gsarti's picture
Update config.json
ee54779
raw
history blame
904 Bytes
{
"_name_or_path": ".",
"architectures": [
"T5ForConditionalGeneration"
],
"d_ff": 2048,
"d_kv": 64,
"d_model": 512,
"decoder_start_token_id": 0,
"dropout_rate": 0.1,
"eos_token_id": 1,
"feed_forward_proj": "relu",
"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": 8,
"num_layers": 32,
"output_past": true,
"pad_token_id": 0,
"relative_attention_max_distance": 128,
"relative_attention_num_buckets": 32,
"torch_dtype": "float32",
"transformers_version": "4.15.0",
"use_cache": true,
"vocab_size": 32100,
"task_specific_params": {
"text2text-generation": {
"early_stopping": true,
"length_penalty": 2.0,
"max_length": 100,
"min_length": 10,
"no_repeat_ngram_size": 3,
"num_beams": 4
}
}
}