text_encoder_2/config.json

{
  "_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--ThinkDiffusion--ThinkDiffusionXL/snapshots/e31c4693b7f87128fee02fa6b16c4dc2ada13721/text_encoder_2",
  "architectures": [
    "CLIPTextModelWithProjection"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 0,
  "dropout": 0.0,
  "eos_token_id": 2,
  "hidden_act": "gelu",
  "hidden_size": 1280,
  "initializer_factor": 1.0,
  "initializer_range": 0.02,
  "intermediate_size": 5120,
  "layer_norm_eps": 1e-05,
  "max_position_embeddings": 77,
  "model_type": "clip_text_model",
  "neuron": {
    "auto_cast": "all",
    "auto_cast_type": "bf16",
    "compiler_type": "neuronx-cc",
    "compiler_version": "2.12.68.0+4480452af",
    "disable_fallback": false,
    "disable_fast_relayout": false,
    "dynamic_batch_size": false,
    "input_names": [
      "input_ids"
    ],
    "model_type": "clip-text-model",
    "optlevel": "2",
    "output_attentions": false,
    "output_hidden_states": false,
    "output_names": [
      "text_embeds",
      "last_hidden_state",
      "hidden_states"
    ],
    "static_batch_size": 1,
    "static_num_beams": 1,
    "static_sequence_length": 77
  },
  "num_attention_heads": 20,
  "num_hidden_layers": 32,
  "output_hidden_states": true,
  "pad_token_id": 1,
  "projection_dim": 1280,
  "task": "feature-extraction",
  "torch_dtype": "float16",
  "torchscript": true,
  "transformers_version": "4.36.2",
  "vocab_size": 49408
}