neuronxcc-2.16.345.0+69131dd3/MODULE_44b00dfe26235af3373e/text_encoder/config.json

{
  "_attn_implementation_autoset": true,
  "_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--hf-internal-testing--tiny-pixart-alpha-pipe/snapshots/4bc7fd2ac07bfe6aa361a00dc0ff5bb87250eab1/text_encoder",
  "architectures": [
    "T5EncoderModel"
  ],
  "bos_token_id": 0,
  "classifier_dropout": 0.0,
  "d_ff": 37,
  "d_kv": 8,
  "d_model": 32,
  "decoder_start_token_id": 0,
  "dense_act_fn": "relu",
  "dropout_rate": 0.1,
  "eos_token_id": 1,
  "feed_forward_proj": "relu",
  "gradient_checkpointing": false,
  "initializer_factor": 0.002,
  "is_encoder_decoder": true,
  "is_gated_act": false,
  "layer_norm_epsilon": 1e-06,
  "model_type": "t5",
  "neuron": {
    "auto_cast": null,
    "auto_cast_type": null,
    "compiler_type": "neuronx-cc",
    "compiler_version": "2.16.345.0+69131dd3",
    "dynamic_batch_size": false,
    "inline_weights_to_neff": false,
    "input_names": [
      "input_ids",
      "attention_mask"
    ],
    "model_type": "t5",
    "optlevel": "2",
    "output_attentions": false,
    "output_hidden_states": false,
    "output_names": [
      "last_hidden_state"
    ],
    "static_batch_size": 1,
    "static_sequence_length": 16,
    "tensor_parallel_size": 1
  },
  "num_decoder_layers": 5,
  "num_heads": 4,
  "num_layers": 5,
  "pad_token_id": 0,
  "relative_attention_max_distance": 128,
  "relative_attention_num_buckets": 8,
  "task": "feature-extraction",
  "torch_dtype": "float32",
  "torchscript": true,
  "transformers_version": "4.46.2",
  "use_cache": true,
  "vocab_size": 1103
}