{ "architectures": [ "MatriochkaForCausalLM" ], "auto_map": { "AutoConfig": "modeling_matriochka.MatriochkaConfig", "AutoModelForCausalLM": "modeling_matriochka.MatriochkaForCausalLM" }, "bos_token_id": 0, "dtype": "float32", "eos_token_id": 0, "junction_type": "norm", "model_type": "matriochka", "sub_model_configs": [ { "head_dim": 64, "hidden_size": 1024, "intermediate_size": 4096, "max_position_embeddings": 8192, "num_attention_heads": 16, "num_hidden_layers": 24, "num_key_value_heads": 16, "rms_norm_eps": 1e-05, "rope_theta": 100000.0, "tie_word_embeddings": false, "vocab_size": 49152 }, { "head_dim": 96, "hidden_size": 2304, "intermediate_size": 9216, "max_position_embeddings": 8192, "num_attention_heads": 24, "num_hidden_layers": 10, "num_key_value_heads": 24, "rms_norm_eps": 1e-05, "rope_theta": 100000.0, "tie_word_embeddings": false, "vocab_size": 49152 }, { "head_dim": 128, "hidden_size": 4352, "intermediate_size": 17408, "max_position_embeddings": 8192, "num_attention_heads": 34, "num_hidden_layers": 5, "num_key_value_heads": 34, "rms_norm_eps": 1e-05, "rope_theta": 100000.0, "tie_word_embeddings": false, "vocab_size": 49152 } ], "sub_model_tags": [ "500M_60B_cd", "1-5B_60B_cd", "3B_60B_cd" ], "transformers_version": "5.6.2", "vocab_size": 49152 }