NLP / zs_model_dir /config.json
ashishraics's picture
optimize app
8bb7965
{
"_name_or_path": "valhalla/distilbart-mnli-12-1",
"_num_labels": 3,
"activation_dropout": 0.0,
"activation_function": "gelu",
"add_bias_logits": false,
"add_final_layer_norm": false,
"architectures": [
"BartForSequenceClassification"
],
"attention_dropout": 0.1,
"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": 1,
"decoder_start_token_id": 2,
"dropout": 0.1,
"encoder_attention_heads": 16,
"encoder_ffn_dim": 4096,
"encoder_layerdrop": 0.0,
"encoder_layers": 12,
"eos_token_id": 2,
"extra_pos_embeddings": 2,
"finetuning_task": "mnli",
"force_bos_token_to_be_generated": false,
"forced_eos_token_id": 2,
"gradient_checkpointing": false,
"id2label": {
"0": "contradiction",
"1": "neutral",
"2": "entailment"
},
"init_std": 0.02,
"is_encoder_decoder": true,
"label2id": {
"contradiction": 0,
"entailment": 2,
"neutral": 1
},
"max_position_embeddings": 1024,
"model_type": "bart",
"normalize_before": false,
"normalize_embedding": true,
"num_hidden_layers": 12,
"output_past": false,
"pad_token_id": 1,
"scale_embedding": false,
"static_position_embeddings": false,
"torch_dtype": "float32",
"total_flos": 153130534133111808,
"transformers_version": "4.18.0",
"use_cache": true,
"vocab_size": 50265
}