bert-base/trainer_output

1{2  "architectures": [3    "Qwen2ForCausalLM"4  ],5  "attention_dropout": 0.0,6  "bos_token_id": 151643,7  "eos_token_id": 151645,8  "hidden_act": "silu",9  "hidden_size": 896,10  "initializer_range": 0.02,11  "intermediate_size": 4864,12  "max_position_embeddings": 32768,13  "max_window_layers": 24,14  "model_type": "qwen2",15  "num_attention_heads": 14,16  "num_hidden_layers": 24,17  "num_key_value_heads": 2,18  "rms_norm_eps": 1e-06,19  "rope_scaling": null,20  "rope_theta": 1000000.0,21  "sliding_window": 32768,22  "tie_word_embeddings": true,23  "torch_dtype": "float32",24  "transformers_version": "4.51.3",25  "use_cache": true,26  "use_sliding_window": false,27  "vocab_size": 15193628}29