{ "_name_or_path": "/Users/seungbo/Downloads/\uc774\uac70/10GB_1epoch/1B_checkpoint_bf16", "architectures": [ "DeepseekV3ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "auto_map": { "AutoConfig": "configuration_deepseek.DeepseekV3Config", "AutoModel": "modeling_deepseek.DeepseekV3Model", "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM" }, "aux_loss_alpha": 0.001, "bos_token_id": 0, "eos_token_id": 1, "ep_size": 1, "first_k_dense_replace": 3, "hidden_act": "silu", "hidden_size": 1024, "initializer_range": 0.02, "intermediate_size": 4096, "kv_lora_rank": 64, "max_position_embeddings": 4096, "model_type": "deepseek_v3", "moe_intermediate_size": 256, "moe_layer_freq": 1, "n_group": 8, "n_routed_experts": 32, "n_shared_experts": 1, "norm_topk_prob": true, "num_attention_heads": 16, "num_experts_per_tok": 1, "num_hidden_layers": 24, "num_key_value_heads": 16, "num_nextn_predict_layers": 1, "pretraining_tp": 1, "q_lora_rank": 224, "qk_nope_head_dim": 16, "qk_rope_head_dim": 8, "rms_norm_eps": 1e-06, "rope_scaling": { "beta_fast": 32, "beta_slow": 1, "factor": 40, "mscale": 1.0, "mscale_all_dim": 1.0, "original_max_position_embeddings": 4096, "type": "yarn" }, "rope_theta": 10000, "routed_scaling_factor": 2.5, "scoring_func": "sigmoid", "seq_aux": true, "tie_word_embeddings": false, "topk_group": 4, "topk_method": "trainable_olmoe", "torch_dtype": "bfloat16", "transformers_version": "4.46.3", "use_cache": true, "v_head_dim": 16, "vocab_size": 129280 }