config.json

{
  "_name_or_path": "/tmp/mmarco-mMiniLMv2-L12-H384-v1-stripped",
  "architectures": [
    "XLMRobertaForSequenceClassification"
  ],
  "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": 384,
  "id2label": {
    "0": "LABEL_0"
  },
  "initializer_range": 0.02,
  "intermediate_size": 1536,
  "label2id": {
    "LABEL_0": 0
  },
  "layer_norm_eps": 1e-05,
  "max_position_embeddings": 514,
  "model_type": "xlm-roberta",
  "num_attention_heads": 12,
  "num_hidden_layers": 4,
  "pad_token_id": 1,
  "position_embedding_type": "absolute",
  "pruned_heads": {
    "0": [
      2,
      4,
      5,
      6,
      8,
      9,
      10,
      11
    ],
    "1": [
      2,
      3,
      5,
      6,
      7,
      8,
      10,
      11
    ],
    "2": [
      0,
      2,
      3,
      4,
      5,
      7,
      8,
      9
    ],
    "3": [
      0,
      2,
      3,
      4,
      5,
      7,
      8,
      10
    ]
  },
  "sbert_ce_default_activation_function": "torch.nn.modules.linear.Identity",
  "torch_dtype": "float32",
  "transformers_version": "4.20.1",
  "type_vocab_size": 1,
  "use_cache": true,
  "vocab_size": 250002
}