qywu
/

Text2Text Generation
Transformers
PyTorch
Inference Endpoints
membart-base / config.json
qywu's picture
Upload MemBartForConditionalGeneration
844d9fe
raw
history blame contribute delete
977 Bytes
{
"activation_dropout": 0.0,
"activation_function": "gelu",
"add_bias_logits": false,
"add_final_layer_norm": false,
"architectures": [
"MemBartForConditionalGeneration"
],
"attention_dropout": 0.0,
"bos_token_id": 0,
"d_model": 768,
"decoder_attention_heads": 12,
"decoder_ffn_dim": 3072,
"decoder_layerdrop": 0.0,
"decoder_layers": 6,
"decoder_start_token_id": 2,
"dropout": 0.0,
"encoder_attention_heads": 12,
"encoder_ffn_dim": 3072,
"encoder_layerdrop": 0.0,
"encoder_layers": 6,
"eos_token_id": 2,
"forced_eos_token_id": 2,
"gradient_checkpointing": false,
"init_std": 0.01,
"is_encoder_decoder": true,
"max_position_embeddings": 1024,
"memory_len": 64,
"normalize_before": false,
"normalize_embedding": true,
"pad_token_id": 1,
"pretrained_name": "facebook/bart-base",
"scale_embedding": false,
"torch_dtype": "float32",
"transformers_version": "4.26.1",
"use_cache": true,
"vocab_size": 50265
}