Upload 8 files

Browse files

Files changed (8) hide show

added_tokens.json +302 -0
config.json +26 -0
pytorch_model.bin +3 -0
special_tokens_map.json +7 -0
stats.json +1 -0
tokenizer.json +0 -0
tokenizer_config.json +15 -0
vocab.txt +0 -0

added_tokens.json ADDED Viewed

	@@ -0,0 +1,302 @@

+{
+  "\\Bbb": 29048,
+  "\\Big": 29275,
+  "\\Bigl": 29257,
+  "\\Bigr": 29259,
+  "\\Box": 29280,
+  "\\Delta": 29063,
+  "\\Gamma": 29084,
+  "\\Im": 29286,
+  "\\Lambda": 29157,
+  "\\Leftarrow": 29278,
+  "\\Leftrightarrow": 29147,
+  "\\Longleftrightarrow": 29270,
+  "\\Longrightarrow": 29211,
+  "\\Omega": 29059,
+  "\\Phi": 29130,
+  "\\Pi": 29229,
+  "\\Pr": 29202,
+  "\\Psi": 29207,
+  "\\R": 29247,
+  "\\Re": 29238,
+  "\\Rightarrow": 29061,
+  "\\Sigma": 29132,
+  "\\Theta": 29203,
+  "\\Vert": 29137,
+  "\\\\": 29004,
+  "\\a": 29254,
+  "\\aleph": 29248,
+  "\\alpha": 29023,
+  "\\angle": 29160,
+  "\\approx": 29074,
+  "\\arcsin": 29279,
+  "\\arctan": 29186,
+  "\\arg": 29249,
+  "\\ast": 29135,
+  "\\b": 29281,
+  "\\backslash": 29151,
+  "\\bar": 29065,
+  "\\barwedge": 29252,
+  "\\begin": 29016,
+  "\\beta": 29041,
+  "\\big": 29103,
+  "\\bigcap": 29153,
+  "\\bigcup": 29117,
+  "\\bigg": 29123,
+  "\\biggl": 29294,
+  "\\biggr": 29288,
+  "\\bigl": 29210,
+  "\\bigoplus": 29237,
+  "\\bigr": 29198,
+  "\\bigtriangleup": 29272,
+  "\\bigwedge": 29295,
+  "\\binom": 29047,
+  "\\blacksquare": 29290,
+  "\\bmod": 29167,
+  "\\boldsymbol": 29155,
+  "\\bot": 29246,
+  "\\boxdot": 29226,
+  "\\boxed": 29255,
+  "\\bullet": 29182,
+  "\\cal": 29204,
+  "\\cancel": 29125,
+  "\\cap": 29033,
+  "\\cdot": 28996,
+  "\\cdots": 29018,
+  "\\cfrac": 29240,
+  "\\chi": 29102,
+  "\\choose": 29129,
+  "\\circ": 29051,
+  "\\colon": 29131,
+  "\\coloneqq": 29134,
+  "\\color": 29212,
+  "\\complement": 29116,
+  "\\cong": 29106,
+  "\\cos": 29019,
+  "\\cosh": 29183,
+  "\\cot": 29087,
+  "\\cr": 29199,
+  "\\csc": 29072,
+  "\\cup": 29045,
+  "\\d": 29236,
+  "\\dagger": 29194,
+  "\\ddot": 29282,
+  "\\ddots": 29208,
+  "\\deg": 29205,
+  "\\delta": 29043,
+  "\\det": 29152,
+  "\\dfrac": 29002,
+  "\\diamond": 29262,
+  "\\dim": 29146,
+  "\\displaystyle": 29075,
+  "\\div": 29120,
+  "\\dot": 29143,
+  "\\dots": 29073,
+  "\\dotsc": 29263,
+  "\\dotsm": 29274,
+  "\\downarrow": 29235,
+  "\\dt": 29291,
+  "\\dx": 29206,
+  "\\ell": 29114,
+  "\\emptyset": 29090,
+  "\\end": 29017,
+  "\\epsilon": 29028,
+  "\\equiv": 29049,
+  "\\eta": 29097,
+  "\\exists": 29092,
+  "\\exp": 29133,
+  "\\f": 29245,
+  "\\forall": 29044,
+  "\\frac": 28997,
+  "\\frak": 29268,
+  "\\gamma": 29057,
+  "\\gcd": 29189,
+  "\\ge": 29081,
+  "\\gep": 29223,
+  "\\geq": 29020,
+  "\\geqslant": 29219,
+  "\\ger": 29224,
+  "\\ges": 29220,
+  "\\get": 29225,
+  "\\gray": 29113,
+  "\\gt": 29150,
+  "\\hat": 29085,
+  "\\hline": 29178,
+  "\\hookrightarrow": 29251,
+  "\\hphantom": 29177,
+  "\\hspace": 29169,
+  "\\iff": 29140,
+  "\\iint": 29214,
+  "\\implies": 29082,
+  "\\in": 29001,
+  "\\inf": 29149,
+  "\\infty": 29006,
+  "\\int": 29009,
+  "\\iota": 29261,
+  "\\kappa": 29156,
+  "\\ker": 29162,
+  "\\lVert": 29181,
+  "\\lambda": 29030,
+  "\\land": 29136,
+  "\\langle": 29052,
+  "\\lbrace": 29192,
+  "\\lceil": 29221,
+  "\\lcm": 29175,
+  "\\ldots": 29067,
+  "\\le": 29046,
+  "\\left": 28998,
+  "\\leftarrow": 29269,
+  "\\leftrightarrow": 29250,
+  "\\lep": 29227,
+  "\\leq": 29011,
+  "\\leqslant": 29172,
+  "\\ler": 29218,
+  "\\les": 29217,
+  "\\let": 29222,
+  "\\lfloor": 29122,
+  "\\lim": 29025,
+  "\\liminf": 29216,
+  "\\limits": 29027,
+  "\\limsup": 29180,
+  "\\ln": 29037,
+  "\\lnot": 29168,
+  "\\log": 29032,
+  "\\longrightarrow": 29154,
+  "\\lor": 29158,
+  "\\lt": 29100,
+  "\\lvert": 29142,
+  "\\mapsto": 29101,
+  "\\mathbb": 29000,
+  "\\mathbf": 29031,
+  "\\mathcal": 29022,
+  "\\mathfrak": 29066,
+  "\\mathop": 29239,
+  "\\mathrm": 29024,
+  "\\mathscr": 29108,
+  "\\mathsf": 29164,
+  "\\max": 29118,
+  "\\mid": 29053,
+  "\\middle": 29179,
+  "\\min": 29139,
+  "\\mod": 29141,
+  "\\models": 29276,
+  "\\mu": 29039,
+  "\\nabla": 29107,
+  "\\ne": 29109,
+  "\\neg": 29144,
+  "\\neq": 29008,
+  "\\newcommand": 29209,
+  "\\ni": 29271,
+  "\\nlet": 29273,
+  "\\nmid": 29244,
+  "\\not": 29126,
+  "\\notin": 29148,
+  "\\nu": 29086,
+  "\\odot": 29241,
+  "\\oint": 29256,
+  "\\omega": 29054,
+  "\\operatorname": 29034,
+  "\\oplus": 29110,
+  "\\oslash": 29253,
+  "\\otimes": 29083,
+  "\\over": 29099,
+  "\\overline": 29058,
+  "\\overset": 29191,
+  "\\p": 29283,
+  "\\parallel": 29287,
+  "\\pars": 29265,
+  "\\partial": 29021,
+  "\\perp": 29165,
+  "\\phantom": 29187,
+  "\\phi": 29036,
+  "\\pi": 29005,
+  "\\pm": 29042,
+  "\\pmatrix": 29242,
+  "\\pmod": 29098,
+  "\\pmxd": 29195,
+  "\\prec": 29289,
+  "\\prime": 29096,
+  "\\prod": 29094,
+  "\\psi": 29076,
+  "\\qquad": 29112,
+  "\\quad": 29055,
+  "\\rVert": 29184,
+  "\\rangle": 29050,
+  "\\rbrace": 29196,
+  "\\rceil": 29215,
+  "\\rfloor": 29121,
+  "\\rho": 29069,
+  "\\right": 28999,
+  "\\rightarrow": 29029,
+  "\\root": 29258,
+  "\\rvert": 29145,
+  "\\scriptsize": 29234,
+  "\\sec": 29071,
+  "\\setminus": 29079,
+  "\\sf": 29292,
+  "\\sigma": 29040,
+  "\\sim": 29128,
+  "\\simeq": 29174,
+  "\\sin": 29014,
+  "\\sinh": 29188,
+  "\\space": 29093,
+  "\\sqrt": 29007,
+  "\\square": 29230,
+  "\\stackrel": 29193,
+  "\\star": 29161,
+  "\\subset": 29077,
+  "\\subseteq": 29088,
+  "\\subsetneq": 29264,
+  "\\substack": 29176,
+  "\\sum": 29010,
+  "\\sup": 29095,
+  "\\supset": 29260,
+  "\\supseteq": 29293,
+  "\\tag": 29078,
+  "\\tan": 29056,
+  "\\tanh": 29284,
+  "\\tau": 29064,
+  "\\text": 29013,
+  "\\textbf": 29115,
+  "\\textit": 29277,
+  "\\textrm": 29159,
+  "\\tfrac": 29035,
+  "\\therefore": 29243,
+  "\\theta": 29026,
+  "\\thinspace": 29038,
+  "\\tilde": 29111,
+  "\\times": 29003,
+  "\\to": 29012,
+  "\\top": 29213,
+  "\\triangle": 29173,
+  "\\triangleleft": 29285,
+  "\\underbrace": 29170,
+  "\\underline": 29171,
+  "\\uparrow": 29231,
+  "\\varepsilon": 29062,
+  "\\varnothing": 29166,
+  "\\varphi": 29060,
+  "\\vartheta": 29124,
+  "\\vdash": 29232,
+  "\\vdots": 29138,
+  "\\vec": 29127,
+  "\\vee": 29163,
+  "\\vert": 29105,
+  "\\vphantom": 29185,
+  "\\wedge": 29104,
+  "\\widehat": 29197,
+  "\\widetilde": 29201,
+  "\\x": 29200,
+  "\\xi": 29080,
+  "\\xrightarrow": 29190,
+  "\\zeta": 29068,
+  "\\|": 29015,
+  "align": 29089,
+  "align*": 29119,
+  "bmatrix": 29091,
+  "eqnarray": 29228,
+  "eqnarray*": 29266,
+  "equation*": 29233,
+  "pmatrix": 29070,
+  "vmatrix": 29267
+}

config.json ADDED Viewed

	@@ -0,0 +1,26 @@

+{
+  "_name_or_path": "/models/tokenized",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.25.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 29296
+}

pytorch_model.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:7ad0e71c27c6fb4af46a1c398603e50805a68b79af61bb3543e9bcc86b4b6166
+size 434231085

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,7 @@

+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

stats.json ADDED Viewed

	@@ -0,0 +1 @@


1	+ {"objectives": "MFM,NFIR,FFIR,MTM", "mixed": true, "steps": "250000"}

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,15 @@

+{
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "/models/tokenized",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": "/models/tokenized/special_tokens_map.json",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

vocab.txt ADDED Viewed

The diff for this file is too large to render. See raw diff