| { | |
| "architectures": [ | |
| "MiniMaxM2ForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "dtype": "float32", | |
| "eos_token_id": 2, | |
| "head_dim": 64, | |
| "hidden_act": "silu", | |
| "hidden_size": 512, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 256, | |
| "max_position_embeddings": 4096, | |
| "model_type": "minimax_m2", | |
| "num_attention_heads": 8, | |
| "num_experts_per_tok": 4, | |
| "num_hidden_layers": 12, | |
| "num_key_value_heads": 4, | |
| "num_local_experts": 8, | |
| "output_router_logits": false, | |
| "pad_token_id": null, | |
| "partial_rotary_factor": 0.5, | |
| "qk_norm_type": "per_layer", | |
| "rms_norm_eps": 1e-06, | |
| "rope_parameters": { | |
| "partial_rotary_factor": 0.5, | |
| "rope_theta": 5000000, | |
| "rope_type": "default" | |
| }, | |
| "rope_theta": 5000000, | |
| "rotary_dim": 32, | |
| "router_aux_loss_coef": 0.001, | |
| "router_jitter_noise": 0.0, | |
| "scoring_func": "sigmoid", | |
| "sliding_window": null, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "5.2.0.dev0", | |
| "use_cache": true, | |
| "use_grouped_mm": false, | |
| "use_qk_norm": true, | |
| "use_routing_bias": true, | |
| "vocab_size": 200064 | |
| } | |