{ "_name_or_path": "deepseekmini_2048", "architectures": [ "DeepseekV3ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "aux_loss_alpha": 0.001, "bos_token_id": 0, "eos_token_id": 1, "ep_size": 1, "first_k_dense_replace": 1, "hidden_act": "silu", "hidden_size": 1024, "initializer_range": 0.02, "intermediate_size": 2560, "kv_lora_rank": 64, "max_position_embeddings": 4096, "model_type": "deepseek_v3", "moe_intermediate_size": 512, "moe_layer_freq": 1, "n_group": 2, "n_routed_experts": 16, "n_shared_experts": 1, "norm_topk_prob": true, "num_attention_heads": 12, "num_experts_per_tok": 4, "num_hidden_layers": 8, "num_key_value_heads": 12, "num_nextn_predict_layers": 1, "pad_token_id": 1, "pretraining_tp": 1, "q_lora_rank": 128, "qk_nope_head_dim": 48, "qk_rope_head_dim": 16, "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": 2048, "type": "yarn" }, "rope_theta": 10000.0, "routed_scaling_factor": 2.5, "scoring_func": "sigmoid", "seq_aux": true, "tie_word_embeddings": true, "topk_group": 1, "topk_method": "noaux_tc", "torch_dtype": "float32", "transformers_version": "4.48.3", "use_cache": true, "v_head_dim": 48, "vocab_size": 129280 }