{
  "architectures": [
    "UMT5EncoderModel"
  ],
  "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,
  "dtype": "bfloat16",
  "eos_token_id": 1,
  "feed_forward_proj": "gated-gelu",
  "initializer_factor": 1.0,
  "is_encoder_decoder": true,
  "is_gated_act": true,
  "layer_norm_epsilon": 1e-06,
  "model_type": "umt5",
  "num_decoder_layers": 24,
  "num_heads": 64,
  "num_layers": 24,
  "output_past": true,
  "pad_token_id": 0,
  "quantization_config": {
    "add_skip_keys": false,
    "dequantize_fp32": false,
    "group_size": 0,
    "is_integer": true,
    "modules_dtype_dict": {},
    "modules_to_not_convert": [
      "wo"
    ],
    "non_blocking": false,
    "quant_conv": false,
    "quant_method": "sdnq",
    "quantization_device": null,
    "return_device": null,
    "svd_rank": 32,
    "svd_steps": 8,
    "use_quantized_matmul": false,
    "use_quantized_matmul_conv": false,
    "use_svd": true,
    "weights_dtype": "uint4"
  },
  "relative_attention_max_distance": 128,
  "relative_attention_num_buckets": 32,
  "scalable_attention": true,
  "tie_word_embeddings": false,
  "tokenizer_class": "T5Tokenizer",
  "transformers_version": "4.57.1",
  "use_cache": true,
  "vocab_size": 256384
}