LongLM-large / config.json
{
"_name_or_path": "./model6/t5-xlarge_train19",
"architectures": [
"T5ForConditionalGeneration"
],
"d_ff": 3072,
"d_kv": 64,
"d_model": 1536,
"decoder_start_token_id": 1,
"dropout_rate": 0.1,
"early_stopping": true,
"eos_token_id": 2,
"feed_forward_proj": "relu",
"gradient_checkpointing": false,
"initializer_factor": 1.0,
"is_encoder_decoder": true,
"layer_norm_epsilon": 1e-06,
"length_penalty": 2.0,
"max_length": 512,
"min_length": 30,
"model_type": "t5",
"n_positions": 512,
"no_repeat_ngram_size": 3,
"num_beams": 4,
"num_decoder_layers": 32,
"num_heads": 12,
"num_layers": 24,
"output_past": true,
"pad_token_id": 5,
"prefix": "",
"relative_attention_num_buckets": 32,
"save_step": 6,
"task_specific_params": {
"summarization": {
"early_stopping": true,
"length_penalty": 2.0,
"max_length": 512,
"min_length": 30,
"no_repeat_ngram_size": 3,
"num_beams": 4,
"prefix": ""
}
},
"transformers_version": "4.6.1",
"use_cache": true,
"vocab_size": 32100
}