bert-large-uncased-whole-word-masking-finetuned-squad, roberta-base-discourse-marker-prediction, xlm-roberta-base

BERT/bert-large-uncased-whole-word-masking-finetuned-squad/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d25f8217b8877a253a602a22b94b6e5fff7a3bcbc8ee61fe91b368d0fc8a0ce4
+size 1340995544

BERT/bert-large-uncased-whole-word-masking-finetuned-squad/model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e2349f21ec01f7c90729cd54452e28d1a3aa7f2d7f8dfd91b437fb4fef022da
+size 670783496

BERT/bert-large-uncased-whole-word-masking-finetuned-squad/model_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe79991f4bf5aa1dd07ca36edf6deb4fc86a09dac9682f0a751943d78d7bfa4d
+size 336791930

BERT/bert-large-uncased-whole-word-masking-finetuned-squad/model_opt.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4747d76b753d28e50bfee5d96de9fd7408fcf7e0340a96bffa9a260a90c06d2
+size 1340944121

BERT/bert-large-uncased-whole-word-masking-finetuned-squad/model_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0723656cd81b24345b08ad041a71c096445df62893e80c7a147dba1cb5f62e39
+size 336792017

RoBERTa/roberta-base-discourse-marker-prediction/.gitattributes

@@ -0,0 +1,28 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+model.safetensors filter=lfs diff=lfs merge=lfs -text

RoBERTa/roberta-base-discourse-marker-prediction/README.md

@@ -0,0 +1,49 @@
+---
+language:
+- en
+tags:
+- discourse-marker-prediction
+- discourse-connective-prediction
+- discourse-connective
+- discourse-marker
+- discourse-relation-prediction
+- pragmatics
+- discourse
+license: apache-2.0
+datasets:
+- discovery
+metrics:
+- accuracy
+widget:
+- text: "But no, Amazon selling 3D printers is not new.</s></s>The promise of 3D printing is very great."
+---
+
+# Discourse marker prediction / discourse connective prediction pretrained model
+
+`roberta-base` pretrained on discourse marker prediction on the Discovery dataset with a validation accuracy of 30.93% (majority class is 0.57%)
+
+https://github.com/sileod/discovery
+
+https://huggingface.co/datasets/discovery
+
+This model can also be used as a pretrained model for NLU, pragmatics and discourse tasks
+
+## Citing & Authors
+
+```bibtex 
+@inproceedings{sileo-etal-2019-mining,
+    title = "Mining Discourse Markers for Unsupervised Sentence Representation Learning",
+    author = "Sileo, Damien  and
+      Van De Cruys, Tim  and
+      Pradel, Camille  and
+      Muller, Philippe",
+    booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
+    month = jun,
+    year = "2019",
+    address = "Minneapolis, Minnesota",
+    publisher = "Association for Computational Linguistics",
+    url = "https://aclanthology.org/N19-1351",
+    doi = "10.18653/v1/N19-1351",
+    pages = "3477--3486",
+}
+```

RoBERTa/roberta-base-discourse-marker-prediction/config.json

@@ -0,0 +1,380 @@
+{
+  "_name_or_path": "roberta-base-discourse-marker-prediction/",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "[no-conn]",
+    "1": "absolutely,",
+    "10": "alternately,",
+    "100": "notably,",
+    "101": "now,",
+    "102": "obviously,",
+    "103": "occasionally,",
+    "104": "oddly,",
+    "105": "often,",
+    "106": "on_the_contrary,",
+    "107": "on_the_other_hand",
+    "108": "once,",
+    "109": "only,",
+    "11": "alternatively",
+    "110": "optionally,",
+    "111": "or,",
+    "112": "originally,",
+    "113": "otherwise,",
+    "114": "overall,",
+    "115": "particularly,",
+    "116": "perhaps,",
+    "117": "personally,",
+    "118": "plus,",
+    "119": "preferably,",
+    "12": "although,",
+    "120": "presently,",
+    "121": "presumably,",
+    "122": "previously,",
+    "123": "probably,",
+    "124": "rather,",
+    "125": "realistically,",
+    "126": "really,",
+    "127": "recently,",
+    "128": "regardless,",
+    "129": "remarkably,",
+    "13": "altogether,",
+    "130": "sadly,",
+    "131": "second,",
+    "132": "secondly,",
+    "133": "separately,",
+    "134": "seriously,",
+    "135": "significantly,",
+    "136": "similarly,",
+    "137": "simultaneously",
+    "138": "slowly,",
+    "139": "so,",
+    "14": "amazingly,",
+    "140": "sometimes,",
+    "141": "soon,",
+    "142": "specifically,",
+    "143": "still,",
+    "144": "strangely,",
+    "145": "subsequently,",
+    "146": "suddenly,",
+    "147": "supposedly,",
+    "148": "surely,",
+    "149": "surprisingly,",
+    "15": "and",
+    "150": "technically,",
+    "151": "thankfully,",
+    "152": "then,",
+    "153": "theoretically,",
+    "154": "thereafter,",
+    "155": "thereby,",
+    "156": "therefore",
+    "157": "third,",
+    "158": "thirdly,",
+    "159": "this,",
+    "16": "anyway,",
+    "160": "though,",
+    "161": "thus,",
+    "162": "together,",
+    "163": "traditionally,",
+    "164": "truly,",
+    "165": "truthfully,",
+    "166": "typically,",
+    "167": "ultimately,",
+    "168": "undoubtedly,",
+    "169": "unfortunately,",
+    "17": "apparently,",
+    "170": "unsurprisingly,",
+    "171": "usually,",
+    "172": "well,",
+    "173": "yet,",
+    "18": "arguably,",
+    "19": "as_a_result,",
+    "2": "accordingly",
+    "20": "basically,",
+    "21": "because_of_that",
+    "22": "because_of_this",
+    "23": "besides,",
+    "24": "but",
+    "25": "by_comparison,",
+    "26": "by_contrast,",
+    "27": "by_doing_this,",
+    "28": "by_then",
+    "29": "certainly,",
+    "3": "actually,",
+    "30": "clearly,",
+    "31": "coincidentally,",
+    "32": "collectively,",
+    "33": "consequently",
+    "34": "conversely",
+    "35": "curiously,",
+    "36": "currently,",
+    "37": "elsewhere,",
+    "38": "especially,",
+    "39": "essentially,",
+    "4": "additionally",
+    "40": "eventually,",
+    "41": "evidently,",
+    "42": "finally,",
+    "43": "first,",
+    "44": "firstly,",
+    "45": "for_example",
+    "46": "for_instance",
+    "47": "fortunately,",
+    "48": "frankly,",
+    "49": "frequently,",
+    "5": "admittedly,",
+    "50": "further,",
+    "51": "furthermore",
+    "52": "generally,",
+    "53": "gradually,",
+    "54": "happily,",
+    "55": "hence,",
+    "56": "here,",
+    "57": "historically,",
+    "58": "honestly,",
+    "59": "hopefully,",
+    "6": "afterward",
+    "60": "however",
+    "61": "ideally,",
+    "62": "immediately,",
+    "63": "importantly,",
+    "64": "in_contrast,",
+    "65": "in_fact,",
+    "66": "in_other_words",
+    "67": "in_particular,",
+    "68": "in_short,",
+    "69": "in_sum,",
+    "7": "again,",
+    "70": "in_the_end,",
+    "71": "in_the_meantime,",
+    "72": "in_turn,",
+    "73": "incidentally,",
+    "74": "increasingly,",
+    "75": "indeed,",
+    "76": "inevitably,",
+    "77": "initially,",
+    "78": "instead,",
+    "79": "interestingly,",
+    "8": "already,",
+    "80": "ironically,",
+    "81": "lastly,",
+    "82": "lately,",
+    "83": "later,",
+    "84": "likewise,",
+    "85": "locally,",
+    "86": "luckily,",
+    "87": "maybe,",
+    "88": "meaning,",
+    "89": "meantime,",
+    "9": "also,",
+    "90": "meanwhile,",
+    "91": "moreover",
+    "92": "mostly,",
+    "93": "namely,",
+    "94": "nationally,",
+    "95": "naturally,",
+    "96": "nevertheless",
+    "97": "next,",
+    "98": "nonetheless",
+    "99": "normally,"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "[no-conn]": 0,
+    "absolutely,": 1,
+    "accordingly": 2,
+    "actually,": 3,
+    "additionally": 4,
+    "admittedly,": 5,
+    "afterward": 6,
+    "again,": 7,
+    "already,": 8,
+    "also,": 9,
+    "alternately,": 10,
+    "alternatively": 11,
+    "although,": 12,
+    "altogether,": 13,
+    "amazingly,": 14,
+    "and": 15,
+    "anyway,": 16,
+    "apparently,": 17,
+    "arguably,": 18,
+    "as_a_result,": 19,
+    "basically,": 20,
+    "because_of_that": 21,
+    "because_of_this": 22,
+    "besides,": 23,
+    "but": 24,
+    "by_comparison,": 25,
+    "by_contrast,": 26,
+    "by_doing_this,": 27,
+    "by_then": 28,
+    "certainly,": 29,
+    "clearly,": 30,
+    "coincidentally,": 31,
+    "collectively,": 32,
+    "consequently": 33,
+    "conversely": 34,
+    "curiously,": 35,
+    "currently,": 36,
+    "elsewhere,": 37,
+    "especially,": 38,
+    "essentially,": 39,
+    "eventually,": 40,
+    "evidently,": 41,
+    "finally,": 42,
+    "first,": 43,
+    "firstly,": 44,
+    "for_example": 45,
+    "for_instance": 46,
+    "fortunately,": 47,
+    "frankly,": 48,
+    "frequently,": 49,
+    "further,": 50,
+    "furthermore": 51,
+    "generally,": 52,
+    "gradually,": 53,
+    "happily,": 54,
+    "hence,": 55,
+    "here,": 56,
+    "historically,": 57,
+    "honestly,": 58,
+    "hopefully,": 59,
+    "however": 60,
+    "ideally,": 61,
+    "immediately,": 62,
+    "importantly,": 63,
+    "in_contrast,": 64,
+    "in_fact,": 65,
+    "in_other_words": 66,
+    "in_particular,": 67,
+    "in_short,": 68,
+    "in_sum,": 69,
+    "in_the_end,": 70,
+    "in_the_meantime,": 71,
+    "in_turn,": 72,
+    "incidentally,": 73,
+    "increasingly,": 74,
+    "indeed,": 75,
+    "inevitably,": 76,
+    "initially,": 77,
+    "instead,": 78,
+    "interestingly,": 79,
+    "ironically,": 80,
+    "lastly,": 81,
+    "lately,": 82,
+    "later,": 83,
+    "likewise,": 84,
+    "locally,": 85,
+    "luckily,": 86,
+    "maybe,": 87,
+    "meaning,": 88,
+    "meantime,": 89,
+    "meanwhile,": 90,
+    "moreover": 91,
+    "mostly,": 92,
+    "namely,": 93,
+    "nationally,": 94,
+    "naturally,": 95,
+    "nevertheless": 96,
+    "next,": 97,
+    "nonetheless": 98,
+    "normally,": 99,
+    "notably,": 100,
+    "now,": 101,
+    "obviously,": 102,
+    "occasionally,": 103,
+    "oddly,": 104,
+    "often,": 105,
+    "on_the_contrary,": 106,
+    "on_the_other_hand": 107,
+    "once,": 108,
+    "only,": 109,
+    "optionally,": 110,
+    "or,": 111,
+    "originally,": 112,
+    "otherwise,": 113,
+    "overall,": 114,
+    "particularly,": 115,
+    "perhaps,": 116,
+    "personally,": 117,
+    "plus,": 118,
+    "preferably,": 119,
+    "presently,": 120,
+    "presumably,": 121,
+    "previously,": 122,
+    "probably,": 123,
+    "rather,": 124,
+    "realistically,": 125,
+    "really,": 126,
+    "recently,": 127,
+    "regardless,": 128,
+    "remarkably,": 129,
+    "sadly,": 130,
+    "second,": 131,
+    "secondly,": 132,
+    "separately,": 133,
+    "seriously,": 134,
+    "significantly,": 135,
+    "similarly,": 136,
+    "simultaneously": 137,
+    "slowly,": 138,
+    "so,": 139,
+    "sometimes,": 140,
+    "soon,": 141,
+    "specifically,": 142,
+    "still,": 143,
+    "strangely,": 144,
+    "subsequently,": 145,
+    "suddenly,": 146,
+    "supposedly,": 147,
+    "surely,": 148,
+    "surprisingly,": 149,
+    "technically,": 150,
+    "thankfully,": 151,
+    "then,": 152,
+    "theoretically,": 153,
+    "thereafter,": 154,
+    "thereby,": 155,
+    "therefore": 156,
+    "third,": 157,
+    "thirdly,": 158,
+    "this,": 159,
+    "though,": 160,
+    "thus,": 161,
+    "together,": 162,
+    "traditionally,": 163,
+    "truly,": 164,
+    "truthfully,": 165,
+    "typically,": 166,
+    "ultimately,": 167,
+    "undoubtedly,": 168,
+    "unfortunately,": 169,
+    "unsurprisingly,": 170,
+    "usually,": 171,
+    "well,": 172,
+    "yet,": 173
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

RoBERTa/roberta-base-discourse-marker-prediction/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b028bf3cf656959677292b56aa99f74479f6b88d15857e27f0c1fec21c12fe48
+size 499146104

RoBERTa/roberta-base-discourse-marker-prediction/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57cc527274cdcfaf49f1366594eb30512c45ecaf2a3a5b800eb82676868408ba
+size 499201261

RoBERTa/roberta-base-discourse-marker-prediction/special_tokens_map.json

@@ -0,0 +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}}

RoBERTa/roberta-base-discourse-marker-prediction/tokenizer_config.json

@@ -0,0 +1 @@
+{"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-base", "tokenizer_class": "RobertaTokenizer"}

XLM-RoBERTa/xlm-roberta-base/config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "XLMRobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.17.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

XLM-RoBERTa/xlm-roberta-base/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a76bfe6a405f1a9ace42b2dbd8fbd284dd8127a732ddcf2145b0fc9413b30d40
+size 1881470773

XLM-RoBERTa/xlm-roberta-base/tokenizer_config.json

@@ -0,0 +1 @@
+{"model_max_length": 512}