| { |
| "architectures": [ |
| "DeepseekV3ForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "auto_map": { |
| "AutoConfig": "configuration_deepseek.DeepseekV3Config", |
| "AutoModel": "modeling_deepseek.DeepseekV3Model", |
| "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM" |
| }, |
| "bos_token_id": 0, |
| "dtype": "bfloat16", |
| "eos_token_id": 1, |
| "ep_size": 1, |
| "first_k_dense_replace": 1, |
| "head_dim": 64, |
| "hidden_act": "silu", |
| "hidden_size": 2048, |
| "initializer_range": 0.02, |
| "intermediate_size": 7168, |
| "kv_lora_rank": 512, |
| "max_position_embeddings": 131072, |
| "model_type": "deepseek_v3", |
| "moe_intermediate_size": 768, |
| "moe_layer_freq": 1, |
| "n_group": 1, |
| "n_routed_experts": 256, |
| "n_shared_experts": 1, |
| "norm_topk_prob": true, |
| "num_attention_heads": 32, |
| "num_experts_per_tok": 8, |
| "num_hidden_layers": 40, |
| "num_key_value_heads": 32, |
| "num_nextn_predict_layers": 1, |
| "pretraining_tp": 1, |
| "q_lora_rank": 1536, |
| "qk_head_dim": 192, |
| "qk_nope_head_dim": 128, |
| "qk_rope_head_dim": 64, |
| "quantization_config": { |
| "config_groups": { |
| "group_0": { |
| "format": "pack-quantized", |
| "input_activations": null, |
| "output_activations": null, |
| "targets": [ |
| "Linear" |
| ], |
| "weights": { |
| "actorder": null, |
| "block_structure": null, |
| "dynamic": false, |
| "group_size": 32, |
| "num_bits": 8, |
| "observer": "mse", |
| "observer_kwargs": {}, |
| "scale_dtype": null, |
| "strategy": "group", |
| "symmetric": true, |
| "type": "int", |
| "zp_dtype": null |
| } |
| } |
| }, |
| "format": "pack-quantized", |
| "global_compression_ratio": null, |
| "ignore": [ |
| "model.layers.0.self_attn.q_a_proj", |
| "model.layers.0.self_attn.q_b_proj", |
| "model.layers.0.self_attn.kv_a_proj_with_mqa", |
| "model.layers.0.self_attn.kv_b_proj", |
| "model.layers.0.self_attn.o_proj", |
| "model.layers.0.mlp.gate_proj", |
| "model.layers.0.mlp.up_proj", |
| "model.layers.0.mlp.down_proj", |
| "model.layers.1.mlp.shared_experts.gate_proj", |
| "model.layers.1.mlp.shared_experts.up_proj", |
| "model.layers.1.mlp.shared_experts.down_proj", |
| "model.layers.2.mlp.shared_experts.gate_proj", |
| "model.layers.2.mlp.shared_experts.up_proj", |
| "model.layers.2.mlp.shared_experts.down_proj", |
| "model.layers.3.mlp.shared_experts.gate_proj", |
| "model.layers.3.mlp.shared_experts.up_proj", |
| "model.layers.3.mlp.shared_experts.down_proj", |
| "model.layers.4.mlp.shared_experts.gate_proj", |
| "model.layers.4.mlp.shared_experts.up_proj", |
| "model.layers.4.mlp.shared_experts.down_proj", |
| "model.layers.5.mlp.shared_experts.gate_proj", |
| "model.layers.5.mlp.shared_experts.up_proj", |
| "model.layers.5.mlp.shared_experts.down_proj", |
| "model.layers.6.mlp.shared_experts.gate_proj", |
| "model.layers.6.mlp.shared_experts.up_proj", |
| "model.layers.6.mlp.shared_experts.down_proj", |
| "model.layers.7.mlp.shared_experts.gate_proj", |
| "model.layers.7.mlp.shared_experts.up_proj", |
| "model.layers.7.mlp.shared_experts.down_proj", |
| "model.layers.8.mlp.shared_experts.gate_proj", |
| "model.layers.8.mlp.shared_experts.up_proj", |
| "model.layers.8.mlp.shared_experts.down_proj", |
| "model.layers.9.mlp.shared_experts.gate_proj", |
| "model.layers.9.mlp.shared_experts.up_proj", |
| "model.layers.9.mlp.shared_experts.down_proj", |
| "model.layers.10.mlp.shared_experts.gate_proj", |
| "model.layers.10.mlp.shared_experts.up_proj", |
| "model.layers.10.mlp.shared_experts.down_proj", |
| "model.layers.11.mlp.shared_experts.gate_proj", |
| "model.layers.11.mlp.shared_experts.up_proj", |
| "model.layers.11.mlp.shared_experts.down_proj", |
| "model.layers.12.mlp.shared_experts.gate_proj", |
| "model.layers.12.mlp.shared_experts.up_proj", |
| "model.layers.12.mlp.shared_experts.down_proj", |
| "model.layers.13.mlp.shared_experts.gate_proj", |
| "model.layers.13.mlp.shared_experts.up_proj", |
| "model.layers.13.mlp.shared_experts.down_proj", |
| "model.layers.14.mlp.shared_experts.gate_proj", |
| "model.layers.14.mlp.shared_experts.up_proj", |
| "model.layers.14.mlp.shared_experts.down_proj", |
| "model.layers.15.mlp.shared_experts.gate_proj", |
| "model.layers.15.mlp.shared_experts.up_proj", |
| "model.layers.15.mlp.shared_experts.down_proj", |
| "model.layers.16.mlp.shared_experts.gate_proj", |
| "model.layers.16.mlp.shared_experts.up_proj", |
| "model.layers.16.mlp.shared_experts.down_proj", |
| "model.layers.17.mlp.shared_experts.gate_proj", |
| "model.layers.17.mlp.shared_experts.up_proj", |
| "model.layers.17.mlp.shared_experts.down_proj", |
| "model.layers.18.mlp.shared_experts.gate_proj", |
| "model.layers.18.mlp.shared_experts.up_proj", |
| "model.layers.18.mlp.shared_experts.down_proj", |
| "model.layers.19.mlp.shared_experts.gate_proj", |
| "model.layers.19.mlp.shared_experts.up_proj", |
| "model.layers.19.mlp.shared_experts.down_proj", |
| "model.layers.20.mlp.shared_experts.gate_proj", |
| "model.layers.20.mlp.shared_experts.up_proj", |
| "model.layers.20.mlp.shared_experts.down_proj", |
| "model.layers.21.mlp.shared_experts.gate_proj", |
| "model.layers.21.mlp.shared_experts.up_proj", |
| "model.layers.21.mlp.shared_experts.down_proj", |
| "model.layers.22.mlp.shared_experts.gate_proj", |
| "model.layers.22.mlp.shared_experts.up_proj", |
| "model.layers.22.mlp.shared_experts.down_proj", |
| "model.layers.23.mlp.shared_experts.gate_proj", |
| "model.layers.23.mlp.shared_experts.up_proj", |
| "model.layers.23.mlp.shared_experts.down_proj", |
| "model.layers.24.mlp.shared_experts.gate_proj", |
| "model.layers.24.mlp.shared_experts.up_proj", |
| "model.layers.24.mlp.shared_experts.down_proj", |
| "model.layers.25.mlp.shared_experts.gate_proj", |
| "model.layers.25.mlp.shared_experts.up_proj", |
| "model.layers.25.mlp.shared_experts.down_proj", |
| "model.layers.26.mlp.shared_experts.gate_proj", |
| "model.layers.26.mlp.shared_experts.up_proj", |
| "model.layers.26.mlp.shared_experts.down_proj", |
| "model.layers.27.mlp.shared_experts.gate_proj", |
| "model.layers.27.mlp.shared_experts.up_proj", |
| "model.layers.27.mlp.shared_experts.down_proj", |
| "model.layers.28.mlp.shared_experts.gate_proj", |
| "model.layers.28.mlp.shared_experts.up_proj", |
| "model.layers.28.mlp.shared_experts.down_proj", |
| "model.layers.29.mlp.shared_experts.gate_proj", |
| "model.layers.29.mlp.shared_experts.up_proj", |
| "model.layers.29.mlp.shared_experts.down_proj", |
| "model.layers.30.mlp.shared_experts.gate_proj", |
| "model.layers.30.mlp.shared_experts.up_proj", |
| "model.layers.30.mlp.shared_experts.down_proj", |
| "model.layers.31.mlp.shared_experts.gate_proj", |
| "model.layers.31.mlp.shared_experts.up_proj", |
| "model.layers.31.mlp.shared_experts.down_proj", |
| "model.layers.32.mlp.shared_experts.gate_proj", |
| "model.layers.32.mlp.shared_experts.up_proj", |
| "model.layers.32.mlp.shared_experts.down_proj", |
| "model.layers.33.mlp.shared_experts.gate_proj", |
| "model.layers.33.mlp.shared_experts.up_proj", |
| "model.layers.33.mlp.shared_experts.down_proj", |
| "model.layers.34.mlp.shared_experts.gate_proj", |
| "model.layers.34.mlp.shared_experts.up_proj", |
| "model.layers.34.mlp.shared_experts.down_proj", |
| "model.layers.35.mlp.shared_experts.gate_proj", |
| "model.layers.35.mlp.shared_experts.up_proj", |
| "model.layers.35.mlp.shared_experts.down_proj", |
| "model.layers.36.mlp.shared_experts.gate_proj", |
| "model.layers.36.mlp.shared_experts.up_proj", |
| "model.layers.36.mlp.shared_experts.down_proj", |
| "model.layers.37.mlp.shared_experts.gate_proj", |
| "model.layers.37.mlp.shared_experts.up_proj", |
| "model.layers.37.mlp.shared_experts.down_proj", |
| "model.layers.38.mlp.shared_experts.gate_proj", |
| "model.layers.38.mlp.shared_experts.up_proj", |
| "model.layers.38.mlp.shared_experts.down_proj", |
| "model.layers.39.mlp.shared_experts.gate_proj", |
| "model.layers.39.mlp.shared_experts.up_proj", |
| "model.layers.39.mlp.shared_experts.down_proj", |
| "lm_head" |
| ], |
| "kv_cache_scheme": null, |
| "quant_method": "compressed-tensors", |
| "quantization_status": "compressed", |
| "sparsity_config": {}, |
| "transform_config": {}, |
| "version": "0.13.1.a20260218" |
| }, |
| "rms_norm_eps": 1e-06, |
| "rope_interleave": true, |
| "rope_scaling": null, |
| "rope_theta": 32000000, |
| "routed_scaling_factor": 2.5, |
| "scoring_func": "sigmoid", |
| "tie_word_embeddings": false, |
| "topk_group": 1, |
| "topk_method": "noaux_tc", |
| "transformers_version": "4.57.6", |
| "use_cache": true, |
| "v_head_dim": 128, |
| "vocab_size": 129280 |
| } |
