Milan Straka
Initial upload 25efaf3
{
"_name_or_path": "checkpoints/es/byt5-small_wiki_epoch-6",
"architectures": [
"T5ForConditionalGeneration"
],
"d_ff": 3584,
"d_kv": 64,
"d_model": 1472,
"decoder_start_token_id": 0,
"dropout_rate": 0.1,
"eos_token_id": 1,
"feed_forward_proj": "gated-gelu",
"gradient_checkpointing": false,
"initializer_factor": 1.0,
"is_encoder_decoder": true,
"layer_norm_epsilon": 1e-06,
"model_type": "t5",
"num_decoder_layers": 4,
"num_heads": 6,
"num_layers": 12,
"pad_token_id": 0,
"relative_attention_num_buckets": 32,
"tie_word_embeddings": false,
"tokenizer_class": "ByT5Tokenizer",
"transformers_version": "4.8.2",
"use_cache": true,
"vocab_size": 384
}