anli/src/nli/train_with_confidence.py [64:148]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
MODEL_CLASSES = {
    "bert-base": {
        "model_name": "bert-base-uncased",
        "tokenizer": BertTokenizer,
        "sequence_classification": BertForSequenceClassification,
        # "padding_token_value": 0,
        "padding_segement_value": 0,
        "padding_att_value": 0,
        "do_lower_case": True,
    },
    "bert-large": {
        "model_name": "bert-large-uncased",
        "tokenizer": BertTokenizer,
        "sequence_classification": BertForSequenceClassification,
        # "padding_token_value": 0,
        "padding_segement_value": 0,
        "padding_att_value": 0,
        "do_lower_case": True,
    },
    "xlnet-base": {
        "model_name": "xlnet-base-cased",
        "tokenizer": XLNetTokenizer,
        "sequence_classification": XLNetForSequenceClassification,
        # "padding_token_value": 0,
        "padding_segement_value": 4,
        "padding_att_value": 0,
        "left_pad": True,
    },
    "xlnet-large": {
        "model_name": "xlnet-large-cased",
        "tokenizer": XLNetTokenizer,
        "sequence_classification": XLNetForSequenceClassification,
        "padding_segement_value": 4,
        "padding_att_value": 0,
        "left_pad": True,
    },
    "roberta-base": {
        "model_name": "roberta-base",
        "tokenizer": RobertaTokenizer,
        "sequence_classification": RobertaForSequenceClassification,
        "padding_segement_value": 0,
        "padding_att_value": 0,
    },
    "roberta-large": {
        "model_name": "roberta-large",
        "tokenizer": RobertaTokenizer,
        "sequence_classification": RobertaForSequenceClassification,
        "padding_segement_value": 0,
        "padding_att_value": 0,
    },
    "albert-xxlarge": {
        "model_name": "albert-xxlarge-v2",
        "tokenizer": AlbertTokenizer,
        "sequence_classification": AlbertForSequenceClassification,
        "padding_segement_value": 0,
        "padding_att_value": 0,
    },
    "distilbert": {
        "model_name": "distilbert-base-cased",
        "tokenizer": DistilBertTokenizer,
        "sequence_classification": DistilBertForSequenceClassification,
        "padding_segement_value": 0,
        "padding_att_value": 0,
    },
    "bart-large": {
        "model_name": "facebook/bart-large",
        "tokenizer": BartTokenizer,
        "sequence_classification": BartForSequenceClassification,
        "padding_segement_value": 0,
        "padding_att_value": 0,
    },
    "electra-base": {
        "model_name": "google/electra-base-discriminator",
        "tokenizer": ElectraTokenizer,
        "sequence_classification": ElectraForSequenceClassification,
        "padding_segement_value": 0,
        "padding_att_value": 0,
    },
    "electra-large": {
        "model_name": "google/electra-large-discriminator",
        "tokenizer": ElectraTokenizer,
        "sequence_classification": ElectraForSequenceClassification,
        "padding_segement_value": 0,
        "padding_att_value": 0,
    },
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



anli/src/nli/train_with_scramble.py [57:141]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
MODEL_CLASSES = {
    "bert-base": {
        "model_name": "bert-base-uncased",
        "tokenizer": BertTokenizer,
        "sequence_classification": BertForSequenceClassification,
        # "padding_token_value": 0,
        "padding_segement_value": 0,
        "padding_att_value": 0,
        "do_lower_case": True,
    },
    "bert-large": {
        "model_name": "bert-large-uncased",
        "tokenizer": BertTokenizer,
        "sequence_classification": BertForSequenceClassification,
        # "padding_token_value": 0,
        "padding_segement_value": 0,
        "padding_att_value": 0,
        "do_lower_case": True,
    },
    "xlnet-base": {
        "model_name": "xlnet-base-cased",
        "tokenizer": XLNetTokenizer,
        "sequence_classification": XLNetForSequenceClassification,
        # "padding_token_value": 0,
        "padding_segement_value": 4,
        "padding_att_value": 0,
        "left_pad": True,
    },
    "xlnet-large": {
        "model_name": "xlnet-large-cased",
        "tokenizer": XLNetTokenizer,
        "sequence_classification": XLNetForSequenceClassification,
        "padding_segement_value": 4,
        "padding_att_value": 0,
        "left_pad": True,
    },
    "roberta-base": {
        "model_name": "roberta-base",
        "tokenizer": RobertaTokenizer,
        "sequence_classification": RobertaForSequenceClassification,
        "padding_segement_value": 0,
        "padding_att_value": 0,
    },
    "roberta-large": {
        "model_name": "roberta-large",
        "tokenizer": RobertaTokenizer,
        "sequence_classification": RobertaForSequenceClassification,
        "padding_segement_value": 0,
        "padding_att_value": 0,
    },
    "albert-xxlarge": {
        "model_name": "albert-xxlarge-v2",
        "tokenizer": AlbertTokenizer,
        "sequence_classification": AlbertForSequenceClassification,
        "padding_segement_value": 0,
        "padding_att_value": 0,
    },
    "distilbert": {
        "model_name": "distilbert-base-cased",
        "tokenizer": DistilBertTokenizer,
        "sequence_classification": DistilBertForSequenceClassification,
        "padding_segement_value": 0,
        "padding_att_value": 0,
    },
    "bart-large": {
        "model_name": "facebook/bart-large",
        "tokenizer": BartTokenizer,
        "sequence_classification": BartForSequenceClassification,
        "padding_segement_value": 0,
        "padding_att_value": 0,
    },
    "electra-base": {
        "model_name": "google/electra-base-discriminator",
        "tokenizer": ElectraTokenizer,
        "sequence_classification": ElectraForSequenceClassification,
        "padding_segement_value": 0,
        "padding_att_value": 0,
    },
    "electra-large": {
        "model_name": "google/electra-large-discriminator",
        "tokenizer": ElectraTokenizer,
        "sequence_classification": ElectraForSequenceClassification,
        "padding_segement_value": 0,
        "padding_att_value": 0,
    },
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -