| { |
| "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 |
| } |
|
|
