Anja Reusch commited on
Commit
de44ce9
1 Parent(s): 3ff6c8a

added model and tokenizer files

Browse files
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"\\subsetneqq": 50662, "\\psi": 50607, "\\lessapprox": 50496, "\\bmod": 50352, "\\phi": 50590, "\\deg": 50390, "\\unlhd": 50701, "\\gneq": 50440, "\\backslash": 50333, "\\precneqq": 50600, "\\rightleftarrows": 50624, "\\rceil": 50615, "\\varnothing": 50724, "\\varinjlim": 50720, "\\varTheta": 50716, "\\leftrightarrows": 50490, "\\triangleright": 50697, "\\lnot": 50511, "\\varDelta": 50710, "\\divideontimes": 50397, "\\vee": 50741, "\\lbrack": 50479, "\\exists": 50424, "\\varliminf": 50722, "\\Iota": 50278, "\\cdot": 50359, "\\atop": 50329, "\\gtreqqless": 50447, "\\frac": 50427, "\\updownarrow": 50704, "\\bigvee": 50349, "\\rmoustache": 50628, "\\perp": 50589, "\\iddots": 50454, "\\gtrsim": 50449, "\\mu": 50535, "\\precapprox": 50596, "\\eta": 50422, "\\gvertneqq": 50450, "\\leftrightharpoons": 50491, "\\Rightarrow": 50299, "\\downharpoonleft": 50409, "\\prec": 50595, "\\leqslant": 50495, "\\underline": 50699, "\\barwedge": 50334, "\\rightarrowtail": 50621, "\\Doteq": 50273, "\\max": 50528, "\\veebar": 50742, "\\longrightarrow": 50516, "\\gtrless": 50448, "\\looparrowright": 50518, "\\lVert": 50473, "\\dot=": 50406, "\\bigoplus": 50343, "\\lfloor": 50499, "\\iiint": 50458, "\\forall": 50426, "\\leqq": 50494, "\\Psi": 50296, "\\equiv": 50421, "\\gtrdot": 50445, "\\gnapprox": 50439, "\\theta": 50686, "\\succnapprox": 50667, "\\Tau": 50305, "\\preccurlyeq": 50597, "alignat": 50756, "\\geqslant": 50434, "\\neg": 50544, "\\measuredangle": 50529, "\\ddots": 50389, "\\precnapprox": 50599, "\\choose": 50363, "\\Alpha": 50265, "\\supsetneq": 50676, "\\bracevert": 50355, "\\varsubsetneq": 50731, "\\And": 50266, "\\Cup": 50271, "\\Kappa": 50280, "\\bigotimes": 50344, "\\sup": 50672, "\\dashv": 50384, "\\tan": 50679, "\\lt": 50520, "\\varkappa": 50721, "\\circlearrowright": 50367, "\\biguplus": 50348, "\\inf": 50464, "\\eqcirc": 50417, "\\mapsto": 50524, "\\Gamma": 50277, "\\lceil": 50478, "\\jmath": 50470, "\\subset": 50658, "\\Lambda": 50281, "\\tfrac": 50685, "\\Rsh": 50301, "\\sphericalangle": 50649, "\\nparallel": 50561, "\\iota": 50469, "\\cr": 50375, "\\textstyle": 50684, "\\varXi": 50718, "\\Beta": 50268, "\\binom": 50351, "\\imath": 50460, "\\omicron": 50576, "\\rtimes": 50630, "\\nleqslant": 50557, "\\neq": 50545, "\\sqsubset": 50653, "equation": 50760, "\\rightharpoonup": 50623, "\\mathcal": 50526, "\\Epsilon": 50275, "\\Leftrightarrow": 50283, "\\sim": 50641, "\\mathrm": 50527, "\\rVert": 50611, "\\varPhi": 50712, "\\dotso": 50404, "\\enspace": 50415, "\\cong": 50369, "\\Theta": 50306, "\\int": 50467, "\\otimes": 50580, "\\leftarrowtail": 50485, "\\smallsmile": 50648, "\\wedge": 50744, "\\det": 50392, "\\lneq": 50509, "\\right": 50619, "\\npreceq": 50563, "\\cot": 50373, "\\nsupseteq": 50569, "\\exp": 50425, "\\nwarrow": 50571, "\\iff": 50456, "\\%": 50750, "\\propto": 50606, "\\varlimsup": 50723, "\\sqrt": 50652, "\\ast": 50327, "\\succneqq": 50668, "\\longleftrightarrow": 50514, "\\uplus": 50707, "\\sqcup": 50651, "\\gt": 50443, "\\prod": 50604, "\\mathbb": 50525, "\\dots": 50399, "\\oplus": 50578, "\\asymp": 50328, "\\lbrace": 50477, "\\precsim": 50602, "\\hookrightarrow": 50453, "\\dbinom": 50385, "eqnarray": 50759, "\\hookleftarrow": 50452, "\\Chi": 50270, "pmatrix": 50765, "\\ll": 50505, "\\lnapprox": 50508, "\\lmoustache": 50506, "\\of": 50573, "\\varsupsetneqq": 50734, "\\in": 50463, "\\rightsquigarrow": 50627, "\\backsimeq": 50332, "\\smallfrown": 50645, "alignedat": 50757, "\\circlearrowleft": 50366, "\\bigcup": 50341, "\\Mu": 50289, ":=": 50752, "\\Rrightarrow": 50300, "\\VarOmega": 50311, "\\bowtie": 50354, "\\swarrow": 50678, "\\Leftarrow": 50282, "\\idotsint": 50455, "subarray": 50767, "\\Cap": 50269, "\\Sigma": 50302, "\\varphi": 50725, "\\dotsm": 50403, "\\rightleftharpoons": 50625, "\\not": 50560, "\\varpropto": 50728, "\\downdownarrows": 50408, "\\nu": 50570, "\\xrightarrow": 50748, "\\dotsc": 50401, "\\tbinom": 50682, "\\preceq": 50598, "\\subseteq": 50659, "\\looparrowleft": 50517, "\\tau": 50681, "\\lg": 50500, "\\Nu": 50290, "\\mp": 50534, "\\dotplus": 50398, "\\lesssim": 50498, "\\ker": 50472, "\\Upsilon": 50309, "\\rho": 50618, "\\eqsim": 50418, "\\nleq": 50555, "\\lambda": 50474, "\\ldots": 50480, "\\succsim": 50670, "\\nleftrightarrow": 50554, "\\bigwedge": 50350, "\\sigma": 50638, "\\dotsb": 50400, "\\injlim": 50466, "\\approxeq": 50321, "\\qquad": 50608, "\\langle": 50476, "\\times": 50689, "\\le": 50481, "\\rbrack": 50614, "\\tanh": 50680, "\\curvearrowright": 50383, "\\succcurlyeq": 50665, "\\ne": 50542, "\\succapprox": 50664, "\\overset": 50585, "\\subsetneq": 50661, "\\ngeqq": 50549, "\\Downarrow": 50274, "\\mod": 50533, "\\bigtriangledown": 50346, "\\mid": 50531, "\\arccos": 50322, "\\sec": 50635, "\\colon": 50368, "\\nsim": 50565, "\\unrhd": 50702, "\\triangle": 50692, "\\Zeta": 50314, "\\prime": 50603, "\\Longleftrightarrow": 50286, "\\sin": 50643, "\\downharpoonright": 50410, "\\owns": 50586, "\\operatorname": 50579, "\\triangleleft": 50694, "\\scriptstyle": 50633, "\\iiiint": 50457, "\\smallint": 50646, "\\rightarrow": 50620, "\\rangle": 50612, "\\dddot": 50387, "\\cfrac": 50361, "\\text": 50683, "\\ni": 50552, "\\nless": 50558, "\\Phi": 50293, "\\multimap": 50536, "\\eth": 50423, "\\succnsim": 50669, "\\div": 50396, "\\nRightarrow": 50539, "\\gg": 50436, "\\eqslantgtr": 50419, "\\nearrow": 50543, "\\dotsi": 50402, "\\dfrac": 50393, "\\ncong": 50541, "\\triangledown": 50693, "\\min": 50532, "\\thicksim": 50688, "\\infty": 50465, "\\sqsubseteq": 50654, "\\vartriangle": 50736, "\\Pr": 50295, "\\gets": 50435, "\\ddot": 50388, "\\impliedby": 50461, "\\rbrace": 50613, "\\supseteq": 50674, "\\end": 50414, "\\above": 50315, "\\curvearrowleft": 50382, "\\cup": 50377, "\\Join": 50279, "\\smallsetminus": 50647, "\\lvert": 50522, "\\top": 50691, "\\nLeftrightarrow": 50538, "\\searrow": 50634, "\\Arrowvert": 50267, "\\coprod": 50370, "\\cos": 50371, "\\nsubseteq": 50566, "\\upuparrows": 50709, "\\vartheta": 50735, "\\Longleftarrow": 50285, "\\hom": 50451, "\\vartriangleright": 50738, "\\emptyset": 50413, "\\vartriangleleft": 50737, "\\varsubsetneqq": 50732, "\\pm": 50592, "\\nmid": 50559, "\\longmapsto": 50515, "\\signum": 50640, "\\nexists": 50547, "\\odot": 50572, "\\sqcap": 50650, "\\precnsim": 50601, "\\varsigma": 50730, "\\csc": 50376, "\\rvert": 50631, "\\gnsim": 50442, "\\parallel": 50587, "\\Supset": 50304, "\\leq": 50493, "\\doteq": 50405, "\\upharpoonright": 50706, "\\rightrightarrows": 50626, "\\vert": 50743, "\\quad": 50609, "\\curlyeqprec": 50378, "\\aleph": 50316, "\\gtrapprox": 50444, "Vmatrix": 50755, "\\Re": 50297, "\\ln": 50507, "\\ngtr": 50551, "\\varepsilon": 50719, "\\varGamma": 50711, "\\Omicron": 50292, "\\bigcirc": 50340, "\\gtreqless": 50446, "\\longleftarrow": 50513, "\\lim": 50502, "\\liminf": 50503, "\\VarLambda": 50310, "\\cosh": 50372, "\\brack": 50356, "\\mho": 50530, "\\chi": 50362, "\\ggg": 50437, "\\nsucceq": 50568, "\\buildrel": 50357, "gathered": 50762, "\\curlywedge": 50381, "\\log": 50512, "\\Uparrow": 50307, "\\sgn": 50637, "\\Lleftarrow": 50284, "\\root": 50629, "\\curlyeqsucc": 50379, "\\gamma": 50429, "\\arcsin": 50323, "\\rightharpoondown": 50622, "\\land": 50475, "\\downarrow": 50407, "\\varprojlim": 50727, "\\between": 50337, "\\leftrightsquigarrow": 50492, "\\dim": 50394, "\\supset": 50673, "\\newline": 50546, "\\lor": 50519, "\\alpha": 50317, "\\Xi": 50313, "\\to": 50690, "\\partial": 50588, "\\backsim": 50331, "\\iint": 50459, "\\ge": 50431, "\\ell": 50411, "\\underset": 50700, "\\gggtr": 50438, "\\zeta": 50749, "\\pi": 50591, "\\coth": 50374, "\\ngeqslant": 50550, "\\geq": 50432, "\\succ": 50663, "\\backepsilon": 50330, "\\intop": 50468, "\\sqsupset": 50655, "\\Eta": 50276, "\\overline": 50583, "\\pod": 50594, "\\supsetneqq": 50677, "\\angle": 50319, "\\upharpoonleft": 50705, "\\varPi": 50713, "\\Delta": 50272, "\\stackrel": 50657, "\\varpi": 50726, "\\lvertneqq": 50523, "matrix": 50763, "\\omega": 50575, "\\subseteqq": 50660, "\\xi": 50746, "\\ddddot": 50386, "\\triangleq": 50696, "\\scriptscriptstyle": 50632, "\\leadsto": 50482, "\\bigsqcup": 50345, "\\implies": 50462, "\\varSigma": 50715, "\\ngeq": 50548, "\\Rho": 50298, "\\xleftarrow": 50747, "\\trianglerighteq": 50698, "\\amalg": 50318, "\\varsupsetneq": 50733, "vmatrix": 50768, "\\beta": 50335, "\\sinh": 50644, "\\leftharpoonup": 50487, "\\gneqq": 50441, "\\bigtriangleup": 50347, "\\supseteqq": 50675, "\\Updownarrow": 50308, "\\circ": 50364, "\\nleftarrow": 50553, "\\nrightarrow": 50564, "\\rfloor": 50616, "\\leftleftarrows": 50488, "bmatrix": 50758, "\\lessdot": 50497, "\\bigodot": 50342, "\\ltimes": 50521, "\\nprec": 50562, "\\oint": 50574, "\\kappa": 50471, "\\beth": 50336, "\\vdots": 50739, "\\arctan": 50324, "\\simeq": 50642, "\\nsucc": 50567, "\\varrho": 50729, "\\overrightarrow": 50584, "\\sign": 50639, "\\trianglelefteq": 50695, "\\nLeftarrow": 50537, "gather": 50761, "\\leftrightarrow": 50489, "\\left": 50483, "\\displaystyle": 50395, "\\arg": 50325, "Bmatrix": 50754, "\\lgroup": 50501, "\\circeq": 50365, "\\uparrow": 50703, "\\over": 50581, "\\overleftarrow": 50582, "\\delta": 50391, "\\qvar": 50610, "\\leftharpoondown": 50486, "\\Longrightarrow": 50287, "\\thickapprox": 50687, "\\cap": 50358, "\\pmod": 50593, "\\wr": 50745, "\\sqsupseteq": 50656, "\\begin": 50338, "\\nleqq": 50556, "\\nabla": 50540, "\\Subset": 50303, "\\limsup": 50504, "\\eqslantless": 50420, "\\Pi": 50294, "∞": 50753, "\\geqq": 50433, "\\^": 50751, "\\upsilon": 50708, "\\setminus": 50636, "\\bot": 50353, "\\leftarrow": 50484, "\\vec": 50740, "\\sum": 50671, "\\frown": 50428, "\\varPsi": 50714, "\\lneqq": 50510, "\\arrowvert": 50326, "\\Vert": 50312, "\\Lsh": 50288, "\\Omega": 50291, "\\projlim": 50605, "\\empty": 50412, "multline": 50764, "\\gcd": 50430, "\\approx": 50320, "\\epsilon": 50416, "\\ominus": 50577, "\\rgroup": 50617, "\\cdots": 50360, "\\succeq": 50666, "\\bigcap": 50339, "smallmatrix": 50766, "\\varUpsilon": 50717, "\\curlyvee": 50380}
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/scratch/ws/1/s8252120-polbert/Slurm-for-ALBERT_Math/ALBERT-for-Math-AR/untrained_models/model_roberta-base_with_latex",
3
+ "architectures": [
4
+ "RobertaForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-05,
17
+ "max_position_embeddings": 514,
18
+ "model_type": "roberta",
19
+ "num_attention_heads": 12,
20
+ "num_hidden_layers": 12,
21
+ "pad_token_id": 1,
22
+ "position_embedding_type": "absolute",
23
+ "torch_dtype": "float32",
24
+ "transformers_version": "4.9.2",
25
+ "type_vocab_size": 1,
26
+ "use_cache": true,
27
+ "vocab_size": 50769
28
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df32449503572d7b22039078e82b1e8a30fc93b85aa0fcc90594943ed5cc4404
3
+ size 500412011
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-base", "tokenizer_class": "RobertaTokenizer"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff