config.json

{
  "_name_or_path": "/tmp/tmppfzb__ev",
  "architectures": [
    "XLMRobertaModel"
  ],
  "attention_probs_dropout_prob": 0.1,
  "bos_token_id": 0,
  "classifier_dropout": null,
  "eos_token_id": 2,
  "export_model_type": "transformer",
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 1024,
  "initializer_range": 0.02,
  "intermediate_size": 4096,
  "layer_norm_eps": 1e-05,
  "max_position_embeddings": 8194,
  "model_type": "xlm-roberta",
  "neuron": {
    "auto_cast": null,
    "auto_cast_type": null,
    "compiler_type": "neuronx-cc",
    "compiler_version": "2.13.66.0+6dfecc895",
    "disable_fallback": false,
    "disable_fast_relayout": false,
    "dynamic_batch_size": false,
    "inline_weights_to_neff": false,
    "input_names": [
      "input_ids",
      "attention_mask"
    ],
    "model_type": "transformer",
    "optlevel": "2",
    "output_attentions": false,
    "output_hidden_states": false,
    "output_names": [
      "token_embeddings",
      "sentence_embedding"
    ],
    "static_batch_size": 1,
    "static_sequence_length": 1024
  },
  "num_attention_heads": 16,
  "num_hidden_layers": 24,
  "output_past": true,
  "pad_token_id": 1,
  "position_embedding_type": "absolute",
  "task": "feature-extraction",
  "torch_dtype": "float32",
  "torchscript": true,
  "transformers_version": "4.36.2",
  "type_vocab_size": 1,
  "use_cache": true,
  "vocab_size": 250002
}