{
  "_name_or_path": "/mnt/bingadseuunifiedstorage/v-liziheng/result/xtreme-rlm-t2-target-enlm-fwd-ams0-xlm-roberta-base.2",
  "architectures": [
    "RobertaForRLM"
  ],
  "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,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "langs": [
    "af",
    "ar",
    "bg",
    "bn",
    "de",
    "el",
    "es",
    "et",
    "eu",
    "fa",
    "fi",
    "fr",
    "he",
    "hi",
    "hu",
    "id",
    "it",
    "ja",
    "jv",
    "ka",
    "kk",
    "ko",
    "ml",
    "mr",
    "nl",
    "pt",
    "ru",
    "sw",
    "ta",
    "te",
    "th",
    "tl",
    "tr",
    "ur",
    "vi",
    "zh"
  ],
  "layer_norm_eps": 1e-05,
  "max_position_embeddings": 514,
  "model_type": "roberta",
  "n_langs": 38,
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "output_past": true,
  "pad_token_id": 1,
  "position_embedding_type": "absolute",
  "torch_dtype": "float32",
  "transformers_version": "4.18.0",
  "type_vocab_size": 1,
  "use_cache": true,
  "use_lang_emb": false,
  "vocab_size": 250002
}