| { | |
| "vocab_size": 69, | |
| "hidden_size": 2048, | |
| "num_hidden_layers": 18, | |
| "num_attention_heads": 16, | |
| "intermediate_size": 8192, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "attention_probs_dropout_prob": 0.1, | |
| "initializer_range": 0.02, | |
| "layer_norm_eps": 1e-12, | |
| "pad_token_id": 3, | |
| "position_embedding_type": "rotary", | |
| "classifier_dropout": 0.1, | |
| "rotary_theta": 10000.0, | |
| "ignore_index": -100, | |
| "loss_type": "cross_entropy", | |
| "lora": false, | |
| "lora_alpha": 32.0, | |
| "lora_r": 16, | |
| "lora_dropout": 0.1 | |
| } |