| { |
| "architectures": [ |
| "DeepseekV4ForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 0, |
| "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 |
| ], |
| "compress_rope_parameters": { |
| "beta_fast": 32, |
| "beta_slow": 1, |
| "factor": 16, |
| "original_max_position_embeddings": 65536, |
| "partial_rotary_factor": 0.125, |
| "rope_theta": 160000, |
| "rope_type": "yarn", |
| "type": "yarn" |
| }, |
| "compress_rope_theta": 160000, |
| "dtype": "bfloat16", |
| "eos_token_id": 1, |
| "expert_dtype": "fp4", |
| "first_k_dense_replace": null, |
| "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, |
| "kv_lora_rank": null, |
| "max_position_embeddings": 1048576, |
| "model_type": "deepseek_v4", |
| "moe_intermediate_size": 2048, |
| "n_group": null, |
| "n_routed_experts": 256, |
| "n_shared_experts": 1, |
| "norm_topk_prob": true, |
| "num_attention_heads": 64, |
| "num_experts_per_tok": 6, |
| "num_hash_layers": 3, |
| "num_hidden_layers": 43, |
| "num_key_value_heads": 1, |
| "num_nextn_predict_layers": 1, |
| "o_groups": 8, |
| "o_lora_rank": 1024, |
| "output_router_logits": false, |
| "pad_token_id": null, |
| "partial_rotary_factor": 0.125, |
| "pretraining_tp": 1, |
| "q_lora_rank": 1024, |
| "qk_nope_head_dim": 448, |
| "qk_rope_head_dim": 64, |
| "quantization_config": { |
| "config_groups": { |
| "group_0": { |
| "format": "float-quantized", |
| "input_activations": { |
| "actorder": null, |
| "block_structure": null, |
| "dynamic": true, |
| "group_size": 128, |
| "num_bits": 8, |
| "observer": null, |
| "observer_kwargs": {}, |
| "scale_dtype": null, |
| "strategy": "group", |
| "symmetric": true, |
| "type": "float", |
| "zp_dtype": null |
| }, |
| "output_activations": null, |
| "targets": [ |
| "re:.*attn.*(wgate|wkv|wo_a|wo_b|wq_a|wq_b|fused_wkv_wgate|fused_wqa_wkv|gate_up_proj)$" |
| ], |
| "weights": { |
| "actorder": null, |
| "block_structure": [ |
| 128, |
| 128 |
| ], |
| "dynamic": false, |
| "group_size": null, |
| "num_bits": 8, |
| "observer": "memoryless_minmax", |
| "observer_kwargs": {}, |
| "scale_dtype": null, |
| "strategy": "block", |
| "symmetric": true, |
| "type": "float", |
| "zp_dtype": null |
| } |
| }, |
| "group_1": { |
| "format": "nvfp4-pack-quantized", |
| "input_activations": { |
| "actorder": null, |
| "block_structure": null, |
| "dynamic": "local", |
| "group_size": 16, |
| "num_bits": 4, |
| "observer": "static_minmax", |
| "observer_kwargs": {}, |
| "scale_dtype": "torch.float8_e4m3fn", |
| "strategy": "tensor_group", |
| "symmetric": true, |
| "type": "float", |
| "zp_dtype": null |
| }, |
| "output_activations": null, |
| "targets": [ |
| "re:.*ffn.*(gate|up|down)_proj$" |
| ], |
| "weights": { |
| "actorder": null, |
| "block_structure": null, |
| "dynamic": false, |
| "group_size": 16, |
| "num_bits": 4, |
| "observer": "memoryless_minmax", |
| "observer_kwargs": {}, |
| "scale_dtype": "torch.float8_e4m3fn", |
| "strategy": "tensor_group", |
| "symmetric": true, |
| "type": "float", |
| "zp_dtype": null |
| } |
| } |
| }, |
| "format": "mixed-precision", |
| "global_compression_ratio": null, |
| "ignore": [ |
| "layers.2.attn.indexer.weights_proj", |
| "layers.4.attn.indexer.weights_proj", |
| "layers.6.attn.indexer.weights_proj", |
| "layers.8.attn.indexer.weights_proj", |
| "layers.10.attn.indexer.weights_proj", |
| "layers.12.attn.indexer.weights_proj", |
| "layers.14.attn.indexer.weights_proj", |
| "layers.16.attn.indexer.weights_proj", |
| "layers.18.attn.indexer.weights_proj", |
| "layers.20.attn.indexer.weights_proj", |
| "layers.22.attn.indexer.weights_proj", |
| "layers.24.attn.indexer.weights_proj", |
| "layers.26.attn.indexer.weights_proj", |
| "layers.28.attn.indexer.weights_proj", |
| "layers.30.attn.indexer.weights_proj", |
| "layers.32.attn.indexer.weights_proj", |
| "layers.34.attn.indexer.weights_proj", |
| "layers.36.attn.indexer.weights_proj", |
| "layers.38.attn.indexer.weights_proj", |
| "layers.40.attn.indexer.weights_proj", |
| "layers.42.attn.indexer.weights_proj", |
| "lm_head" |
| ], |
| "kv_cache_scheme": null, |
| "quant_method": "compressed-tensors", |
| "quantization_status": "compressed", |
| "sparsity_config": {}, |
| "transform_config": {}, |
| "version": "0.15.1.dev15+g11daf97.d20260427" |
| }, |
| "rms_norm_eps": 1e-06, |
| "rope_interleave": true, |
| "rope_parameters": { |
| "beta_fast": 32, |
| "beta_slow": 1, |
| "factor": 16, |
| "original_max_position_embeddings": 65536, |
| "partial_rotary_factor": 0.125, |
| "rope_theta": 10000, |
| "rope_type": "yarn", |
| "type": "yarn" |
| }, |
| "rope_theta": 10000, |
| "routed_scaling_factor": 1.5, |
| "router_aux_loss_coef": 0.001, |
| "router_jitter_noise": 0.0, |
| "scoring_func": "sqrtsoftplus", |
| "sliding_window": 128, |
| "swiglu_limit": 10.0, |
| "tie_word_embeddings": false, |
| "topk_group": null, |
| "topk_method": "noaux_tc", |
| "transformers_version": "5.7.0.dev0", |
| "use_cache": true, |
| "v_head_dim": null, |
| "vocab_size": 129280 |
| } |
|
|
