krm's picture
Training in progress epoch 0
d32f6da
raw
history blame
745 Bytes
{
"_name_or_path": "google/mt5-small",
"architectures": [
"MT5ForConditionalGeneration"
],
"d_ff": 1024,
"d_kv": 64,
"d_model": 512,
"decoder_start_token_id": 0,
"dense_act_fn": "gelu_new",
"dropout_rate": 0.1,
"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": "mt5",
"num_decoder_layers": 8,
"num_heads": 6,
"num_layers": 8,
"pad_token_id": 0,
"relative_attention_max_distance": 128,
"relative_attention_num_buckets": 32,
"tie_word_embeddings": false,
"tokenizer_class": "T5Tokenizer",
"transformers_version": "4.22.2",
"use_cache": true,
"vocab_size": 250112
}