{ "_attn_implementation_autoset": false, "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": 163584, "dtype": "bfloat16", "eos_token_id": 163586, "ep_size": 1, "first_k_dense_replace": 1, "hidden_act": "silu", "hidden_size": 7168, "initializer_range": 0.02, "intermediate_size": 18432, "kv_lora_rank": 512, "max_position_embeddings": 262144, "model_type": "deepseek_v3", "moe_intermediate_size": 2048, "moe_layer_freq": 1, "n_group": 1, "n_routed_experts": 384, "n_shared_experts": 1, "norm_topk_prob": true, "num_attention_heads": 64, "num_experts_per_tok": 8, "num_hidden_layers": 61, "num_key_value_heads": 64, "num_nextn_predict_layers": 0, "pad_token_id": 163839, "pretraining_tp": 1, "q_lora_rank": 1536, "qk_nope_head_dim": 128, "qk_rope_head_dim": 64, "rms_norm_eps": 1e-05, "rope_scaling": { "beta_fast": 1.0, "beta_slow": 1.0, "factor": 64.0, "mscale": 1.0, "mscale_all_dim": 1.0, "original_max_position_embeddings": 4096, "type": "yarn" }, "rope_theta": 50000.0, "routed_scaling_factor": 2.827, "scoring_func": "sigmoid", "seq_aux": true, "tie_word_embeddings": false, "topk_group": 1, "topk_method": "noaux_tc", "transformers_version": "4.57.1", "use_cache": true, "v_head_dim": 128, "vocab_size": 163840, "quantization_config": { "config_groups": { "group_0": { "input_activations": { "dynamic": false, "num_bits": 4, "type": "float", "group_size": 16 }, "weights": { "dynamic": false, "num_bits": 4, "type": "float", "group_size": 16 }, "targets": [ "Linear" ] } }, "ignore": [ "lm_head", "model.layers.0*", "model.layers.1.mlp.shared_experts*", "model.layers.1.self_attn*", "model.layers.10.mlp.shared_experts*", "model.layers.10.self_attn*", "model.layers.11.mlp.shared_experts*", "model.layers.11.self_attn*", "model.layers.12.mlp.shared_experts*", "model.layers.12.self_attn*", "model.layers.13.mlp.shared_experts*", "model.layers.13.self_attn*", "model.layers.14.mlp.shared_experts*", "model.layers.14.self_attn*", "model.layers.15.mlp.shared_experts*", "model.layers.15.self_attn*", "model.layers.16.mlp.shared_experts*", "model.layers.16.self_attn*", "model.layers.17.mlp.shared_experts*", "model.layers.17.self_attn*", "model.layers.18.mlp.shared_experts*", "model.layers.18.self_attn*", "model.layers.19.mlp.shared_experts*", "model.layers.19.self_attn*", "model.layers.2.mlp.shared_experts*", "model.layers.2.self_attn*", "model.layers.20.mlp.shared_experts*", "model.layers.20.self_attn*", "model.layers.21.mlp.shared_experts*", "model.layers.21.self_attn*", "model.layers.22.mlp.shared_experts*", "model.layers.22.self_attn*", "model.layers.23.mlp.shared_experts*", "model.layers.23.self_attn*", "model.layers.24.mlp.shared_experts*", "model.layers.24.self_attn*", "model.layers.25.mlp.shared_experts*", "model.layers.25.self_attn*", "model.layers.26.mlp.shared_experts*", "model.layers.26.self_attn*", "model.layers.27.mlp.shared_experts*", "model.layers.27.self_attn*", "model.layers.28.mlp.shared_experts*", "model.layers.28.self_attn*", "model.layers.29.mlp.shared_experts*", "model.layers.29.self_attn*", "model.layers.3.mlp.shared_experts*", "model.layers.3.self_attn*", "model.layers.30.mlp.shared_experts*", "model.layers.30.self_attn*", "model.layers.31.mlp.shared_experts*", "model.layers.31.self_attn*", "model.layers.32.mlp.shared_experts*", "model.layers.32.self_attn*", "model.layers.33.mlp.shared_experts*", "model.layers.33.self_attn*", "model.layers.34.mlp.shared_experts*", "model.layers.34.self_attn*", "model.layers.35.mlp.shared_experts*", "model.layers.35.self_attn*", "model.layers.36.mlp.shared_experts*", "model.layers.36.self_attn*", "model.layers.37.mlp.shared_experts*", "model.layers.37.self_attn*", "model.layers.38.mlp.shared_experts*", "model.layers.38.self_attn*", "model.layers.39.mlp.shared_experts*", "model.layers.39.self_attn*", "model.layers.4.mlp.shared_experts*", "model.layers.4.self_attn*", "model.layers.40.mlp.shared_experts*", "model.layers.40.self_attn*", "model.layers.41.mlp.shared_experts*", "model.layers.41.self_attn*", "model.layers.42.mlp.shared_experts*", "model.layers.42.self_attn*", "model.layers.43.mlp.shared_experts*", "model.layers.43.self_attn*", "model.layers.44.mlp.shared_experts*", "model.layers.44.self_attn*", "model.layers.45.mlp.shared_experts*", "model.layers.45.self_attn*", "model.layers.46.mlp.shared_experts*", "model.layers.46.self_attn*", "model.layers.47.mlp.shared_experts*", "model.layers.47.self_attn*", "model.layers.48.mlp.shared_experts*", "model.layers.48.self_attn*", "model.layers.49.mlp.shared_experts*", "model.layers.49.self_attn*", "model.layers.5.mlp.shared_experts*", "model.layers.5.self_attn*", "model.layers.50.mlp.shared_experts*", "model.layers.50.self_attn*", "model.layers.51.mlp.shared_experts*", "model.layers.51.self_attn*", "model.layers.52.mlp.shared_experts*", "model.layers.52.self_attn*", "model.layers.53.mlp.shared_experts*", "model.layers.53.self_attn*", "model.layers.54.mlp.shared_experts*", "model.layers.54.self_attn*", "model.layers.55.mlp.shared_experts*", "model.layers.55.self_attn*", "model.layers.56.mlp.shared_experts*", "model.layers.56.self_attn*", "model.layers.57.mlp.shared_experts*", "model.layers.57.self_attn*", "model.layers.58.mlp.shared_experts*", "model.layers.58.self_attn*", "model.layers.59.mlp.shared_experts*", "model.layers.59.self_attn*", "model.layers.6.mlp.shared_experts*", "model.layers.6.self_attn*", "model.layers.60.mlp.shared_experts*", "model.layers.60.self_attn*", "model.layers.7.mlp.shared_experts*", "model.layers.7.self_attn*", "model.layers.8.mlp.shared_experts*", "model.layers.8.self_attn*", "model.layers.9.mlp.shared_experts*", "model.layers.9.self_attn*" ], "quant_algo": "NVFP4", "kv_cache_scheme": { "dynamic": false, "num_bits": 8, "type": "float" }, "producer": { "name": "modelopt", "version": "0.40.0.dev66+gbe64f6b1d.d20251119" }, "quant_method": "modelopt" } }