| { | |
| "architectures": [ | |
| "ProPrimeForMaskedLM" | |
| ], | |
| "attention_probs_dropout_prob": 0.0, | |
| "auto_map": { | |
| "AutoModelForMaskedLM": "modeling_proprime.ProPrimeForMaskedLM" | |
| }, | |
| "emb_layer_norm_before": false, | |
| "flash_attention": true, | |
| "hidden_dropout_prob": 0.0, | |
| "hidden_size": 1280, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 5120, | |
| "layer_norm_eps": 1e-05, | |
| "mask_token_id": 32, | |
| "max_position_embeddings": 1026, | |
| "model_type": "proprime", | |
| "num_attention_heads": 20, | |
| "num_hidden_layers": 33, | |
| "pad_token_id": 1, | |
| "position_embedding_type": "rotary", | |
| "token_dropout": true, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.36.2", | |
| "use_cache": true, | |
| "vocab_size": 33 | |
| } | |