slovak-t5-base / config.json
dhladek's picture
training on large slovak corpus
1729ba2 verified
raw
history blame contribute delete
686 Bytes
{
"_name_or_path": "/home/patrick/hugging_face/t5/t5-v1_1-base",
"architectures": [
"T5ForConditionalGeneration"
],
"d_ff": 2048,
"d_kv": 64,
"d_model": 768,
"decoder_start_token_id": 0,
"dropout_rate": 0.1,
"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",
"num_decoder_layers": 12,
"num_heads": 12,
"num_layers": 12,
"output_past": true,
"pad_token_id": 0,
"relative_attention_num_buckets": 32,
"tie_word_embeddings": false,
"vocab_size": 120100,
"sp_model_kwargs":{
"enable_sampling": true,
"nbest_size": 4
}
}