{
    "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": 7168,
    "initializer_range": 0.02,
    "intermediate_size": 18432,
    "kv_lora_rank": 512,
    "max_position_embeddings": 163840,
    "model_type": "deepseek_v3",
    "moe_intermediate_size": 2048,
    "moe_layer_freq": 1,
    "n_group": 8,
    "n_routed_experts": 256,
    "n_shared_experts": 1,
    "norm_topk_prob": true,
    "num_attention_heads": 128,
    "num_experts_per_tok": 8,
    "num_hidden_layers": 61,
    "num_key_value_heads": 128,
    "num_nextn_predict_layers": 1,
    "pretraining_tp": 1,
    "q_lora_rank": 1536,
    "qk_nope_head_dim": 128,
    "qk_rope_head_dim": 64,
    "quantization_config": {
        "config_groups": {
            "config_group_0": {
                "targets": [
                    "re:.*self_attn.(o_proj|q_b_proj).*"
                ],
                "weights": {
                    "num_bits": 8,
                    "type": "float",
                    "symmetric": true,
                    "group_size": null,
                    "strategy": "block",
                    "block_structure": [
                        128,
                        128
                    ],
                    "dynamic": false,
                    "actorder": null,
                    "scale_dtype": null,
                    "zp_dtype": null,
                    "observer": "static_minmax",
                    "observer_kwargs": {}
                },
                "input_activations": {
                    "num_bits": 8,
                    "type": "float",
                    "symmetric": true,
                    "group_size": 128,
                    "strategy": "group",
                    "block_structure": null,
                    "dynamic": true,
                    "actorder": null,
                    "scale_dtype": null,
                    "zp_dtype": null,
                    "observer": null,
                    "observer_kwargs": {}
                },
                "output_activations": null,
                "format": "float-quantized"
            },
            "config_group_1": {
                "targets": [
                    "re:.*mlp.*\\.(gate_up|gate|up|down)_proj$"
                ],
                "weights": {
                    "num_bits": 4,
                    "type": "float",
                    "symmetric": true,
                    "group_size": 16,
                    "strategy": "tensor_group",
                    "block_structure": null,
                    "dynamic": false,
                    "actorder": null,
                    "scale_dtype": "torch.float8_e4m3fn",
                    "zp_dtype": null,
                    "observer": "static_minmax",
                    "observer_kwargs": {}
                },
                "input_activations": {
                    "num_bits": 4,
                    "type": "float",
                    "symmetric": true,
                    "group_size": 16,
                    "strategy": "tensor_group",
                    "block_structure": null,
                    "dynamic": "local",
                    "actorder": null,
                    "scale_dtype": "torch.float8_e4m3fn",
                    "zp_dtype": null,
                    "observer": "static_minmax",
                    "observer_kwargs": {}
                },
                "output_activations": null,
                "format": "nvfp4-pack-quantized"
            }
        },
        "quant_method": "compressed-tensors",
        "kv_cache_scheme": null,
        "format": "mixed-precision",
        "quantization_status": "compressed",
        "global_compression_ratio": null,
        "ignore": [
            "re:.*self_attn.(kv_a_proj_with_mqa|kv_b_proj|q_a_proj)$"
        ]
    },
    "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": "noaux_tc",
    "torch_dtype": "bfloat16",
    "transformers_version": "4.46.3",
    "use_cache": true,
    "v_head_dim": 128,
    "vocab_size": 129280
}