text_encoder/config.json

{
  "_attn_implementation_autoset": true,
  "architectures": [
    "CLIPTextModel"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 0,
  "dropout": 0.0,
  "eos_token_id": 2,
  "export_model_type": "clip-text-model",
  "hidden_act": "quick_gelu",
  "hidden_size": 768,
  "initializer_factor": 1.0,
  "initializer_range": 0.02,
  "intermediate_size": 3072,
  "layer_norm_eps": 1e-05,
  "max_position_embeddings": 77,
  "model_type": "clip_text_model",
  "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": "clip-text-model",
    "optlevel": "2",
    "output_attentions": false,
    "output_hidden_states": false,
    "output_names": [
      "last_hidden_state",
      "pooler_output"
    ],
    "static_batch_size": 1,
    "static_sequence_length": 77,
    "task": "feature-extraction",
    "tensor_parallel_size": 1
  },
  "num_attention_heads": 12,
  "num_hidden_layers": 12,
  "pad_token_id": 1,
  "projection_dim": 768,
  "torch_dtype": "bfloat16",
  "torchscript": true,
  "transformers_version": "4.51.3",
  "vocab_size": 49408
}