| { |
| "_attn_implementation_autoset": false, |
| "add_cross_attention": false, |
| "architectures": [ |
| "MiniMaxM1ForCausalLM" |
| ], |
| "attention_dropout": 0.0, |
| "attn_type_list": [ |
| 0, |
| 0, |
| 0, |
| 0, |
| 0, |
| 0, |
| 0, |
| 1 |
| ], |
| "auto_map": { |
| "AutoConfig": "configuration_minimax_m1.MiniMaxM1Config", |
| "AutoModelForCausalLM": "modeling_minimax_m1.MiniMaxM1ForCausalLM" |
| }, |
| "bos_token_id": null, |
| "cross_attention_hidden_size": null, |
| "decoder_start_token_id": null, |
| "dtype": "float32", |
| "eos_token_id": null, |
| "finetuning_task": null, |
| "head_dim": 64, |
| "hidden_act": "silu", |
| "hidden_size": 512, |
| "initializer_range": 0.02, |
| "intermediate_size": 256, |
| "is_decoder": false, |
| "layernorm_full_attention_alpha": 3.5565588200778455, |
| "layernorm_full_attention_beta": 1.0, |
| "layernorm_linear_attention_alpha": 3.5565588200778455, |
| "layernorm_linear_attention_beta": 1.0, |
| "layernorm_mlp_alpha": 3.5565588200778455, |
| "layernorm_mlp_beta": 1.0, |
| "max_position_embeddings": 10240000, |
| "model_type": "minimax_m1", |
| "num_attention_heads": 8, |
| "num_experts_per_tok": 2, |
| "num_hidden_layers": 8, |
| "num_key_value_heads": 2, |
| "num_local_experts": 4, |
| "output_router_logits": false, |
| "pad_token_id": null, |
| "postnorm": true, |
| "prefix": null, |
| "pruned_heads": {}, |
| "rms_norm_eps": 1e-05, |
| "rope_theta": 10000000, |
| "rotary_dim": 32, |
| "router_aux_loss_coef": 0.001, |
| "router_jitter_noise": 0.0, |
| "sep_token_id": null, |
| "shared_intermediate_size": 0, |
| "shared_moe_mode": "sigmoid", |
| "sliding_window": null, |
| "task_specific_params": null, |
| "tf_legacy_loss": false, |
| "tie_encoder_decoder": false, |
| "tie_word_embeddings": false, |
| "tokenizer_class": null, |
| "torchscript": false, |
| "transformers_version": "5.3.0", |
| "use_bfloat16": false, |
| "use_cache": true, |
| "vocab_size": 200064 |
| } |
|
|
