| { |
| "architectures": [ |
| "DeepseekV4ForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 0, |
| "eos_token_id": 1, |
| "expert_dtype": "fp4", |
| "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": 3, |
| "o_groups": 8, |
| "o_lora_rank": 1024, |
| "q_lora_rank": 1024, |
| "qk_rope_head_dim": 64, |
| "quantization_config": { |
| "quant_method": "exl3", |
| "version": "1.4.8", |
| "bits": 2.77, |
| "head_bits": 5, |
| "calibration": { |
| "rows": 250, |
| "cols": 2048 |
| }, |
| "out_scales": "always", |
| "codebook": "mul1", |
| "original_quantization_config": { |
| "activation_scheme": "dynamic", |
| "fmt": "e4m3", |
| "quant_method": "fp8", |
| "scale_fmt": "ue8m0", |
| "weight_block_size": [ |
| 128, |
| 128 |
| ] |
| }, |
| "vision_bits": 5, |
| "mtp_bits": 3 |
| }, |
| "rms_norm_eps": 1e-20, |
| "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": "5.0.0", |
| "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, |
| 0, |
| 0 |
| ], |
| "dspark_block_size": 5, |
| "dspark_noise_token_id": 128799, |
| "dspark_target_layer_ids": [ |
| 40, |
| 41, |
| 42 |
| ], |
| "dspark_markov_rank": 256, |
| "vision_n_layers": 32, |
| "vision_dim": 1024, |
| "vision_n_heads": 16, |
| "vision_inter_dim": 2816, |
| "vision_patch_size": 14, |
| "vision_rope_theta": 10000.0, |
| "vision_downsample_ratio": 3, |
| "vision_max_n_token": 384, |
| "vision_min_pixels": 147456, |
| "vision_max_wh_ratio": 8 |
| } |
