| { |
| "add_cross_attentions": false, |
| "architectures": [ |
| "GeneratorDiscriminatorTransformer" |
| ], |
| "attention_implementation": "sdpa", |
| "attention_probability_dropout_probability": 0.1, |
| "bos_token_id": 0, |
| "discriminator_weight": 0.15, |
| "dropout_probability": 0.1, |
| "embedding_size": 512, |
| "eos_token_id": 2, |
| "generator_to_discriminator_ratio": 4, |
| "hidden_activation_function": "gelu", |
| "hidden_size": 768, |
| "initializer_factor": 1.0, |
| "intermediate_size": 3072, |
| "intializer_factor": 1.0, |
| "layer_norm_eps": 1e-05, |
| "max_position_embeddings": 514, |
| "num_attention_heads": 12, |
| "num_hidden_layers": 12, |
| "num_intermediate_layers": 1, |
| "pad_token_id": 1, |
| "position_embedding_type": "absolute", |
| "share_embeddings": false, |
| "torch_dtype": "float32", |
| "transformers_version": "4.48.3", |
| "type_vocab_size": 1, |
| "use_cache": false, |
| "vocab_size": 50265, |
| "wac_distribution_layers": [], |
| "wac_distribution_matrix": "none", |
| "wac_embedding_size": -1 |
| } |
|
|
