praTran / config.json
sarch7040's picture
Training in progress, step 370
158727d verified
raw
history blame
935 Bytes
{
"_name_or_path": "facebook/m2m100_418M",
"activation_dropout": 0.0,
"activation_function": "relu",
"architectures": [
"M2M100ForConditionalGeneration"
],
"attention_dropout": 0.1,
"bos_token_id": 0,
"d_model": 1024,
"decoder_attention_heads": 16,
"decoder_ffn_dim": 4096,
"decoder_layerdrop": 0.05,
"decoder_layers": 12,
"decoder_start_token_id": 2,
"dropout": 0.1,
"early_stopping": null,
"encoder_attention_heads": 16,
"encoder_ffn_dim": 4096,
"encoder_layerdrop": 0.05,
"encoder_layers": 12,
"eos_token_id": 2,
"gradient_checkpointing": false,
"init_std": 0.02,
"is_encoder_decoder": true,
"max_length": null,
"max_position_embeddings": 1024,
"model_type": "m2m_100",
"num_beams": null,
"num_hidden_layers": 12,
"pad_token_id": 1,
"scale_embedding": true,
"torch_dtype": "float32",
"transformers_version": "4.45.1",
"use_cache": true,
"vocab_size": 128112
}