| { | |
| "alibi": true, | |
| "architectures": [ | |
| "MosaicBertForMaskedLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attention_probs_dropout_prob": 0.0, | |
| "bos_token_id": 50281, | |
| "classifier_activation": "gelu", | |
| "classifier_bias": false, | |
| "classifier_dropout": 0.0, | |
| "classifier_pooling": "mean", | |
| "cls_token_id": 50281, | |
| "context_length": 1024, | |
| "decoder_bias": true, | |
| "deterministic_flash_attn": false, | |
| "embedding_dropout": 0.0, | |
| "eos_token_id": 50282, | |
| "flash_attention": true, | |
| "gated_linear_units": true, | |
| "global_attn_every_n_layers": 3, | |
| "global_rope_theta": 160000.0, | |
| "gradient_checkpointing": false, | |
| "hidden_act": "gelu", | |
| "hidden_activation": "gelu", | |
| "hidden_dropout_prob": 0.0, | |
| "hidden_size": 768, | |
| "initializer_cutoff_factor": 2.0, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 1152, | |
| "layer_norm_eps": 1e-05, | |
| "local_attention": 128, | |
| "local_rope_theta": 10000.0, | |
| "max_position_embeddings": 8192, | |
| "mlp_bias": false, | |
| "mlp_dropout": 0.0, | |
| "model_type": "bert", | |
| "norm_bias": false, | |
| "norm_eps": 1e-05, | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 22, | |
| "pad_token_id": 50283, | |
| "position_embedding_type": "absolute", | |
| "reference_compile": null, | |
| "repad_logits_with_grad": false, | |
| "rope_theta": 10000, | |
| "sep_token_id": 50282, | |
| "sparse_pred_ignore_index": -100, | |
| "sparse_prediction": false, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.50.0", | |
| "type_vocab_size": 2, | |
| "use_cache": true, | |
| "use_low_precision_layernorm": true, | |
| "vocab_size": 50368 | |
| } | |