| { | |
| "architectures": [ | |
| "CharformerCanineForMaskedLM" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "bos_token_id": 57344, | |
| "downsampling_rate": 4, | |
| "eos_token_id": 57345, | |
| "gbst_dim": 768, | |
| "gbst_downsample_factor": 4, | |
| "gbst_max_block_size": 8, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "layer_norm_eps": 1e-12, | |
| "local_transformer_stride": 128, | |
| "mask_token_id": 1, | |
| "max_position_embeddings": 8192, | |
| "max_span_length": 10, | |
| "model_type": "canine", | |
| "num_attention_heads": 12, | |
| "num_hash_buckets": 16384, | |
| "num_hash_functions": 8, | |
| "num_hidden_layers": 12, | |
| "pad_token_id": 0, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.48.3", | |
| "type_vocab_size": 16, | |
| "upsampling_kernel_size": 4, | |
| "vocab_size": 38 | |
| } | |