distilbart-cnn-6-6 / config.json
valhalla's picture
add flax model
d2fde4c
{
"_num_labels": 3,
"activation_dropout": 0.0,
"activation_function": "gelu",
"add_bias_logits": false,
"add_final_layer_norm": false,
"architectures": [
"BartForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 0,
"classif_dropout": 0.0,
"classifier_dropout": 0.0,
"d_model": 1024,
"decoder_attention_heads": 16,
"decoder_ffn_dim": 4096,
"decoder_layerdrop": 0.0,
"decoder_layers": 6,
"decoder_start_token_id": 2,
"dropout": 0.1,
"early_stopping": true,
"encoder_attention_heads": 16,
"encoder_ffn_dim": 4096,
"encoder_layerdrop": 0.0,
"encoder_layers": 6,
"eos_token_id": 2,
"extra_pos_embeddings": 2,
"force_bos_token_to_be_generated": true,
"forced_bos_token_id": 0,
"forced_eos_token_id": 2,
"gradient_checkpointing": false,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1",
"2": "LABEL_2"
},
"init_std": 0.02,
"is_encoder_decoder": true,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1,
"LABEL_2": 2
},
"length_penalty": 2.0,
"max_length": 142,
"max_position_embeddings": 1024,
"min_length": 56,
"model_type": "bart",
"no_repeat_ngram_size": 3,
"normalize_before": false,
"normalize_embedding": true,
"num_beams": 4,
"num_hidden_layers": 6,
"output_past": true,
"pad_token_id": 1,
"prefix": " ",
"replacing_rate": 0,
"scale_embedding": false,
"static_position_embeddings": false,
"student_decoder_layers": null,
"student_encoder_layers": null,
"task_specific_params": {
"summarization": {
"early_stopping": true,
"length_penalty": 2.0,
"max_length": 142,
"min_length": 56,
"no_repeat_ngram_size": 3,
"num_beams": 4
}
},
"transformers_version": "4.7.0.dev0",
"use_cache": true,
"vocab_size": 50264
}