{ "auto_map": { "AutoConfig": "configuration_hybrid.HybridConfig", "AutoModelForCausalLM": "modeling_hybrid.HybridForCausalLM" }, "minicpm_dict": { "_name_or_path": "openbmb/MiniCPM5-1B", "architectures": [ "LlamaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 0, "chunk_size_feed_forward": 0, "dtype": "bfloat16", "eos_token_id": [ 1, 130073 ], "head_dim": 128, "hidden_act": "silu", "hidden_size": 1536, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 4608, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "num_attention_heads": 16, "num_hidden_layers": 24, "num_key_value_heads": 2, "output_attentions": false, "output_hidden_states": false, "pad_token_id": 1, "pretraining_tp": 1, "problem_type": null, "return_dict": true, "rms_norm_eps": 1e-06, "rope_parameters": { "rope_theta": 5000000, "rope_type": "default" }, "tie_word_embeddings": false, "transformers_version": "5.10.2", "use_cache": true, "vocab_size": 130560 }, "minicpm_model_name": "openbmb/MiniCPM5-1B", "model_type": "true_hybrid_reasoning_agent", "qwen_dict": { "_name_or_path": "DavidAU/Qwen3-Zero-Coder-Reasoning-V2-0.8B", "architectures": [ "Qwen3ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 151643, "chunk_size_feed_forward": 0, "dtype": "float16", "eos_token_id": 151645, "head_dim": 128, "hidden_act": "silu", "hidden_size": 1024, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 3072, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_types": [ "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention" ], "max_position_embeddings": 40960, "max_window_layers": 28, "model_type": "qwen3", "num_attention_heads": 16, "num_hidden_layers": 42, "num_key_value_heads": 8, "output_attentions": false, "output_hidden_states": false, "pad_token_id": null, "problem_type": null, "return_dict": true, "rms_norm_eps": 1e-06, "rope_parameters": { "rope_theta": 1000000, "rope_type": "default" }, "sliding_window": null, "tie_word_embeddings": true, "transformers_version": "5.10.2", "use_cache": true, "use_sliding_window": false, "vocab_size": 151936 }, "qwen_model_name": "DavidAU/Qwen3-Zero-Coder-Reasoning-V2-0.8B", "transformers_version": "5.10.2", "use_cache": false }