| { |
| "_attn_implementation_autoset": false, |
| "add_cross_attention": false, |
| "architectures": [ |
| "MiniMaxM2ForCausalLM" |
| ], |
| "attention_dropout": 0.0, |
| "attn_type_list": [ |
| 1, |
| 1 |
| ], |
| "bos_token_id": null, |
| "cross_attention_hidden_size": null, |
| "decoder_start_token_id": null, |
| "dtype": "bfloat16", |
| "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, |
| "max_position_embeddings": 4096, |
| "model_type": "minimax_m2", |
| "mtp_transformer_layers": 1, |
| "num_attention_heads": 8, |
| "num_experts_per_tok": 2, |
| "num_hidden_layers": 2, |
| "num_key_value_heads": 2, |
| "num_local_experts": 4, |
| "num_mtp_modules": 1, |
| "output_router_logits": false, |
| "pad_token_id": null, |
| "prefix": null, |
| "pruned_heads": {}, |
| "qk_norm_type": "per_layer", |
| "rms_norm_eps": 1e-06, |
| "rope_parameters": { |
| "rope_theta": 5000000, |
| "rope_type": "default" |
| }, |
| "rotary_dim": 32, |
| "router_aux_loss_coef": 0.001, |
| "router_jitter_noise": 0.0, |
| "scoring_func": "sigmoid", |
| "sep_token_id": null, |
| "shared_intermediate_size": 0, |
| "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, |
| "use_mtp": true, |
| "use_qk_norm": true, |
| "use_routing_bias": true, |
| "vocab_size": 200064 |
| } |
|
|
