Delete training_ConMATH_ConMATH-2023-03-29_18-47-43
Browse files- training_ConMATH_ConMATH-2023-03-29_18-47-43/0_Asym/140000857040976_MarkuplmTransformerForConMATH/added_tokens.json +0 -4
- training_ConMATH_ConMATH-2023-03-29_18-47-43/0_Asym/140000857040976_MarkuplmTransformerForConMATH/config.json +0 -34
- training_ConMATH_ConMATH-2023-03-29_18-47-43/0_Asym/140000857040976_MarkuplmTransformerForConMATH/generation_config.json +0 -7
- training_ConMATH_ConMATH-2023-03-29_18-47-43/0_Asym/140000857040976_MarkuplmTransformerForConMATH/merges.txt +0 -0
- training_ConMATH_ConMATH-2023-03-29_18-47-43/0_Asym/140000857040976_MarkuplmTransformerForConMATH/preprocessor_config.json +0 -4
- training_ConMATH_ConMATH-2023-03-29_18-47-43/0_Asym/140000857040976_MarkuplmTransformerForConMATH/pytorch_model.bin +0 -3
- training_ConMATH_ConMATH-2023-03-29_18-47-43/0_Asym/140000857040976_MarkuplmTransformerForConMATH/sentence_bert_config.json +0 -4
- training_ConMATH_ConMATH-2023-03-29_18-47-43/0_Asym/140000857040976_MarkuplmTransformerForConMATH/special_tokens_map.json +0 -15
- training_ConMATH_ConMATH-2023-03-29_18-47-43/0_Asym/140000857040976_MarkuplmTransformerForConMATH/tokenizer.json +0 -0
- training_ConMATH_ConMATH-2023-03-29_18-47-43/0_Asym/140000857040976_MarkuplmTransformerForConMATH/tokenizer_config.json +0 -268
- training_ConMATH_ConMATH-2023-03-29_18-47-43/0_Asym/140000857040976_MarkuplmTransformerForConMATH/vocab.json +0 -0
- training_ConMATH_ConMATH-2023-03-29_18-47-43/0_Asym/140000860578048_Transformer/config.json +0 -24
- training_ConMATH_ConMATH-2023-03-29_18-47-43/0_Asym/140000860578048_Transformer/pytorch_model.bin +0 -3
- training_ConMATH_ConMATH-2023-03-29_18-47-43/0_Asym/140000860578048_Transformer/sentence_bert_config.json +0 -4
- training_ConMATH_ConMATH-2023-03-29_18-47-43/0_Asym/140000860578048_Transformer/special_tokens_map.json +0 -15
- training_ConMATH_ConMATH-2023-03-29_18-47-43/0_Asym/140000860578048_Transformer/tokenizer.json +0 -0
- training_ConMATH_ConMATH-2023-03-29_18-47-43/0_Asym/140000860578048_Transformer/tokenizer_config.json +0 -16
- training_ConMATH_ConMATH-2023-03-29_18-47-43/0_Asym/140000860578048_Transformer/vocab.txt +0 -0
- training_ConMATH_ConMATH-2023-03-29_18-47-43/0_Asym/config.json +0 -17
- training_ConMATH_ConMATH-2023-03-29_18-47-43/1_Pooling/config.json +0 -9
- training_ConMATH_ConMATH-2023-03-29_18-47-43/README.md +0 -93
- training_ConMATH_ConMATH-2023-03-29_18-47-43/config_sentence_transformers.json +0 -7
- training_ConMATH_ConMATH-2023-03-29_18-47-43/modules.json +0 -14
training_ConMATH_ConMATH-2023-03-29_18-47-43/0_Asym/140000857040976_MarkuplmTransformerForConMATH/added_tokens.json
DELETED
@@ -1,4 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"<end-of-node>": 50266,
|
3 |
-
"[empty-title]": 50265
|
4 |
-
}
|
|
|
|
|
|
|
|
|
|
training_ConMATH_ConMATH-2023-03-29_18-47-43/0_Asym/140000857040976_MarkuplmTransformerForConMATH/config.json
DELETED
@@ -1,34 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "output/training_markuplm_simcsemicrosoft-markuplm-base-2023-03-16_18-40-10",
|
3 |
-
"architectures": [
|
4 |
-
"MarkupLMModel"
|
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_depth": 50,
|
18 |
-
"max_position_embeddings": 514,
|
19 |
-
"max_xpath_subs_unit_embeddings": 1024,
|
20 |
-
"max_xpath_tag_unit_embeddings": 256,
|
21 |
-
"model_type": "markuplm",
|
22 |
-
"num_attention_heads": 12,
|
23 |
-
"num_hidden_layers": 12,
|
24 |
-
"pad_token_id": 1,
|
25 |
-
"position_embedding_type": "absolute",
|
26 |
-
"subs_pad_id": 1001,
|
27 |
-
"tag_pad_id": 216,
|
28 |
-
"torch_dtype": "float32",
|
29 |
-
"transformers_version": "4.26.1",
|
30 |
-
"type_vocab_size": 1,
|
31 |
-
"use_cache": true,
|
32 |
-
"vocab_size": 50267,
|
33 |
-
"xpath_unit_hidden_size": 32
|
34 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
training_ConMATH_ConMATH-2023-03-29_18-47-43/0_Asym/140000857040976_MarkuplmTransformerForConMATH/generation_config.json
DELETED
@@ -1,7 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_from_model_config": true,
|
3 |
-
"bos_token_id": 0,
|
4 |
-
"eos_token_id": 2,
|
5 |
-
"pad_token_id": 1,
|
6 |
-
"transformers_version": "4.26.1"
|
7 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
training_ConMATH_ConMATH-2023-03-29_18-47-43/0_Asym/140000857040976_MarkuplmTransformerForConMATH/merges.txt
DELETED
The diff for this file is too large to render.
See raw diff
|
|
training_ConMATH_ConMATH-2023-03-29_18-47-43/0_Asym/140000857040976_MarkuplmTransformerForConMATH/preprocessor_config.json
DELETED
@@ -1,4 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"feature_extractor_type": "MarkupLMFeatureExtractor",
|
3 |
-
"processor_class": "MarkupLMProcessor"
|
4 |
-
}
|
|
|
|
|
|
|
|
|
|
training_ConMATH_ConMATH-2023-03-29_18-47-43/0_Asym/140000857040976_MarkuplmTransformerForConMATH/pytorch_model.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:644beecc9dcbf64a22d4a6058e21e564e47333f7384d16d7f85a1c43be7a4b0e
|
3 |
-
size 540919261
|
|
|
|
|
|
|
|
training_ConMATH_ConMATH-2023-03-29_18-47-43/0_Asym/140000857040976_MarkuplmTransformerForConMATH/sentence_bert_config.json
DELETED
@@ -1,4 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"max_seq_length": 512,
|
3 |
-
"do_lower_case": false
|
4 |
-
}
|
|
|
|
|
|
|
|
|
|
training_ConMATH_ConMATH-2023-03-29_18-47-43/0_Asym/140000857040976_MarkuplmTransformerForConMATH/special_tokens_map.json
DELETED
@@ -1,15 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"bos_token": "<s>",
|
3 |
-
"cls_token": "<s>",
|
4 |
-
"eos_token": "</s>",
|
5 |
-
"mask_token": {
|
6 |
-
"content": "<mask>",
|
7 |
-
"lstrip": true,
|
8 |
-
"normalized": false,
|
9 |
-
"rstrip": false,
|
10 |
-
"single_word": false
|
11 |
-
},
|
12 |
-
"pad_token": "<pad>",
|
13 |
-
"sep_token": "</s>",
|
14 |
-
"unk_token": "<unk>"
|
15 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
training_ConMATH_ConMATH-2023-03-29_18-47-43/0_Asym/140000857040976_MarkuplmTransformerForConMATH/tokenizer.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|
training_ConMATH_ConMATH-2023-03-29_18-47-43/0_Asym/140000857040976_MarkuplmTransformerForConMATH/tokenizer_config.json
DELETED
@@ -1,268 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"add_prefix_space": false,
|
3 |
-
"bos_token": {
|
4 |
-
"__type": "AddedToken",
|
5 |
-
"content": "<s>",
|
6 |
-
"lstrip": false,
|
7 |
-
"normalized": true,
|
8 |
-
"rstrip": false,
|
9 |
-
"single_word": false
|
10 |
-
},
|
11 |
-
"cls_token": {
|
12 |
-
"__type": "AddedToken",
|
13 |
-
"content": "<s>",
|
14 |
-
"lstrip": false,
|
15 |
-
"normalized": true,
|
16 |
-
"rstrip": false,
|
17 |
-
"single_word": false
|
18 |
-
},
|
19 |
-
"eos_token": {
|
20 |
-
"__type": "AddedToken",
|
21 |
-
"content": "</s>",
|
22 |
-
"lstrip": false,
|
23 |
-
"normalized": true,
|
24 |
-
"rstrip": false,
|
25 |
-
"single_word": false
|
26 |
-
},
|
27 |
-
"errors": "replace",
|
28 |
-
"mask_token": {
|
29 |
-
"__type": "AddedToken",
|
30 |
-
"content": "<mask>",
|
31 |
-
"lstrip": true,
|
32 |
-
"normalized": true,
|
33 |
-
"rstrip": false,
|
34 |
-
"single_word": false
|
35 |
-
},
|
36 |
-
"max_depth": 50,
|
37 |
-
"max_width": 1000,
|
38 |
-
"model_max_length": 512,
|
39 |
-
"name_or_path": "output/training_markuplm_simcsemicrosoft-markuplm-base-2023-03-16_18-40-10",
|
40 |
-
"only_label_first_subword": true,
|
41 |
-
"pad_token": {
|
42 |
-
"__type": "AddedToken",
|
43 |
-
"content": "<pad>",
|
44 |
-
"lstrip": false,
|
45 |
-
"normalized": true,
|
46 |
-
"rstrip": false,
|
47 |
-
"single_word": false
|
48 |
-
},
|
49 |
-
"pad_token_label": -100,
|
50 |
-
"pad_width": 1001,
|
51 |
-
"processor_class": "MarkupLMProcessor",
|
52 |
-
"sep_token": {
|
53 |
-
"__type": "AddedToken",
|
54 |
-
"content": "</s>",
|
55 |
-
"lstrip": false,
|
56 |
-
"normalized": true,
|
57 |
-
"rstrip": false,
|
58 |
-
"single_word": false
|
59 |
-
},
|
60 |
-
"special_tokens_map_file": null,
|
61 |
-
"tags_dict": {
|
62 |
-
"abs": 0,
|
63 |
-
"and": 1,
|
64 |
-
"annotation": 2,
|
65 |
-
"annotation-xml": 3,
|
66 |
-
"apply": 4,
|
67 |
-
"approx": 5,
|
68 |
-
"arccos": 6,
|
69 |
-
"arccosh": 7,
|
70 |
-
"arccot": 8,
|
71 |
-
"arccoth": 9,
|
72 |
-
"arccsc": 10,
|
73 |
-
"arccsch": 11,
|
74 |
-
"arcsec": 12,
|
75 |
-
"arcsech": 13,
|
76 |
-
"arcsin": 14,
|
77 |
-
"arcsinh": 15,
|
78 |
-
"arctan": 16,
|
79 |
-
"arctanh": 17,
|
80 |
-
"arg": 18,
|
81 |
-
"bind": 19,
|
82 |
-
"bvar": 20,
|
83 |
-
"card": 21,
|
84 |
-
"cartesianproduct": 22,
|
85 |
-
"cbytes": 23,
|
86 |
-
"ceiling": 24,
|
87 |
-
"cerror": 25,
|
88 |
-
"ci": 26,
|
89 |
-
"cn": 27,
|
90 |
-
"codomain": 28,
|
91 |
-
"complexes": 29,
|
92 |
-
"compose": 30,
|
93 |
-
"condition": 31,
|
94 |
-
"conjugate": 32,
|
95 |
-
"cos": 33,
|
96 |
-
"cosh": 34,
|
97 |
-
"cot": 35,
|
98 |
-
"coth": 36,
|
99 |
-
"cs": 37,
|
100 |
-
"csc": 38,
|
101 |
-
"csch": 39,
|
102 |
-
"csymbol": 40,
|
103 |
-
"curl": 41,
|
104 |
-
"declare": 42,
|
105 |
-
"degree": 43,
|
106 |
-
"determinant": 44,
|
107 |
-
"diff": 45,
|
108 |
-
"divergence": 46,
|
109 |
-
"divide": 47,
|
110 |
-
"domain": 48,
|
111 |
-
"domainofapplication": 49,
|
112 |
-
"emptyset": 50,
|
113 |
-
"eq": 51,
|
114 |
-
"equivalent": 52,
|
115 |
-
"eulergamma": 53,
|
116 |
-
"exists": 54,
|
117 |
-
"exp": 55,
|
118 |
-
"exponentiale": 56,
|
119 |
-
"factorial": 57,
|
120 |
-
"factorof": 58,
|
121 |
-
"false": 59,
|
122 |
-
"floor": 60,
|
123 |
-
"fn": 61,
|
124 |
-
"forall": 62,
|
125 |
-
"gcd": 63,
|
126 |
-
"geq": 64,
|
127 |
-
"grad": 65,
|
128 |
-
"gt": 66,
|
129 |
-
"ident": 67,
|
130 |
-
"image": 68,
|
131 |
-
"imaginary": 69,
|
132 |
-
"imaginaryi": 70,
|
133 |
-
"implies": 71,
|
134 |
-
"in": 72,
|
135 |
-
"infinity": 73,
|
136 |
-
"int": 74,
|
137 |
-
"integers": 75,
|
138 |
-
"intersect": 76,
|
139 |
-
"interval": 77,
|
140 |
-
"inverse": 78,
|
141 |
-
"lambda": 79,
|
142 |
-
"laplacian": 80,
|
143 |
-
"lcm": 81,
|
144 |
-
"leq": 82,
|
145 |
-
"limit": 83,
|
146 |
-
"list": 84,
|
147 |
-
"ln": 85,
|
148 |
-
"log": 86,
|
149 |
-
"logbase": 87,
|
150 |
-
"lowlimit": 88,
|
151 |
-
"lt": 89,
|
152 |
-
"maction": 90,
|
153 |
-
"maligngroup": 91,
|
154 |
-
"malignmark": 92,
|
155 |
-
"math": 93,
|
156 |
-
"matrix": 94,
|
157 |
-
"matrixrow": 95,
|
158 |
-
"max": 96,
|
159 |
-
"mean": 97,
|
160 |
-
"median": 98,
|
161 |
-
"menclose": 99,
|
162 |
-
"merror": 100,
|
163 |
-
"mfenced": 101,
|
164 |
-
"mfrac": 102,
|
165 |
-
"mglyph": 103,
|
166 |
-
"mi": 104,
|
167 |
-
"mi\"": 105,
|
168 |
-
"min": 106,
|
169 |
-
"minus": 107,
|
170 |
-
"mlabeledtr": 108,
|
171 |
-
"mlongdiv": 109,
|
172 |
-
"mmultiscripts": 110,
|
173 |
-
"mn": 111,
|
174 |
-
"mo": 112,
|
175 |
-
"mode": 113,
|
176 |
-
"moment": 114,
|
177 |
-
"momentabout": 115,
|
178 |
-
"mover": 116,
|
179 |
-
"mpadded": 117,
|
180 |
-
"mphantom": 118,
|
181 |
-
"mprescripts": 119,
|
182 |
-
"mroot": 120,
|
183 |
-
"mrow": 121,
|
184 |
-
"ms": 122,
|
185 |
-
"mscarries": 123,
|
186 |
-
"mscarry": 124,
|
187 |
-
"msgroup": 125,
|
188 |
-
"msline": 126,
|
189 |
-
"mspace": 127,
|
190 |
-
"msqrt": 128,
|
191 |
-
"msrow": 129,
|
192 |
-
"mstack": 130,
|
193 |
-
"mstyle": 131,
|
194 |
-
"msub": 132,
|
195 |
-
"msubsup": 133,
|
196 |
-
"msup": 134,
|
197 |
-
"mtable": 135,
|
198 |
-
"mtd": 136,
|
199 |
-
"mtext": 137,
|
200 |
-
"mtr": 138,
|
201 |
-
"munder": 139,
|
202 |
-
"munderover": 140,
|
203 |
-
"naturalnumbers": 141,
|
204 |
-
"neq": 142,
|
205 |
-
"none": 143,
|
206 |
-
"not": 144,
|
207 |
-
"notanumber": 145,
|
208 |
-
"notin": 146,
|
209 |
-
"notprsubset": 147,
|
210 |
-
"notsubset": 148,
|
211 |
-
"or": 149,
|
212 |
-
"otherwise": 150,
|
213 |
-
"outerproduct": 151,
|
214 |
-
"partialdiff": 152,
|
215 |
-
"pi": 153,
|
216 |
-
"piece": 154,
|
217 |
-
"piecewise": 155,
|
218 |
-
"plus": 156,
|
219 |
-
"power": 157,
|
220 |
-
"primes": 158,
|
221 |
-
"product": 159,
|
222 |
-
"prsubset": 160,
|
223 |
-
"quotient": 161,
|
224 |
-
"rationals": 162,
|
225 |
-
"real": 163,
|
226 |
-
"reals": 164,
|
227 |
-
"reln": 165,
|
228 |
-
"rem": 166,
|
229 |
-
"root": 167,
|
230 |
-
"scalarproduct": 168,
|
231 |
-
"sdev": 169,
|
232 |
-
"sec": 170,
|
233 |
-
"sech": 171,
|
234 |
-
"selector": 172,
|
235 |
-
"semantics": 173,
|
236 |
-
"sep": 174,
|
237 |
-
"set": 175,
|
238 |
-
"setdiff": 176,
|
239 |
-
"share": 177,
|
240 |
-
"sin": 178,
|
241 |
-
"sinh": 179,
|
242 |
-
"span": 180,
|
243 |
-
"subset": 181,
|
244 |
-
"sum": 182,
|
245 |
-
"tan": 183,
|
246 |
-
"tanh": 184,
|
247 |
-
"tendsto": 185,
|
248 |
-
"times": 186,
|
249 |
-
"transpose": 187,
|
250 |
-
"true": 188,
|
251 |
-
"union": 189,
|
252 |
-
"uplimit": 190,
|
253 |
-
"variance": 191,
|
254 |
-
"vector": 192,
|
255 |
-
"vectorproduct": 193,
|
256 |
-
"xor": 194
|
257 |
-
},
|
258 |
-
"tokenizer_class": "MarkupLMTokenizer",
|
259 |
-
"trim_offsets": false,
|
260 |
-
"unk_token": {
|
261 |
-
"__type": "AddedToken",
|
262 |
-
"content": "<unk>",
|
263 |
-
"lstrip": false,
|
264 |
-
"normalized": true,
|
265 |
-
"rstrip": false,
|
266 |
-
"single_word": false
|
267 |
-
}
|
268 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
training_ConMATH_ConMATH-2023-03-29_18-47-43/0_Asym/140000857040976_MarkuplmTransformerForConMATH/vocab.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|
training_ConMATH_ConMATH-2023-03-29_18-47-43/0_Asym/140000860578048_Transformer/config.json
DELETED
@@ -1,24 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"_name_or_path": "sentence-transformers/all-mpnet-base-v2",
|
3 |
-
"architectures": [
|
4 |
-
"MPNetModel"
|
5 |
-
],
|
6 |
-
"attention_probs_dropout_prob": 0.1,
|
7 |
-
"bos_token_id": 0,
|
8 |
-
"eos_token_id": 2,
|
9 |
-
"hidden_act": "gelu",
|
10 |
-
"hidden_dropout_prob": 0.1,
|
11 |
-
"hidden_size": 768,
|
12 |
-
"initializer_range": 0.02,
|
13 |
-
"intermediate_size": 3072,
|
14 |
-
"layer_norm_eps": 1e-05,
|
15 |
-
"max_position_embeddings": 514,
|
16 |
-
"model_type": "mpnet",
|
17 |
-
"num_attention_heads": 12,
|
18 |
-
"num_hidden_layers": 12,
|
19 |
-
"pad_token_id": 1,
|
20 |
-
"relative_attention_num_buckets": 32,
|
21 |
-
"torch_dtype": "float32",
|
22 |
-
"transformers_version": "4.26.1",
|
23 |
-
"vocab_size": 30527
|
24 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
training_ConMATH_ConMATH-2023-03-29_18-47-43/0_Asym/140000860578048_Transformer/pytorch_model.bin
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:15d7a9813b0a24c11d46812f8bda297891490b64c6e7f47c228bc8dee06079f2
|
3 |
-
size 438014769
|
|
|
|
|
|
|
|
training_ConMATH_ConMATH-2023-03-29_18-47-43/0_Asym/140000860578048_Transformer/sentence_bert_config.json
DELETED
@@ -1,4 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"max_seq_length": 512,
|
3 |
-
"do_lower_case": false
|
4 |
-
}
|
|
|
|
|
|
|
|
|
|
training_ConMATH_ConMATH-2023-03-29_18-47-43/0_Asym/140000860578048_Transformer/special_tokens_map.json
DELETED
@@ -1,15 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"bos_token": "<s>",
|
3 |
-
"cls_token": "<s>",
|
4 |
-
"eos_token": "</s>",
|
5 |
-
"mask_token": {
|
6 |
-
"content": "<mask>",
|
7 |
-
"lstrip": true,
|
8 |
-
"normalized": false,
|
9 |
-
"rstrip": false,
|
10 |
-
"single_word": false
|
11 |
-
},
|
12 |
-
"pad_token": "<pad>",
|
13 |
-
"sep_token": "</s>",
|
14 |
-
"unk_token": "[UNK]"
|
15 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
training_ConMATH_ConMATH-2023-03-29_18-47-43/0_Asym/140000860578048_Transformer/tokenizer.json
DELETED
The diff for this file is too large to render.
See raw diff
|
|
training_ConMATH_ConMATH-2023-03-29_18-47-43/0_Asym/140000860578048_Transformer/tokenizer_config.json
DELETED
@@ -1,16 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"bos_token": "<s>",
|
3 |
-
"cls_token": "<s>",
|
4 |
-
"do_lower_case": true,
|
5 |
-
"eos_token": "</s>",
|
6 |
-
"mask_token": "<mask>",
|
7 |
-
"model_max_length": 512,
|
8 |
-
"name_or_path": "sentence-transformers/all-mpnet-base-v2",
|
9 |
-
"pad_token": "<pad>",
|
10 |
-
"sep_token": "</s>",
|
11 |
-
"special_tokens_map_file": null,
|
12 |
-
"strip_accents": null,
|
13 |
-
"tokenize_chinese_chars": true,
|
14 |
-
"tokenizer_class": "MPNetTokenizer",
|
15 |
-
"unk_token": "[UNK]"
|
16 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
training_ConMATH_ConMATH-2023-03-29_18-47-43/0_Asym/140000860578048_Transformer/vocab.txt
DELETED
The diff for this file is too large to render.
See raw diff
|
|
training_ConMATH_ConMATH-2023-03-29_18-47-43/0_Asym/config.json
DELETED
@@ -1,17 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"types": {
|
3 |
-
"140000860578048_Transformer": "sentence_transformers.models.Transformer",
|
4 |
-
"140000857040976_MarkuplmTransformerForConMATH": "sentence_transformers.models.MarkuplmTransformerForConMATH"
|
5 |
-
},
|
6 |
-
"structure": {
|
7 |
-
"latex": [
|
8 |
-
"140000860578048_Transformer"
|
9 |
-
],
|
10 |
-
"mathml": [
|
11 |
-
"140000857040976_MarkuplmTransformerForConMATH"
|
12 |
-
]
|
13 |
-
},
|
14 |
-
"parameters": {
|
15 |
-
"allow_empty_key": true
|
16 |
-
}
|
17 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
training_ConMATH_ConMATH-2023-03-29_18-47-43/1_Pooling/config.json
DELETED
@@ -1,9 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"word_embedding_dimension": 768,
|
3 |
-
"pooling_mode_cls_token": false,
|
4 |
-
"pooling_mode_mean_tokens": true,
|
5 |
-
"pooling_mode_max_tokens": false,
|
6 |
-
"pooling_mode_mean_sqrt_len_tokens": false,
|
7 |
-
"pooling_mode_weightedmean_tokens": false,
|
8 |
-
"pooling_mode_lasttoken": false
|
9 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
training_ConMATH_ConMATH-2023-03-29_18-47-43/README.md
DELETED
@@ -1,93 +0,0 @@
|
|
1 |
-
---
|
2 |
-
pipeline_tag: sentence-similarity
|
3 |
-
tags:
|
4 |
-
- sentence-transformers
|
5 |
-
- feature-extraction
|
6 |
-
- sentence-similarity
|
7 |
-
|
8 |
-
---
|
9 |
-
|
10 |
-
# {MODEL_NAME}
|
11 |
-
|
12 |
-
This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
|
13 |
-
|
14 |
-
<!--- Describe your model here -->
|
15 |
-
|
16 |
-
## Usage (Sentence-Transformers)
|
17 |
-
|
18 |
-
Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
|
19 |
-
|
20 |
-
```
|
21 |
-
pip install -U sentence-transformers
|
22 |
-
```
|
23 |
-
|
24 |
-
Then you can use the model like this:
|
25 |
-
|
26 |
-
```python
|
27 |
-
from sentence_transformers import SentenceTransformer
|
28 |
-
sentences = ["This is an example sentence", "Each sentence is converted"]
|
29 |
-
|
30 |
-
model = SentenceTransformer('{MODEL_NAME}')
|
31 |
-
embeddings = model.encode(sentences)
|
32 |
-
print(embeddings)
|
33 |
-
```
|
34 |
-
|
35 |
-
|
36 |
-
|
37 |
-
## Evaluation Results
|
38 |
-
|
39 |
-
<!--- Describe how your model was evaluated -->
|
40 |
-
|
41 |
-
For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
|
42 |
-
|
43 |
-
|
44 |
-
## Training
|
45 |
-
The model was trained with the parameters:
|
46 |
-
|
47 |
-
**DataLoader**:
|
48 |
-
|
49 |
-
`torch.utils.data.dataloader.DataLoader` of length 45861 with parameters:
|
50 |
-
```
|
51 |
-
{'batch_size': 4, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
|
52 |
-
```
|
53 |
-
|
54 |
-
**Loss**:
|
55 |
-
|
56 |
-
`sentence_transformers.losses.MultipleNegativesSymmetricRankingLoss.MultipleNegativesSymmetricRankingLoss` with parameters:
|
57 |
-
```
|
58 |
-
{'scale': 20.0, 'similarity_fct': 'cos_sim'}
|
59 |
-
```
|
60 |
-
|
61 |
-
Parameters of the fit()-Method:
|
62 |
-
```
|
63 |
-
{
|
64 |
-
"epochs": 1,
|
65 |
-
"evaluation_steps": 4586,
|
66 |
-
"evaluator": "sentence_transformers.evaluation.AlignmentandUniformityEvaluator.AlignmentandUniformityEvaluator",
|
67 |
-
"max_grad_norm": 1,
|
68 |
-
"optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
|
69 |
-
"optimizer_params": {
|
70 |
-
"lr": 5e-05
|
71 |
-
},
|
72 |
-
"scheduler": "WarmupLinear",
|
73 |
-
"steps_per_epoch": null,
|
74 |
-
"warmup_steps": 4587,
|
75 |
-
"weight_decay": 0.01
|
76 |
-
}
|
77 |
-
```
|
78 |
-
|
79 |
-
|
80 |
-
## Full Model Architecture
|
81 |
-
```
|
82 |
-
SentenceTransformer(
|
83 |
-
(0): Asym(
|
84 |
-
(latex-0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: MPNetModel
|
85 |
-
(mathml-0): MarkuplmTransformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: MarkupLMModel
|
86 |
-
)
|
87 |
-
(1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False})
|
88 |
-
)
|
89 |
-
```
|
90 |
-
|
91 |
-
## Citing & Authors
|
92 |
-
|
93 |
-
<!--- Describe where people can find more information -->
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
training_ConMATH_ConMATH-2023-03-29_18-47-43/config_sentence_transformers.json
DELETED
@@ -1,7 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"__version__": {
|
3 |
-
"sentence_transformers": "2.2.2",
|
4 |
-
"transformers": "4.26.1",
|
5 |
-
"pytorch": "1.12.1+cu113"
|
6 |
-
}
|
7 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
training_ConMATH_ConMATH-2023-03-29_18-47-43/modules.json
DELETED
@@ -1,14 +0,0 @@
|
|
1 |
-
[
|
2 |
-
{
|
3 |
-
"idx": 0,
|
4 |
-
"name": "0",
|
5 |
-
"path": "0_Asym",
|
6 |
-
"type": "sentence_transformers.models.Asym"
|
7 |
-
},
|
8 |
-
{
|
9 |
-
"idx": 1,
|
10 |
-
"name": "1",
|
11 |
-
"path": "1_Pooling",
|
12 |
-
"type": "sentence_transformers.models.Pooling"
|
13 |
-
}
|
14 |
-
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|