{ "architectures": [ "MiniCPMForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "auto_map": { "AutoConfig": "openbmb/MiniCPM4-8B--configuration_minicpm.MiniCPMConfig", "AutoModel": "openbmb/MiniCPM4-8B--modeling_minicpm.MiniCPMModel", "AutoModelForCausalLM": "openbmb/MiniCPM4-8B--modeling_minicpm.MiniCPMForCausalLM", "AutoModelForSeq2SeqLM": "openbmb/MiniCPM4-8B--modeling_minicpm.MiniCPMForCausalLM", "AutoModelForSequenceClassification": "openbmb/MiniCPM4-8B--modeling_minicpm.MiniCPMForSequenceClassification" }, "bos_token_id": 1, "dim_model_base": 32, "eos_token_id": [ 2, 73440 ], "hidden_act": "silu", "hidden_size": 64, "initializer_range": 0.1, "intermediate_size": 128, "max_position_embeddings": 32768, "model_type": "minicpm", "mup_denominator": 32, "num_attention_heads": 2, "num_hidden_layers": 2, "num_key_value_heads": 1, "pad_token_id": 2, "pretraining_tp": 1, "rms_norm_eps": 1e-06, "rope_scaling": { "long_factor": [ 0.9977997200264581, 1.014658295992452, 1.0349680404997148, 1.059429246056193, 1.0888815016813513, 1.1243301355211495, 1.166977103606075, 1.2182568066927284, 1.2798772354275727, 1.3538666751582975, 1.4426259039919596, 1.5489853358570191, 1.6762658237220625, 1.8283407612492941, 2.0096956085876183, 2.225478927469756 ], "original_max_position_embeddings": 32768, "rope_type": "longrope", "short_factor": [ 0.9977997200264581, 1.014658295992452, 1.0349680404997148, 1.059429246056193, 1.0888815016813513, 1.1243301355211495, 1.166977103606075, 1.2182568066927284, 1.2798772354275727, 1.3538666751582975, 1.4426259039919596, 1.5489853358570191, 1.6762658237220625, 1.8283407612492941, 2.0096956085876183, 2.225478927469756 ] }, "rope_theta": 10000.0, "scale_depth": 1.4, "scale_emb": 12, "sparse_config": null, "torch_dtype": "bfloat16", "transformers_version": "4.51.3", "use_cache": true, "vocab_size": 73448 }