ke-t5-large / config.json
kimsan0622's picture
First version of the ke-t5-large model and tokenizer.
50a0f02
raw
history blame
601 Bytes
{
"_name_or_path": "hf/ke-t5-large",
"architectures": [
"T5ForConditionalGeneration"
],
"d_ff": 2816,
"d_kv": 64,
"d_model": 1024,
"decoder_start_token_id": 0,
"dropout_rate": 0.0,
"eos_token_id": 1,
"feed_forward_proj": "gated-gelu",
"initializer_factor": 1.0,
"is_encoder_decoder": true,
"layer_norm_epsilon": 1e-06,
"model_type": "t5",
"n_positions": 512,
"num_decoder_layers": 24,
"num_heads": 16,
"num_layers": 24,
"pad_token_id": 0,
"relative_attention_num_buckets": 32,
"transformers_version": "4.4.2",
"use_cache": true,
"vocab_size": 64128
}