config.json

{
  "_name_or_path": "tasksource/ModernBERT-base-nli",
  "architectures": [
    "ModernBertModel"
  ],
  "attention_bias": false,
  "attention_dropout": 0.0,
  "bos_token_id": 50281,
  "classifier_activation": "gelu",
  "classifier_bias": false,
  "classifier_dropout": 0.0,
  "classifier_pooling": "mean",
  "classifiers_size": [
    3,
    2,
    2,
    2,
    2,
    3,
    3,
    3,
    3,
    3,
    3,
    3,
    2,
    2,
    3,
    2,
    2,
    2,
    2,
    2,
    6,
    2,
    2,
    2,
    2,
    2,
    3,
    3,
    3,
    3,
    3,
    3,
    3,
    2,
    2,
    2,
    2,
    3,
    3,
    3,
    3,
    3,
    3,
    3,
    3,
    2,
    2,
    2,
    2,
    3,
    2,
    4,
    3,
    3,
    2,
    2,
    2,
    2,
    2,
    3,
    2,
    3,
    2,
    4,
    3,
    3,
    3,
    2,
    3,
    1,
    2,
    2,
    3,
    13,
    2,
    3,
    2,
    2,
    3,
    3,
    2,
    3,
    3,
    2,
    3,
    2,
    2,
    2,
    2,
    2,
    3,
    4,
    3,
    3,
    2,
    2,
    3,
    3,
    2,
    2,
    2,
    2,
    2,
    4,
    3,
    2,
    2,
    3
  ],
  "cls_token_id": 50281,
  "decoder_bias": true,
  "deterministic_flash_attn": false,
  "embedding_dropout": 0.0,
  "eos_token_id": 50282,
  "global_attn_every_n_layers": 3,
  "global_rope_theta": 160000.0,
  "gradient_checkpointing": false,
  "hidden_activation": "gelu",
  "hidden_size": 768,
  "id2label": {
    "0": "entailment",
    "1": "neutral",
    "2": "contradiction"
  },
  "initializer_cutoff_factor": 2.0,
  "initializer_range": 0.02,
  "intermediate_size": 1152,
  "label2id": {
    "contradiction": 2,
    "entailment": 0,
    "neutral": 1
  },
  "layer_norm_eps": 1e-05,
  "local_attention": 128,
  "local_rope_theta": 10000.0,
  "max_position_embeddings": 2048,
  "mlp_bias": false,
  "mlp_dropout": 0.0,
  "model_type": "modernbert",
  "norm_bias": false,
  "norm_eps": 1e-05,
  "num_attention_heads": 12,
  "num_hidden_layers": 22,
  "pad_token_id": 50283,
  "position_embedding_type": "absolute",
  "problem_type": "single_label_classification",
  "reference_compile": true,
  "sep_token_id": 50282,
  "sparse_pred_ignore_index": -100,
  "sparse_prediction": false,
  "tasks": [
    "glue/mnli",
    "glue/qnli",
    "glue/rte",
    "glue/wnli",
    "super_glue/boolq",
    "super_glue/cb",
    "anli/a1",
    "anli/a2",
    "anli/a3",
    "sick/label",
    "sick/entailment_AB",
    "snli",
    "scitail/snli_format",
    "hans",
    "WANLI",
    "recast/recast_sentiment",
    "recast/recast_verbcorner",
    "recast/recast_ner",
    "recast/recast_factuality",
    "recast/recast_puns",
    "recast/recast_kg_relations",
    "recast/recast_verbnet",
    "recast/recast_megaveridicality",
    "probability_words_nli/usnli",
    "probability_words_nli/reasoning_1hop",
    "probability_words_nli/reasoning_2hop",
    "nan-nli",
    "nli_fever",
    "breaking_nli",
    "conj_nli",
    "fracas",
    "dialogue_nli",
    "mpe",
    "dnc",
    "recast_white/fnplus",
    "recast_white/sprl",
    "recast_white/dpr",
    "robust_nli/IS_CS",
    "robust_nli/LI_LI",
    "robust_nli/ST_WO",
    "robust_nli/PI_SP",
    "robust_nli/PI_CD",
    "robust_nli/ST_SE",
    "robust_nli/ST_NE",
    "robust_nli/ST_LM",
    "robust_nli_is_sd",
    "robust_nli_li_ts",
    "add_one_rte",
    "cycic_classification",
    "lingnli",
    "monotonicity-entailment",
    "scinli",
    "naturallogic",
    "syntactic-augmentation-nli",
    "autotnli",
    "defeasible-nli/atomic",
    "defeasible-nli/snli",
    "help-nli",
    "nli-veridicality-transitivity",
    "lonli",
    "dadc-limit-nli",
    "folio",
    "tomi-nli",
    "puzzte",
    "temporal-nli",
    "counterfactually-augmented-snli",
    "cnli",
    "boolq-natural-perturbations",
    "equate",
    "chaos-mnli-ambiguity",
    "logiqa-2.0-nli",
    "mindgames",
    "ConTRoL-nli",
    "logical-fallacy",
    "conceptrules_v2",
    "zero-shot-label-nli",
    "scone",
    "monli",
    "SpaceNLI",
    "propsegment/nli",
    "SDOH-NLI",
    "scifact_entailment",
    "AdjectiveScaleProbe-nli",
    "resnli",
    "semantic_fragments_nli",
    "dataset_train_nli",
    "nlgraph",
    "ruletaker",
    "PARARULE-Plus",
    "logical-entailment",
    "nope",
    "LogicNLI",
    "contract-nli/contractnli_a/seg",
    "contract-nli/contractnli_b/full",
    "nli4ct_semeval2024",
    "biosift-nli",
    "SIGA-nli",
    "FOL-nli",
    "doc-nli",
    "mctest-nli",
    "natural-language-satisfiability",
    "idioms-nli",
    "lifecycle-entailment",
    "MSciNLI",
    "hover-3way/nli",
    "seahorse_summarization_evaluation",
    "babi_nli",
    "gen_debiased_nli"
  ],
  "torch_dtype": "float32",
  "transformers_version": "4.48.0.dev0",
  "vocab_size": 50368
}