| { | |
| "add_embedding_noise": false, | |
| "architectures": [ | |
| "LMBaseForMaskedLM" | |
| ], | |
| "attention_probs_dropout_prob": 0.0, | |
| "classifier_dropout": null, | |
| "conditioning_type": null, | |
| "emb_layer_norm_before": null, | |
| "has_conditioning": false, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 384, | |
| "initializer_range": 0.02, | |
| "intermediate_bias": false, | |
| "intermediate_size": 1024, | |
| "key_bias": false, | |
| "layer_norm_eps": 1e-12, | |
| "mask_token_id": 7, | |
| "max_position_embeddings": 512, | |
| "model_type": "pmlm", | |
| "n_concepts": 0, | |
| "noise_mean": 0.0, | |
| "noise_std_max": 0.25, | |
| "noise_std_min": 0.1, | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 8, | |
| "pad_token_id": 9, | |
| "position_embedding_type": "rotary", | |
| "query_bias": false, | |
| "token_dropout": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.46.3", | |
| "use_cache": true, | |
| "value_bias": false, | |
| "vocab_size": 68 | |
| } | |