Skip to content

GitLab

Unverified Commit df4594a9 authored by Stas Bekman's avatar Stas Bekman Committed by GitHub
Browse files

[xlm tok] config dict: fix str into int to match definition (#7034)

parent d6c08b07
Show whitespace changes
Inline Side-by-side
Showing with 152 additions and 152 deletions
src/transformers/tokenization_xlm.py
View file @ df4594a9
...@@ -79,37 +79,37 @@ PRETRAINED_INIT_CONFIGURATION = { ...@@ -79,37 +79,37 @@ PRETRAINED_INIT_CONFIGURATION = {
"xlm-mlm-en-2048": {"do_lowercase_and_remove_accent": True}, "xlm-mlm-en-2048": {"do_lowercase_and_remove_accent": True},
"xlm-mlm-ende-1024": { "xlm-mlm-ende-1024": {
"do_lowercase_and_remove_accent": True, "do_lowercase_and_remove_accent": True,
"id2lang": {"0": "de", "1": "en"}, "id2lang": {0: "de", 1: "en"},
"lang2id": {"de": 0, "en": 1}, "lang2id": {"de": 0, "en": 1},
}, },
"xlm-mlm-enfr-1024": { "xlm-mlm-enfr-1024": {
"do_lowercase_and_remove_accent": True, "do_lowercase_and_remove_accent": True,
"id2lang": {"0": "en", "1": "fr"}, "id2lang": {0: "en", 1: "fr"},
"lang2id": {"en": 0, "fr": 1}, "lang2id": {"en": 0, "fr": 1},
}, },
"xlm-mlm-enro-1024": { "xlm-mlm-enro-1024": {
"do_lowercase_and_remove_accent": True, "do_lowercase_and_remove_accent": True,
"id2lang": {"0": "en", "1": "ro"}, "id2lang": {0: "en", 1: "ro"},
"lang2id": {"en": 0, "ro": 1}, "lang2id": {"en": 0, "ro": 1},
}, },
"xlm-mlm-tlm-xnli15-1024": { "xlm-mlm-tlm-xnli15-1024": {
"do_lowercase_and_remove_accent": True, "do_lowercase_and_remove_accent": True,
"id2lang": { "id2lang": {
"0": "ar", 0: "ar",
"1": "bg", 1: "bg",
"2": "de", 2: "de",
"3": "el", 3: "el",
"4": "en", 4: "en",
"5": "es", 5: "es",
"6": "fr", 6: "fr",
"7": "hi", 7: "hi",
"8": "ru", 8: "ru",
"9": "sw", 9: "sw",
"10": "th", 10: "th",
"11": "tr", 11: "tr",
"12": "ur", 12: "ur",
"13": "vi", 13: "vi",
"14": "zh", 14: "zh",
}, },
"lang2id": { "lang2id": {
"ar": 0, "ar": 0,
...@@ -132,21 +132,21 @@ PRETRAINED_INIT_CONFIGURATION = { ...@@ -132,21 +132,21 @@ PRETRAINED_INIT_CONFIGURATION = {
"xlm-mlm-xnli15-1024": { "xlm-mlm-xnli15-1024": {
"do_lowercase_and_remove_accent": True, "do_lowercase_and_remove_accent": True,
"id2lang": { "id2lang": {
"0": "ar", 0: "ar",
"1": "bg", 1: "bg",
"2": "de", 2: "de",
"3": "el", 3: "el",
"4": "en", 4: "en",
"5": "es", 5: "es",
"6": "fr", 6: "fr",
"7": "hi", 7: "hi",
"8": "ru", 8: "ru",
"9": "sw", 9: "sw",
"10": "th", 10: "th",
"11": "tr", 11: "tr",
"12": "ur", 12: "ur",
"13": "vi", 13: "vi",
"14": "zh", 14: "zh",
}, },
"lang2id": { "lang2id": {
"ar": 0, "ar": 0,
...@@ -168,34 +168,34 @@ PRETRAINED_INIT_CONFIGURATION = { ...@@ -168,34 +168,34 @@ PRETRAINED_INIT_CONFIGURATION = {
}, },
"xlm-clm-enfr-1024": { "xlm-clm-enfr-1024": {
"do_lowercase_and_remove_accent": True, "do_lowercase_and_remove_accent": True,
"id2lang": {"0": "en", "1": "fr"}, "id2lang": {0: "en", 1: "fr"},
"lang2id": {"en": 0, "fr": 1}, "lang2id": {"en": 0, "fr": 1},
}, },
"xlm-clm-ende-1024": { "xlm-clm-ende-1024": {
"do_lowercase_and_remove_accent": True, "do_lowercase_and_remove_accent": True,
"id2lang": {"0": "de", "1": "en"}, "id2lang": {0: "de", 1: "en"},
"lang2id": {"de": 0, "en": 1}, "lang2id": {"de": 0, "en": 1},
}, },
"xlm-mlm-17-1280": { "xlm-mlm-17-1280": {
"do_lowercase_and_remove_accent": False, "do_lowercase_and_remove_accent": False,
"id2lang": { "id2lang": {
"0": "ar", 0: "ar",
"1": "de", 1: "de",
"2": "en", 2: "en",
"3": "es", 3: "es",
"4": "fr", 4: "fr",
"5": "hi", 5: "hi",
"6": "it", 6: "it",
"7": "ja", 7: "ja",
"8": "ko", 8: "ko",
"9": "nl", 9: "nl",
"10": "pl", 10: "pl",
"11": "pt", 11: "pt",
"12": "ru", 12: "ru",
"13": "sv", 13: "sv",
"14": "tr", 14: "tr",
"15": "vi", 15: "vi",
"16": "zh", 16: "zh",
}, },
"lang2id": { "lang2id": {
"ar": 0, "ar": 0,
...@@ -220,106 +220,106 @@ PRETRAINED_INIT_CONFIGURATION = { ...@@ -220,106 +220,106 @@ PRETRAINED_INIT_CONFIGURATION = {
"xlm-mlm-100-1280": { "xlm-mlm-100-1280": {
"do_lowercase_and_remove_accent": False, "do_lowercase_and_remove_accent": False,
"id2lang": { "id2lang": {
"0": "af", 0: "af",
"1": "als", 1: "als",
"2": "am", 2: "am",
"3": "an", 3: "an",
"4": "ang", 4: "ang",
"5": "ar", 5: "ar",
"6": "arz", 6: "arz",
"7": "ast", 7: "ast",
"8": "az", 8: "az",
"9": "bar", 9: "bar",
"10": "be", 10: "be",
"11": "bg", 11: "bg",
"12": "bn", 12: "bn",
"13": "br", 13: "br",
"14": "bs", 14: "bs",
"15": "ca", 15: "ca",
"16": "ceb", 16: "ceb",
"17": "ckb", 17: "ckb",
"18": "cs", 18: "cs",
"19": "cy", 19: "cy",
"20": "da", 20: "da",
"21": "de", 21: "de",
"22": "el", 22: "el",
"23": "en", 23: "en",
"24": "eo", 24: "eo",
"25": "es", 25: "es",
"26": "et", 26: "et",
"27": "eu", 27: "eu",
"28": "fa", 28: "fa",
"29": "fi", 29: "fi",
"30": "fr", 30: "fr",
"31": "fy", 31: "fy",
"32": "ga", 32: "ga",
"33": "gan", 33: "gan",
"34": "gl", 34: "gl",
"35": "gu", 35: "gu",
"36": "he", 36: "he",
"37": "hi", 37: "hi",
"38": "hr", 38: "hr",
"39": "hu", 39: "hu",
"40": "hy", 40: "hy",
"41": "ia", 41: "ia",
"42": "id", 42: "id",
"43": "is", 43: "is",
"44": "it", 44: "it",
"45": "ja", 45: "ja",
"46": "jv", 46: "jv",
"47": "ka", 47: "ka",
"48": "kk", 48: "kk",
"49": "kn", 49: "kn",
"50": "ko", 50: "ko",
"51": "ku", 51: "ku",
"52": "la", 52: "la",
"53": "lb", 53: "lb",
"54": "lt", 54: "lt",
"55": "lv", 55: "lv",
"56": "mk", 56: "mk",
"57": "ml", 57: "ml",
"58": "mn", 58: "mn",
"59": "mr", 59: "mr",
"60": "ms", 60: "ms",
"61": "my", 61: "my",
"62": "nds", 62: "nds",
"63": "ne", 63: "ne",
"64": "nl", 64: "nl",
"65": "nn", 65: "nn",
"66": "no", 66: "no",
"67": "oc", 67: "oc",
"68": "pl", 68: "pl",
"69": "pt", 69: "pt",
"70": "ro", 70: "ro",
"71": "ru", 71: "ru",
"72": "scn", 72: "scn",
"73": "sco", 73: "sco",
"74": "sh", 74: "sh",
"75": "si", 75: "si",
"76": "simple", 76: "simple",
"77": "sk", 77: "sk",
"78": "sl", 78: "sl",
"79": "sq", 79: "sq",
"80": "sr", 80: "sr",
"81": "sv", 81: "sv",
"82": "sw", 82: "sw",
"83": "ta", 83: "ta",
"84": "te", 84: "te",
"85": "th", 85: "th",
"86": "tl", 86: "tl",
"87": "tr", 87: "tr",
"88": "tt", 88: "tt",
"89": "uk", 89: "uk",
"90": "ur", 90: "ur",
"91": "uz", 91: "uz",
"92": "vi", 92: "vi",
"93": "war", 93: "war",
"94": "wuu", 94: "wuu",
"95": "yi", 95: "yi",
"96": "zh", 96: "zh",
"97": "zh_classical", 97: "zh_classical",
"98": "zh_min_nan", 98: "zh_min_nan",
"99": "zh_yue", 99: "zh_yue",
}, },
"lang2id": { "lang2id": {
"af": 0, "af": 0,
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment