| { | |
| "architectures": [ | |
| "CoNNModel" | |
| ], | |
| "attention_probs_dropout_prob": 0.0, | |
| "hidden_act": "relu", | |
| "hidden_dropout_prob": 0.0, | |
| "hidden_size": 297, | |
| "initializer_range": 0.02, | |
| "input_encoding_map": { | |
| "a": 0, | |
| "b": 1, | |
| "bos": 2, | |
| "c": 3, | |
| "d": 4, | |
| "e": 5, | |
| "f": 6, | |
| "g": 7, | |
| "h": 8, | |
| "i": 9, | |
| "j": 10, | |
| "k": 11, | |
| "l": 12, | |
| "m": 13, | |
| "n": 14, | |
| "o": 15, | |
| "p": 16, | |
| "pad": 17, | |
| "q": 18, | |
| "r": 19, | |
| "s": 20, | |
| "t": 21, | |
| "u": 22, | |
| "v": 23, | |
| "w": 24, | |
| "x": 25, | |
| "y": 26, | |
| "z": 27 | |
| }, | |
| "intermediate_size": 82, | |
| "layer_norm": false, | |
| "layer_norm_eps": 0.02, | |
| "max_position_embeddings": 41, | |
| "mlp_hidden_size": 1640, | |
| "model_type": "conn", | |
| "num_attention_heads": 1, | |
| "num_hidden_layers": 4, | |
| "output_encoding_map": { | |
| "a": 0, | |
| "b": 1, | |
| "c": 2, | |
| "d": 3, | |
| "e": 4, | |
| "f": 5, | |
| "g": 6, | |
| "h": 7, | |
| "i": 8, | |
| "j": 9, | |
| "k": 10, | |
| "l": 11, | |
| "m": 12, | |
| "n": 13, | |
| "o": 14, | |
| "p": 15, | |
| "q": 16, | |
| "r": 17, | |
| "s": 18, | |
| "t": 19, | |
| "u": 20, | |
| "v": 21, | |
| "w": 22, | |
| "x": 23, | |
| "y": 24, | |
| "z": 25 | |
| }, | |
| "pad_token_id": 17, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.26.1", | |
| "vocab_size": 28 | |
| } | |