CoolFace
Modelpublic

TencentBAC/FastMTP

sourceHugging Faceapache-2.0updated 1y agoView on Hugging Face
7likes8downloads
config.json88 linesDownload Raw Back to root
1{2  "architectures": [3    "MiMoForCausalLM"4  ],5  "attention_bias": true,6  "attention_dropout": 0.0,7  "auto_map": {8  "AutoConfig": "configuration_mimo.MiMoConfig",9  "AutoModel": "modeling_mimo.MiMoModel",10  "AutoModelForCausalLM": "modeling_mimo.MiMoForCausalLM"11  },12  "bos_token_id": 151643,13  "eos_token_id": 151645,14  "head_dim": 128,15  "hidden_act": "silu",16  "hidden_size": 4096,17  "initializer_range": 0.02,18  "intermediate_size": 11008,19  "layer_types": [20    "full_attention",21    "full_attention",22    "full_attention",23    "full_attention",24    "full_attention",25    "full_attention",26    "full_attention",27    "full_attention",28    "full_attention",29    "full_attention",30    "full_attention",31    "full_attention",32    "full_attention",33    "full_attention",34    "full_attention",35    "full_attention",36    "full_attention",37    "full_attention",38    "full_attention",39    "full_attention",40    "full_attention",41    "full_attention",42    "full_attention",43    "full_attention",44    "full_attention",45    "full_attention",46    "full_attention",47    "full_attention",48    "full_attention",49    "full_attention",50    "full_attention",51    "full_attention",52    "full_attention",53    "full_attention",54    "full_attention",55    "full_attention"56  ],57  "max_position_embeddings": 32768,58  "max_window_layers": 36,59  "model_type": "mimo",60  "mtp_loss_step_weights": [61    0.51,62    0.31,63    0.1864  ],65  "mtp_loss_weight": 1.0,66  "ntp_loss_weight": 0.0,67  "num_attention_heads": 32,68  "num_hidden_layers": 36,69  "num_key_value_heads": 8,70  "num_nextn_predict_layers": 1,71  "num_speculative_steps": 3,72  "pad_token_id": 151643,73  "rms_norm_eps": 1e-05,74  "rope_scaling": null,75  "rope_theta": 640000,76  "sliding_window": null,77  "tie_word_embeddings": false,78  "tokenizer_class": [79    "Qwen2Tokenizer"80  ],81  "torch_dtype": "bfloat16",82  "transformers_version": "4.54.0",83  "use_cache": false,84  "use_mrope": false,85  "use_sliding_window": false,86  "vocab_size": 15168087}88