neuronxcc-2.15.128.0+56dc5a86/MODULE_068f14c83f51585c67d8/config.json

{
  "_name_or_path": "hf-internal-testing/tiny-random-DebertaV2Model",
  "architectures": [
    "DebertaV2Model"
  ],
  "attention_probs_dropout_prob": 0.1,
  "hidden_act": "gelu",
  "hidden_dropout_prob": 0.1,
  "hidden_size": 32,
  "initializer_range": 0.02,
  "intermediate_size": 37,
  "layer_norm_eps": 1e-07,
  "max_position_embeddings": 512,
  "max_relative_positions": -1,
  "model_type": "deberta-v2",
  "neuron": {
    "auto_cast": null,
    "auto_cast_type": null,
    "compiler_type": "neuronx-cc",
    "compiler_version": "2.15.128.0+56dc5a86",
    "disable_fallback": false,
    "disable_fast_relayout": false,
    "dynamic_batch_size": true,
    "inline_weights_to_neff": true,
    "input_names": [
      "input_ids",
      "attention_mask",
      "token_type_ids"
    ],
    "model_type": "deberta-v2",
    "optlevel": "2",
    "output_attentions": false,
    "output_hidden_states": false,
    "output_names": [
      "last_hidden_state"
    ],
    "static_batch_size": 1,
    "static_sequence_length": 32
  },
  "num_attention_heads": 4,
  "num_hidden_layers": 5,
  "pad_token_id": 0,
  "pooler_dropout": 0,
  "pooler_hidden_act": "gelu",
  "pooler_hidden_size": 32,
  "pos_att_type": [
    "none"
  ],
  "position_biased_input": true,
  "relative_attention": false,
  "task": "feature-extraction",
  "torchscript": true,
  "transformers_version": "4.43.2",
  "type_vocab_size": 16,
  "vocab_size": 128001
}