| { | |
| "encoder_embed_dim": 768, | |
| "encoder_ffn_embed_dim": 3072, | |
| "encoder_attention_heads": 12, | |
| "encoder_layers": 6, | |
| "encoder_normalize_before": 0, | |
| "encoder_learned_pos": 1, | |
| "decoder_learned_pos": 1, | |
| "decoder_embed_dim": 768, | |
| "decoder_ffn_embed_dim": 3072, | |
| "decoder_layers": 6, | |
| "decoder_attention_heads": 12, | |
| "decoder_normalize_before": 0, | |
| "attention_dropout": 0.1, | |
| "activation_dropout": 0.1, | |
| "activation_fn": "gelu", | |
| "dropout": 0.1, | |
| "adaptive_softmax_dropout": 0, | |
| "share_decoder_input_output_embed": 1, | |
| "share_all_embeddings": 1, | |
| "no_token_positional_embeddings": 0, | |
| "no_cross_attention": 0, | |
| "cross_self_attention": 0, | |
| "decoder_output_dim": 768, | |
| "decoder_input_dim": 768, | |
| "no_scale_embedding": 0, | |
| "adaptive_input": 0, | |
| "tie_adaptive_weights": 0, | |
| "layernorm_embedding": 1, | |
| "encoder_layerdrop": 0, | |
| "decoder_layerdrop": 0, | |
| "quant_noise_pq": 0, | |
| "quant_noise_pq_block_size": 8, | |
| "quant_noise_scalar": 0, | |
| "is_encoder_decoder": 1, | |
| "vocab_size": 30522 | |
| } | |