| { |
| "architectures": [ |
| "DeepseekV4ForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 0, |
| "eos_token_id": 1, |
| "hc_eps": 1e-06, |
| "hc_mult": 4, |
| "hc_sinkhorn_iters": 20, |
| "head_dim": 512, |
| "hidden_act": "silu", |
| "hidden_size": 4096, |
| "index_head_dim": 128, |
| "index_n_heads": 64, |
| "index_topk": 512, |
| "initializer_range": 0.02, |
| "max_position_embeddings": 1048576, |
| "model_type": "deepseek_v4", |
| "moe_intermediate_size": 2048, |
| "n_routed_experts": 256, |
| "n_shared_experts": 1, |
| "norm_topk_prob": true, |
| "num_attention_heads": 64, |
| "num_experts_per_tok": 6, |
| "num_hidden_layers": 43, |
| "num_hash_layers": 3, |
| "num_key_value_heads": 1, |
| "num_nextn_predict_layers": 1, |
| "o_groups": 8, |
| "o_lora_rank": 1024, |
| "q_lora_rank": 1024, |
| "qk_rope_head_dim": 64, |
| "rms_norm_eps": 1e-06, |
| "rope_scaling": { |
| "beta_fast": 32, |
| "beta_slow": 1, |
| "factor": 16, |
| "original_max_position_embeddings": 65536, |
| "type": "yarn" |
| }, |
| "rope_theta": 10000, |
| "routed_scaling_factor": 1.5, |
| "scoring_func": "sqrtsoftplus", |
| "sliding_window": 128, |
| "swiglu_limit": 10.0, |
| "tie_word_embeddings": false, |
| "topk_method": "noaux_tc", |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.57.1", |
| "use_cache": true, |
| "vocab_size": 129280, |
| "compress_rope_theta": 160000, |
| "compress_ratios": [ |
| 0, |
| 0, |
| 4, |
| 128, |
| 4, |
| 128, |
| 4, |
| 128, |
| 4, |
| 128, |
| 4, |
| 128, |
| 4, |
| 128, |
| 4, |
| 128, |
| 4, |
| 128, |
| 4, |
| 128, |
| 4, |
| 128, |
| 4, |
| 128, |
| 4, |
| 128, |
| 4, |
| 128, |
| 4, |
| 128, |
| 4, |
| 128, |
| 4, |
| 128, |
| 4, |
| 128, |
| 4, |
| 128, |
| 4, |
| 128, |
| 4, |
| 128, |
| 4, |
| 0 |
| ], |
| "quantization_config": { |
| "global_quant_config": { |
| "input_tensors": { |
| "dtype": "fp4", |
| "is_dynamic": true, |
| "qscheme": "per_group", |
| "ch_axis": -1, |
| "group_size": 32, |
| "symmetric": null, |
| "round_method": "half_even", |
| "scale_type": "float", |
| "scale_format": "e8m0", |
| "scale_calculation_mode": "even", |
| "mx_element_dtype": null, |
| "observer_cls": "PerBlockMXObserver", |
| "is_scale_quant": false |
| }, |
| "output_tensors": null, |
| "weight": { |
| "dtype": "fp4", |
| "is_dynamic": false, |
| "qscheme": "per_group", |
| "ch_axis": -1, |
| "group_size": 32, |
| "symmetric": null, |
| "round_method": "half_even", |
| "scale_type": "float", |
| "scale_format": "e8m0", |
| "scale_calculation_mode": "even", |
| "mx_element_dtype": null, |
| "observer_cls": "PerBlockMXObserver", |
| "is_scale_quant": false |
| }, |
| "bias": null, |
| "target_device": null |
| }, |
| "exclude": [ |
| "layers.0.ffn.gate", |
| "layers.0.ffn.shared_experts.w1", |
| "layers.0.ffn.shared_experts.w2", |
| "layers.0.ffn.shared_experts.w3", |
| "layers.1.ffn.gate", |
| "layers.1.ffn.shared_experts.w1", |
| "layers.1.ffn.shared_experts.w2", |
| "layers.1.ffn.shared_experts.w3", |
| "layers.10.ffn.gate", |
| "layers.10.ffn.shared_experts.w1", |
| "layers.10.ffn.shared_experts.w2", |
| "layers.10.ffn.shared_experts.w3", |
| "layers.11.ffn.gate", |
| "layers.11.ffn.shared_experts.w1", |
| "layers.11.ffn.shared_experts.w2", |
| "layers.11.ffn.shared_experts.w3", |
| "layers.12.ffn.gate", |
| "layers.12.ffn.shared_experts.w1", |
| "layers.12.ffn.shared_experts.w2", |
| "layers.12.ffn.shared_experts.w3", |
| "layers.13.ffn.gate", |
| "layers.13.ffn.shared_experts.w1", |
| "layers.13.ffn.shared_experts.w2", |
| "layers.13.ffn.shared_experts.w3", |
| "layers.14.ffn.gate", |
| "layers.14.ffn.shared_experts.w1", |
| "layers.14.ffn.shared_experts.w2", |
| "layers.14.ffn.shared_experts.w3", |
| "layers.15.ffn.gate", |
| "layers.15.ffn.shared_experts.w1", |
| "layers.15.ffn.shared_experts.w2", |
| "layers.15.ffn.shared_experts.w3", |
| "layers.16.ffn.gate", |
| "layers.16.ffn.shared_experts.w1", |
| "layers.16.ffn.shared_experts.w2", |
| "layers.16.ffn.shared_experts.w3", |
| "layers.17.ffn.gate", |
| "layers.17.ffn.shared_experts.w1", |
| "layers.17.ffn.shared_experts.w2", |
| "layers.17.ffn.shared_experts.w3", |
| "layers.18.ffn.gate", |
| "layers.18.ffn.shared_experts.w1", |
| "layers.18.ffn.shared_experts.w2", |
| "layers.18.ffn.shared_experts.w3", |
| "layers.19.ffn.gate", |
| "layers.19.ffn.shared_experts.w1", |
| "layers.19.ffn.shared_experts.w2", |
| "layers.19.ffn.shared_experts.w3", |
| "layers.2.ffn.gate", |
| "layers.2.ffn.shared_experts.w1", |
| "layers.2.ffn.shared_experts.w2", |
| "layers.2.ffn.shared_experts.w3", |
| "layers.20.ffn.gate", |
| "layers.20.ffn.shared_experts.w1", |
| "layers.20.ffn.shared_experts.w2", |
| "layers.20.ffn.shared_experts.w3", |
| "layers.21.ffn.gate", |
| "layers.21.ffn.shared_experts.w1", |
| "layers.21.ffn.shared_experts.w2", |
| "layers.21.ffn.shared_experts.w3", |
| "layers.22.ffn.gate", |
| "layers.22.ffn.shared_experts.w1", |
| "layers.22.ffn.shared_experts.w2", |
| "layers.22.ffn.shared_experts.w3", |
| "layers.23.ffn.gate", |
| "layers.23.ffn.shared_experts.w1", |
| "layers.23.ffn.shared_experts.w2", |
| "layers.23.ffn.shared_experts.w3", |
| "layers.24.ffn.gate", |
| "layers.24.ffn.shared_experts.w1", |
| "layers.24.ffn.shared_experts.w2", |
| "layers.24.ffn.shared_experts.w3", |
| "layers.25.ffn.gate", |
| "layers.25.ffn.shared_experts.w1", |
| "layers.25.ffn.shared_experts.w2", |
| "layers.25.ffn.shared_experts.w3", |
| "layers.26.ffn.gate", |
| "layers.26.ffn.shared_experts.w1", |
| "layers.26.ffn.shared_experts.w2", |
| "layers.26.ffn.shared_experts.w3", |
| "layers.27.ffn.gate", |
| "layers.27.ffn.shared_experts.w1", |
| "layers.27.ffn.shared_experts.w2", |
| "layers.27.ffn.shared_experts.w3", |
| "layers.28.ffn.gate", |
| "layers.28.ffn.shared_experts.w1", |
| "layers.28.ffn.shared_experts.w2", |
| "layers.28.ffn.shared_experts.w3", |
| "layers.29.ffn.gate", |
| "layers.29.ffn.shared_experts.w1", |
| "layers.29.ffn.shared_experts.w2", |
| "layers.29.ffn.shared_experts.w3", |
| "layers.3.ffn.gate", |
| "layers.3.ffn.shared_experts.w1", |
| "layers.3.ffn.shared_experts.w2", |
| "layers.3.ffn.shared_experts.w3", |
| "layers.30.ffn.gate", |
| "layers.30.ffn.shared_experts.w1", |
| "layers.30.ffn.shared_experts.w2", |
| "layers.30.ffn.shared_experts.w3", |
| "layers.31.ffn.gate", |
| "layers.31.ffn.shared_experts.w1", |
| "layers.31.ffn.shared_experts.w2", |
| "layers.31.ffn.shared_experts.w3", |
| "layers.32.ffn.gate", |
| "layers.32.ffn.shared_experts.w1", |
| "layers.32.ffn.shared_experts.w2", |
| "layers.32.ffn.shared_experts.w3", |
| "layers.33.ffn.gate", |
| "layers.33.ffn.shared_experts.w1", |
| "layers.33.ffn.shared_experts.w2", |
| "layers.33.ffn.shared_experts.w3", |
| "layers.34.ffn.gate", |
| "layers.34.ffn.shared_experts.w1", |
| "layers.34.ffn.shared_experts.w2", |
| "layers.34.ffn.shared_experts.w3", |
| "layers.35.ffn.gate", |
| "layers.35.ffn.shared_experts.w1", |
| "layers.35.ffn.shared_experts.w2", |
| "layers.35.ffn.shared_experts.w3", |
| "layers.36.ffn.gate", |
| "layers.36.ffn.shared_experts.w1", |
| "layers.36.ffn.shared_experts.w2", |
| "layers.36.ffn.shared_experts.w3", |
| "layers.37.ffn.gate", |
| "layers.37.ffn.shared_experts.w1", |
| "layers.37.ffn.shared_experts.w2", |
| "layers.37.ffn.shared_experts.w3", |
| "layers.38.ffn.gate", |
| "layers.38.ffn.shared_experts.w1", |
| "layers.38.ffn.shared_experts.w2", |
| "layers.38.ffn.shared_experts.w3", |
| "layers.39.ffn.gate", |
| "layers.39.ffn.shared_experts.w1", |
| "layers.39.ffn.shared_experts.w2", |
| "layers.39.ffn.shared_experts.w3", |
| "layers.4.ffn.gate", |
| "layers.4.ffn.shared_experts.w1", |
| "layers.4.ffn.shared_experts.w2", |
| "layers.4.ffn.shared_experts.w3", |
| "layers.40.ffn.gate", |
| "layers.40.ffn.shared_experts.w1", |
| "layers.40.ffn.shared_experts.w2", |
| "layers.40.ffn.shared_experts.w3", |
| "layers.41.ffn.gate", |
| "layers.41.ffn.shared_experts.w1", |
| "layers.41.ffn.shared_experts.w2", |
| "layers.41.ffn.shared_experts.w3", |
| "layers.42.ffn.gate", |
| "layers.42.ffn.shared_experts.w1", |
| "layers.42.ffn.shared_experts.w2", |
| "layers.42.ffn.shared_experts.w3", |
| "layers.5.ffn.gate", |
| "layers.5.ffn.shared_experts.w1", |
| "layers.5.ffn.shared_experts.w2", |
| "layers.5.ffn.shared_experts.w3", |
| "layers.6.ffn.gate", |
| "layers.6.ffn.shared_experts.w1", |
| "layers.6.ffn.shared_experts.w2", |
| "layers.6.ffn.shared_experts.w3", |
| "layers.7.ffn.gate", |
| "layers.7.ffn.shared_experts.w1", |
| "layers.7.ffn.shared_experts.w2", |
| "layers.7.ffn.shared_experts.w3", |
| "layers.8.ffn.gate", |
| "layers.8.ffn.shared_experts.w1", |
| "layers.8.ffn.shared_experts.w2", |
| "layers.8.ffn.shared_experts.w3", |
| "layers.9.ffn.gate", |
| "layers.9.ffn.shared_experts.w1", |
| "layers.9.ffn.shared_experts.w2", |
| "layers.9.ffn.shared_experts.w3", |
| "mtp.0.ffn.gate", |
| "mtp.0.ffn.shared_experts.w1", |
| "mtp.0.ffn.shared_experts.w2", |
| "mtp.0.ffn.shared_experts.w3" |
| ], |
| "algo_config": null, |
| "softmax_quant_spec": null, |
| "quant_method": "quark", |
| "layer_type_quant_config": {}, |
| "layer_quant_config": {}, |
| "kv_cache_quant_config": {}, |
| "kv_cache_post_rope": false, |
| "quant_mode": "eager_mode", |
| "version": "0.11.1", |
| "export": { |
| "kv_cache_group": [], |
| "min_kv_scale": 0.0, |
| "pack_method": "reorder", |
| "weight_format": "real_quantized", |
| "weight_merge_groups": null |
| } |
| } |
| } |
