| { | |
| "architectures": [ | |
| "KORMoMoeForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_kormo_moe.KORMoMoeConfig", | |
| "AutoModelForCausalLM": "modeling_kormo_moe.KORMoMoeForCausalLM" | |
| }, | |
| "bos_token_id": 125030, | |
| "decoder_sparse_step": 1, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 125040, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 4096, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 16384, | |
| "mask_type": null, | |
| "max_position_embeddings": 131072, | |
| "mlp_bias": false, | |
| "model_type": "kormo_moe", | |
| "moe_intermediate_size": 16384, | |
| "norm_topk_prob": true, | |
| "num_attention_heads": 32, | |
| "num_experts": 2, | |
| "num_experts_per_tok": 2, | |
| "num_hidden_layers": 40, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 125032, | |
| "pretrain_tp": 1, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "rope_theta": 8000000.0, | |
| "shared_expert_intermediate_size": null, | |
| "tie_word_embeddings": false, | |
| "tie_word_embeddins": false, | |
| "transformers_version": "4.57.0", | |
| "use_cache": true, | |
| "vocab_size": 125184 | |
| } | |