distilt5-qg-hl-12-6 / config.json
{
"_name_or_path": "student-t5-base-qg-hl-12-6",
"architectures": [
"T5ForConditionalGeneration"
],
"d_ff": 3072,
"d_kv": 64,
"d_model": 768,
"decoder_start_token_id": 0,
"dropout_rate": 0.1,
"eos_token_id": 1,
"init_metadata": {
"copied_decoder_layers": [
0,
2,
4,
7,
9,
11
],
"copied_encoder_layers": [
0,
1,
2,
3,
4,
5,
6,
7,
8,
9,
10,
11
],
"teacher_type": "t5"
},
"initializer_factor": 1.0,
"is_encoder_decoder": true,
"layer_norm_epsilon": 1e-06,
"model_type": "t5",
"n_positions": 512,
"num_decoder_layers": 6,
"num_heads": 12,
"num_layers": 12,
"output_past": true,
"pad_token_id": 0,
"relative_attention_num_buckets": 32,
"task_specific_params": {
"summarization": {
"early_stopping": true,
"max_length": 32,
"num_beams": 4,
"prefix": ""
},
"translation_en_to_de": {
"early_stopping": true,
"max_length": 32,
"num_beams": 4,
"prefix": ""
},
"translation_en_to_fr": {
"early_stopping": true,
"max_length": 32,
"num_beams": 4,
"prefix": ""
},
"translation_en_to_ro": {
"early_stopping": true,
"max_length": 32,
"num_beams": 4,
"prefix": ""
}
},
"vocab_size": 32101
}