sismetanin's picture
initial commit
ffb93ed
{
"_name_or_path": "/home/ssmetanin/sentiment_hf/ft_models/linis_hf/linis_hf-mbart_ru_sum_gazeta-l128-b64_lr2e-5_e4/v1",
"activation_dropout": 0.0,
"activation_function": "gelu",
"add_bias_logits": false,
"add_final_layer_norm": true,
"architectures": [
"MBartForSequenceClassification"
],
"attention_dropout": 0.1,
"bos_token_id": 0,
"classifier_dropout": 0.0,
"d_model": 1024,
"decoder_attention_heads": 16,
"decoder_ffn_dim": 4096,
"decoder_layerdrop": 0.0,
"decoder_layers": 12,
"decoder_start_token_id": 250021,
"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": "sst2",
"force_bos_token_to_be_generated": false,
"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
},
"max_length": 602,
"max_position_embeddings": 1024,
"model_type": "mbart",
"normalize_before": true,
"normalize_embedding": true,
"num_beams": 5,
"num_hidden_layers": 12,
"output_past": true,
"pad_token_id": 1,
"scale_embedding": true,
"static_position_embeddings": false,
"tie_word_embeddings": false,
"transformers_version": "4.2.2",
"use_cache": true,
"vocab_size": 250027
}