config.json

{
  "auto_map": {
    "AutoConfig": "configuration_xlm_roberta.XLMRobertaFlashConfig",
    "AutoModel": "modeling_xlm_roberta.XLMRobertaModel",
    "AutoModelForPreTraining": "modeling_xlm_roberta.XLMRobertaForPreTraining",
    "AutoModelForMaskedLM": "modeling_xlm_roberta.XLMRobertaForMaskedLM",
    "AutoModelForSequenceClassification":"modeling_xlm_roberta.XLMRobertaForSequenceClassification"
  },
  "architectures": [
    "XLMRobertaModel"
  ],
  "attention_probs_dropout_prob": 0.1,
  "bos_token_id": 0,
  "eos_token_id": 2,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 768,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "layer_norm_eps": 1e-05,
  "max_position_embeddings": 8194,
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "output_past": true,
  "pad_token_id": 1,
  "position_embedding_type": "absolute",
  "transformers_version": "4.17.0.dev0",
  "type_vocab_size": 1,
  "use_cache": false,
  "vocab_size": 250002
}