| { | |
| "architectures": [ | |
| "MiniMaxForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "layer_types": [ | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "linear_attention", | |
| "full_attention" | |
| ], | |
| "bos_token_id": null, | |
| "eos_token_id": null, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 6144, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 9216, | |
| "full_attn_alpha_factor": 3.5565588200778455, | |
| "full_attn_beta_factor": 1.0, | |
| "linear_attn_alpha_factor": 3.5565588200778455, | |
| "linear_attn_beta_factor": 1.0, | |
| "mlp_alpha_factor": 3.5565588200778455, | |
| "mlp_beta_factor": 1.0, | |
| "max_position_embeddings": 10240000, | |
| "model_type": "minimax", | |
| "num_attention_heads": 64, | |
| "num_experts_per_tok": 2, | |
| "num_hidden_layers": 80, | |
| "num_key_value_heads": 8, | |
| "num_local_experts": 32, | |
| "output_router_logits": false, | |
| "postnorm": true, | |
| "rms_norm_eps": 1e-05, | |
| "rope_theta": 10000000, | |
| "rotary_dim": 64, | |
| "router_aux_loss_coef": 0.001, | |
| "router_jitter_noise": 0.0, | |
| "shared_intermediate_size": 0, | |
| "shared_moe_mode": "sigmoid", | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "4.45.2", | |
| "use_cache": true, | |
| "vocab_size": 200064 | |
| } |