config.json

{
  "architectures": [
    "EsmForSequenceClassification"
  ],
  "attention_probs_dropout_prob": 0.0,
  "classifier_dropout": null,
  "emb_layer_norm_before": false,
  "esmfold_config": null,
  "head_activation": "relu",
  "head_dropout_prob": 0.2,
  "head_num_hidden_layers": 2,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.0,
  "hidden_size": 1280,
  "id2label": {
    "0": "A",
    "1": "C",
    "2": "G",
    "3": "T"
  },
  "initializer_range": 0.02,
  "intermediate_size": 5120,
  "is_folding_model": false,
  "label2id": {
    "A": 0,
    "C": 1,
    "G": 2,
    "T": 3
  },
  "layer_norm_eps": 1e-05,
  "mask_token_id": 32,
  "max_position_embeddings": 1026,
  "model_type": "esm",
  "num_attention_heads": 20,
  "num_hidden_layers": 33,
  "output_shape": [
    10,
    4
  ],
  "pad_token_id": 1,
  "position_embedding_type": "rotary",
  "problem_type": "single_label_classification",
  "token_dropout": true,
  "torch_dtype": "float32",
  "transformers_version": "4.46.3",
  "use_cache": true,
  "use_flash_attn": null,
  "vocab_list": null,
  "vocab_size": 33
}