| { |
| "architectures": [ |
| "MiMoForCausalLM" |
| ], |
| "attention_bias": true, |
| "attention_dropout": 0.0, |
| "auto_map": { |
| "AutoConfig": "XiaomiMiMo/MiMo-7B-Base--configuration_mimo.MiMoConfig", |
| "AutoModel": "XiaomiMiMo/MiMo-7B-Base--modeling_mimo.MiMoModel", |
| "AutoModelForCausalLM": "XiaomiMiMo/MiMo-7B-Base--modeling_mimo.MiMoForCausalLM" |
| }, |
| "head_dim": 128, |
| "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, |
| "num_hidden_layers": 36, |
| "num_key_value_heads": 8, |
| "num_nextn_predict_layers": 1, |
| "quantization_config": { |
| "act_bits": 16, |
| "act_data_type": "int", |
| "act_dynamic": true, |
| "act_group_size": 128, |
| "act_sym": true, |
| "amp": true, |
| "autoround_version": "0.5.1", |
| "batch_size": 8, |
| "bits": 4, |
| "damp_percent": 0.01, |
| "data_type": "int", |
| "desc_act": false, |
| "enable_minmax_tuning": true, |
| "enable_norm_bias_tuning": false, |
| "enable_quanted_input": true, |
| "gradient_accumulate_steps": 1, |
| "group_size": 128, |
| "iters": 1000, |
| "low_gpu_mem_usage": true, |
| "lr": 0.001, |
| "minmax_lr": 0.001, |
| "nsamples": 512, |
| "quant_method": "gptq", |
| "scale_dtype": "torch.float16", |
| "seqlen": 2048, |
| "super_bits": null, |
| "super_group_size": null, |
| "sym": true, |
| "to_quant_block_names": null, |
| "true_sequential": false |
| }, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": null, |
| "rope_theta": 640000, |
| "sliding_window": 32768, |
| "tie_word_embeddings": false, |
| "torch_dtype": "float16", |
| "transformers_version": "4.51.3", |
| "use_cache": true, |
| "use_mrope": false, |
| "use_sliding_window": false, |
| "vocab_size": 151680 |
| } |
