{ "model_type": "hrm_text_moe", "architectures": [ "HrmTextMoEForCausalLM" ], "vocab_size": 65536, "hidden_size": 1280, "intermediate_size": 448, "num_hidden_layers": 12, "num_attention_heads": 10, "num_key_value_heads": 10, "head_dim": 128, "H_cycles": 2, "L_cycles": 3, "L_bp_cycles": [ 0, 3 ], "max_position_embeddings": 4096, "rms_norm_eps": 1e-06, "rope_theta": 10000.0, "tie_word_embeddings": false, "initializer_range": 0.02795084971874737, "embedding_scale": 35.77708763999664, "prefix_lm": true, "moe_num_experts": 64, "moe_top_k": 8, "moe_intermediate_size": 448, "moe_implementation": "grouped_triton", "moe_norm_topk_prob": true, "moe_router_aux_loss_coef": 0.001, "pad_token_id": 5, "condition_mapping": { "cot": "<|object_ref_end|>", "direct": "<|object_ref_start|>", "noisy": "<|quad_start|>", "synth": "<|quad_end|>" }, "bos_token_id": 6, "eos_token_id": 11, "auto_map": { "AutoConfig": "configuration_hrm_text_moe.HrmTextMoEConfig", "AutoModelForCausalLM": "modeling_hrm_text_moe.HrmTextMoEForCausalLM" }, "total_params": 3008759040, "active_params_per_token": 696648960, "non_expert_params": 366347520, "expert_params": 2642411520 }