model_zu-en_updated / config.json
Kabelo Malapane
Training in progress, epoch 1
727d595
{
"_name_or_path": "Helsinki-NLP/opus-mt-mul-en",
"activation_dropout": 0.0,
"activation_function": "swish",
"add_bias_logits": false,
"add_final_layer_norm": false,
"architectures": [
"MarianMTModel"
],
"attention_dropout": 0.0,
"bad_words_ids": [
[
64171
]
],
"bos_token_id": 0,
"classif_dropout": 0.0,
"classifier_dropout": 0.0,
"d_model": 512,
"decoder_attention_heads": 8,
"decoder_ffn_dim": 2048,
"decoder_layerdrop": 0.0,
"decoder_layers": 6,
"decoder_start_token_id": 64171,
"dropout": 0.1,
"encoder_attention_heads": 8,
"encoder_ffn_dim": 2048,
"encoder_layerdrop": 0.0,
"encoder_layers": 6,
"eos_token_id": 0,
"extra_pos_embeddings": 64172,
"forced_eos_token_id": 0,
"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": 512,
"max_position_embeddings": 512,
"model_type": "marian",
"normalize_before": false,
"normalize_embedding": false,
"num_beams": 6,
"num_hidden_layers": 6,
"pad_token_id": 64171,
"scale_embedding": true,
"static_position_embeddings": true,
"torch_dtype": "float32",
"transformers_version": "4.16.2",
"use_cache": true,
"vocab_size": 64172
}