text_encoder_2/config.json

{
  "_attn_implementation_autoset": true,
  "architectures": [
    "T5EncoderModel"
  ],
  "classifier_dropout": 0.0,
  "d_ff": 10240,
  "d_kv": 64,
  "d_model": 4096,
  "decoder_start_token_id": 0,
  "dense_act_fn": "gelu_new",
  "dropout_rate": 0.1,
  "eos_token_id": 1,
  "export_model_type": "t5-encoder",
  "feed_forward_proj": "gated-gelu",
  "initializer_factor": 1.0,
  "is_encoder_decoder": true,
  "is_gated_act": true,
  "layer_norm_epsilon": 1e-06,
  "model_type": "t5",
  "neuron": {
    "auto_cast": null,
    "auto_cast_type": null,
    "compiler_type": "neuronx-cc",
    "compiler_version": "2.19.8089.0+8ab9f450",
    "dynamic_batch_size": false,
    "float_dtype": "fp32",
    "inline_weights_to_neff": false,
    "input_names": [
      "input_ids"
    ],
    "int_dtype": "int64",
    "model_type": "t5-encoder",
    "optlevel": "2",
    "output_attentions": false,
    "output_hidden_states": false,
    "output_names": [
      "last_hidden_state"
    ],
    "static_batch_size": 1,
    "static_sequence_length": 512,
    "task": "feature-extraction",
    "tensor_parallel_size": 8
  },
  "num_decoder_layers": 24,
  "num_heads": 64,
  "num_layers": 24,
  "output_past": true,
  "pad_token_id": 0,
  "relative_attention_max_distance": 128,
  "relative_attention_num_buckets": 32,
  "tie_word_embeddings": false,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.51.3",
  "use_cache": true,
  "vocab_size": 32128
}