test2 / config.json
piazzola's picture
End of training
2163981 verified
raw
history blame contribute delete
755 Bytes
{
"_name_or_path": "google/t5-efficient-base",
"architectures": [
"T5ForConditionalGeneration"
],
"classifier_dropout": 0.0,
"d_ff": 3072,
"d_kv": 64,
"d_model": 768,
"decoder_start_token_id": 0,
"dense_act_fn": "relu",
"dropout_rate": 0.1,
"eos_token_id": 1,
"feed_forward_proj": "relu",
"initializer_factor": 1.0,
"is_encoder_decoder": true,
"is_gated_act": false,
"layer_norm_epsilon": 1e-06,
"model_type": "t5",
"n_positions": 512,
"num_decoder_layers": 12,
"num_heads": 12,
"num_layers": 12,
"pad_token_id": 0,
"relative_attention_max_distance": 128,
"relative_attention_num_buckets": 32,
"torch_dtype": "float32",
"transformers_version": "4.38.2",
"use_cache": true,
"vocab_size": 32124
}