "alk"
    },
    "125357": {
    "logprob": -3.972280502319336,
    "rank": 7,
    "decoded_token": "hia"
    },
    "39201": {
    "logprob": -4.034780502319336,
    "rank": 8,
    "decoded_token": "pit"
    },
    "20637": {
    "logprob": -4.097280502319336,
    "rank": 9,
    "decoded_token": "elo"
    },
    "36380": {
    "logprob": -4.097280502319336,
    "rank": 10,
    "decoded_token": "iji"
    }
    },
    {
    "114640": {
    "logprob": -1.8719139099121094,
    "rank": 1,
    "decoded_token": "oui"
    },
    "104848": {
    "logprob": -2.7469139099121094,
    "rank": 2,
    "decoded_token": "uwen"
    },
    "114316": {
    "logprob": -2.9344139099121094,
    "rank": 3,
    "decoded_token": "uft"
    },
    "54356": {
    "logprob": -3.3719139099121094,
    "rank": 4,
    "decoded_token": "uder"
    },
    "103919": {
    "logprob": -3.6219139099121094,
    "rank": 5,
    "decoded_token": "oub"
    },
    "1736": {
    "logprob": -3.6844139099121094,
    "rank": 6,
    "decoded_token": "day"
    },
    "116301": {
    "logprob": -3.9344139099121094,
    "rank": 7,
    "decoded_token": "dura"
    },
    "15280": {
    "logprob": -4.059413909912109,
    "rank": 8,
    "decoded_token": "uen"
    },
    "52098": {
    "logprob": -4.059413909912109,
    "rank": 9,
    "decoded_token": "embed"
    },
    "26409": {
    "logprob": -4.309413909912109,
    "rank": 10,
    "decoded_token": "oku"
    }
    },
    {
    "126879": {
    "logprob": -2.8916187286376953,
    "rank": 1,
    "decoded_token": "-ye"
    },
    "119808": {
    "logprob": -3.7666187286376953,
    "rank": 2,
    "decoded_token": "letta"
    },
    "108099": {
    "logprob": -4.016618728637695,
    "rank": 3,
    "decoded_token": "heb"
    },
    "46194": {
    "logprob": -4.079118728637695,
    "rank": 4,
    "decoded_token": ".fr"
    },
    "104069": {
    "logprob": -4.141618728637695,
    "rank": 5,
    "decoded_token": "abal"
    },
    "17929": {
    "logprob": -4.391618728637695,
    "rank": 6,
    "decoded_token": "\u710a"
    },
    "12098": {
    "logprob": -4.579118728637695,
    "rank": 7,
    "decoded_token": "yan"
    },
    "35334": {
    "logprob": -4.829118728637695,
    "rank": 8,
    "decoded_token": "anni"
    },
    "87963": {
    "logprob": -4.954118728637695,
    "rank": 9,
    "decoded_token": "\u627f\u62c5\u8d23\u4efb"
    },
    "114640": {
    "logprob": -4.954118728637695,
    "rank": 10,
    "decoded_token": "oui"
    }
    },
    {
    "3994": {
    "logprob": -1.133575439453125,
    "rank": 1,
    "decoded_token": "oman"
    },
    "109212": {
    "logprob": -3.008575439453125,
    "rank": 2,
    "decoded_token": "ebo"
    },
    "32902": {
    "logprob": -3.571075439453125,
    "rank": 3,
    "decoded_token": "outube"
    },
    "114301": {
    "logprob": -3.571075439453125,
    "rank": 4,
    "decoded_token": "apai"
    },
    "62270": {
    "logprob": -3.758575439453125,
    "rank": 5,
    "decoded_token": ".blogspot"
    },
    "9650": {
    "logprob": -3.946075439453125,
    "rank": 6,
    "decoded_token": "olean"
    },
    "26828": {
    "logprob": -3.946075439453125,
    "rank": 7,
    "decoded_token": "bsite"
    },
    "120442": {
    "logprob": -4.071075439453125,
    "rank": 8,
    "decoded_token": "\u6539\u9769\u521b\u65b0"
    },
    "77643": {
    "logprob": -4.196075439453125,
    "rank": 9,
    "decoded_token": "olg"
    },
    "77579": {
    "logprob": -4.821075439453125,
    "rank": 10,
    "decoded_token": ""
    }
    },
    {
    "744": {
    "logprob": -3.282543182373047,
    "rank": 1,
    "decoded_token": "ry"
    },
    "14124": {
    "logprob": -3.345043182373047,
    "rank": 2,
    "decoded_token": "eed"
    },
    "74562": {
    "logprob": -3.470043182373047,
    "rank": 3,
    "decoded_token": "ikai"
    },
    "57691": {
    "logprob": -3.595043182373047,
    "rank": 4,
    "decoded_token": "esses"
    },
    "2117": {
    "logprob": -3.657543182373047,
    "rank": 5,
    "decoded_token": "alk"
    },
    "17095": {
    "logprob": -3.720043182373047,
    "rank": 6,
    "decoded_token": "ned"
    },
    "2327": {
    "logprob": -4.032543182373047,
    "rank": 7,
    "decoded_token": "ium"
    },
    "3302": {
    "logprob": -4.345043182373047,
    "rank": 8,
    "decoded_token": "orth"
    },
    "54197": {
    "logprob": -4.407543182373047,
    "rank": 9,
    "decoded_token": "iak"
    },
    "26679": {
    "logprob": -4.595043182373047,
    "rank": 10,
    "decoded_token": "-gener"
    }
    },
    {
    "23318": {
    "logprob": -3.1598758697509766,
    "rank": 1,
    "decoded_token": "-col"
    },
    "111894": {
    "logprob": -3.5973758697509766,
    "rank": 2,
    "decoded_token": "capac"
    },
    "54910": {
    "logprob": -3.8473758697509766,
    "rank": 3,
    "decoded_token": "lene"
    },
    "54532": {
    "logprob": -3.8473758697509766,
    "rank": 4,
    "decoded_token": "-cap"
    },
    "59994": {
    "logprob": -3.8473758697509766,
    "rank": 5,
    "decoded_token": "-aged"
    },
    "94350": {
    "logprob": -3.8473758697509766,
    "rank": 6,
    "decoded_token": "axe"
    },
    "113470": {
    "logprob": -4.284875869750977,
    "rank": 7,
    "decoded_token": "arii"
    },
    "22315": {
    "logprob": -4.347375869750977,
    "rank": 8,
    "decoded_token": "aura"
    },
    "66190": {
    "logprob": -4.472375869750977,
    "rank": 9,
    "decoded_token": "acid"
    },
    "70810": {
    "logprob": -4.597375869750977,
    "rank": 10,
    "decoded_token": "colors"
    }
    },
    {
    "8294": {
    "logprob": -2.700857162475586,
    "rank": 1,
    "decoded_token": "lections"
    },
    "92867": {
    "logprob": -2.763357162475586,
    "rank": 2,
    "decoded_token": "ossal"
    },
    "102735": {
    "logprob": -2.763357162475586,
    "rank": 3,
    "decoded_token": "umna"
    },
    "78936": {
    "logprob": -3.013357162475586,
    "rank": 4,
    "decoded_token": "onate"
    },
    "54911": {
    "logprob": -3.075857162475586,
    "rank": 5,
    "decoded_token": "lective"
    },
    "21660": {
    "logprob": -3.138357162475586,
    "rank": 6,
    "decoded_token": "oured"
    },
    "11406": {
    "logprob": -3.325857162475586,
    "rank": 7,
    "decoded_token": "lected"
    },
    "3206": {
    "logprob": -3.700857162475586,
    "rank": 8,
    "decoded_token": "lection"
    },
    "5128": {
    "logprob": -4.200857162475586,
    "rank": 9,
    "decoded_token": "lege"
    },
    "1044": {
    "logprob": -4.200857162475586,
    "rank": 10,
    "decoded_token": "lect"
    }
    },
    {
    "84722": {
    "logprob": -3.078632354736328,
    "rank": 1,
    "decoded_token": "cape"
    },
    "58171": {
    "logprob": -4.203632354736328,
    "rank": 2,
    "decoded_token": "uhi"
    },
    "119235": {
    "logprob": -4.453632354736328,
    "rank": 3,
    "decoded_token": "alate"
    },
    "118815": {
    "logprob": -4.578632354736328,
    "rank": 4,
    "decoded_token": ".fire"
    },
    "109077": {
    "logprob": -4.766132354736328,
    "rank": 5,
    "decoded_token": " Viz"
    },
    "107590": {
    "logprob": -4.766132354736328,
    "rank": 6,
    "decoded_token": "ipi"
    },
    "68157": {
    "logprob": -4.828632354736328,
    "rank": 7,
    "decoded_token": "-tax"
    },
    "76584": {
    "logprob": -4.828632354736328,
    "rank": 8,
    "decoded_token": " tents"
    },
    "37687": {
    "logprob": -4.891132354736328,
    "rank": 9,
    "decoded_token": "-art"
    },
    "102735": {
    "logprob": -4.953632354736328,
    "rank": 10,
    "decoded_token": "umna"
    }
    },
    {
    "32213": {
    "logprob": -2.824495315551758,
    "rank": 1,
    "decoded_token": "cards"
    },
    "80889": {
    "logprob": -4.011995315551758,
    "rank": 2,
    "decoded_token": "-design"
    },
    "59079": {
    "logprob": -4.199495315551758,
    "rank": 3,
    "decoded_token": " Artists"
    },
    "91806": {
    "logprob": -4.261995315551758,
    "rank": 4,
    "decoded_token": "voy"
    },
    "48180": {
    "logprob": -4.324495315551758,
    "rank": 5,
    "decoded_token": " phylogen"
    },
    "28425": {
    "logprob": -4.386995315551758,
    "rank": 6,
    "decoded_token": "egy"
    },
    "75635": {
    "logprob": -4.386995315551758,
    "rank": 7,
    "decoded_token": "anoi"
    },
    "114941": {
    "logprob": -4.449495315551758,
    "rank": 8,
    "decoded_token": "uzzi"
    },
    "73913": {
    "logprob": -4.511995315551758,
    "rank": 9,
    "decoded_token": "-ra"
    },
    "41480": {
    "logprob": -4.699495315551758,
    "rank": 10,
    "decoded_token": "gos"
    }
    }
    ]