config_ul2_base_nl36.json

{
    "_name_or_path": "./",
    "architectures": [
        "T5ForConditionalGeneration"
    ],
    "d_ff": 2048,
    "d_kv": 64,
    "d_model": 768,
    "decoder_start_token_id": 0,
    "dense_act_fn": "silu",
    "dropout_rate": 0.1,
    "eos_token_id": 1,
    "feed_forward_proj": "gated-silu",
    "initializer_factor": 1.0,
    "is_encoder_decoder": true,
    "is_gated_act": true,
    "layer_norm_epsilon": 1e-06,
    "model_type": "t5",
    "n_positions": 512,
    "num_decoder_layers": 36,
    "num_heads": 12,
    "num_layers": 36,
    "output_past": true,
    "pad_token_id": 0,
    "relative_attention_max_distance": 128,
    "relative_attention_num_buckets": 32,
    "tie_word_embeddings": true,
    "torch_dtype": "float16",
    "transformers_version": "4.26.1",
    "use_cache": true,
    "vocab_size": 64384
}