| { | |
| "architectures": [ | |
| "MiMoForCausalLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_mimo.MiMoConfig", | |
| "AutoModel": "modeling_mimo.MiMoModel", | |
| "AutoModelForCausalLM": "modeling_mimo.MiMoForCausalLM" | |
| }, | |
| "attention_dropout": 0.0, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 11008, | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 32, | |
| "model_type": "mimo", | |
| "num_attention_heads": 32, | |
| "head_dim": 128, | |
| "num_hidden_layers": 36, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 640000, | |
| "sliding_window": 32768, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.40.1", | |
| "use_cache": true, | |
| "use_mrope": false, | |
| "use_sliding_window": false, | |
| "vocab_size": 151680, | |
| "attention_bias": true, | |
| "num_nextn_predict_layers": 1 | |
| } | |