33 lines
803 B
JSON
33 lines
803 B
JSON
|
{
|
||
|
|
"_name_or_path": "T5Autocorrection228",
|
||
|
|
"architectures": [
|
||
|
|
"T5ForConditionalGeneration"
|
||
|
|
],
|
||
|
|
"classifier_dropout": 0.0,
|
||
|
|
"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": "t5",
|
||
|
|
"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",
|
||
|
|
"torch_dtype": "float32",
|
||
|
|
"transformers_version": "4.44.1",
|
||
|
|
"use_cache": true,
|
||
|
|
"vocab_size": 250112
|
||
|
|
}
|