|
{ |
|
"_name_or_path": "lmqg_output/mt5_small_itquad_answer/best_model", |
|
"add_prefix": true, |
|
"architectures": [ |
|
"MT5ForConditionalGeneration" |
|
], |
|
"d_ff": 1024, |
|
"d_kv": 64, |
|
"d_model": 512, |
|
"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": "mt5", |
|
"num_decoder_layers": 8, |
|
"num_heads": 6, |
|
"num_layers": 8, |
|
"pad_token_id": 0, |
|
"relative_attention_num_buckets": 32, |
|
"tie_word_embeddings": false, |
|
"tokenizer_class": "T5Tokenizer", |
|
"torch_dtype": "float32", |
|
"transformers_version": "4.18.0.dev0", |
|
"use_cache": true, |
|
"vocab_size": 250101 |
|
} |
|
|