| { | |
| "adapter_layer_norm": false, | |
| "adapter_reduction_factor": 2, | |
| "adapter_reuse_layer_norm": true, | |
| "architectures": [ | |
| "XmodForCausalLM" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "bos_token_id": 0, | |
| "classifier_dropout": null, | |
| "default_language": "en_XX", | |
| "eos_token_id": 2, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 32, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 37, | |
| "is_decoder": true, | |
| "languages": [ | |
| "en_XX" | |
| ], | |
| "layer_norm_eps": 1e-12, | |
| "ln_before_adapter": true, | |
| "max_position_embeddings": 512, | |
| "model_type": "xmod", | |
| "num_attention_heads": 4, | |
| "num_hidden_layers": 5, | |
| "pad_token_id": 1, | |
| "position_embedding_type": "absolute", | |
| "pre_norm": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.28.0.dev0", | |
| "type_vocab_size": 16, | |
| "use_cache": true, | |
| "vocab_size": 250002 | |
| } | |