| { | |
| "architectures": [ | |
| "MantaForConditionalGeneration" | |
| ], | |
| "byte_embedding_dim": 64, | |
| "d_ff": 2048, | |
| "d_kv": 64, | |
| "d_model": 512, | |
| "dense_act_fn": "gelu_new", | |
| "dropout_rate": 0.1, | |
| "eos_token_id": 1, | |
| "feed_forward_proj": "gated-gelu", | |
| "frontier_predictor_attention_window": 16, | |
| "frontier_predictor_num_attention_heads": 8, | |
| "frontier_predictor_num_layers": 1, | |
| "initializer_factor": 1.0, | |
| "is_encoder_decoder": true, | |
| "is_gated_act": true, | |
| "layer_norm_epsilon": 1e-06, | |
| "max_length_encoder_decoder": 256, | |
| "max_length_inputs": 256, | |
| "model_type": "manta", | |
| "num_decoder_layers": 6, | |
| "num_heads": 8, | |
| "num_layers": 6, | |
| "pad_token_id": 0, | |
| "pooling_depthwise_convolution": true, | |
| "pooling_kernel_size": 3, | |
| "pooling_mean_pool": false, | |
| "pooling_variance_regularization": 1e-06, | |
| "relative_attention_max_distance": 128, | |
| "relative_attention_num_buckets": 32, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.29.2", | |
| "use_cache": true, | |
| "vocab_size": 384 | |
| } | |