{ "architectures": [ "DeepseekV4ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 0, "compress_rates": { "compressed_sparse_attention": 4, "heavily_compressed_attention": 128 }, "compress_rope_theta": 160000, "dtype": "bfloat16", "eos_token_id": 1, "expert_dtype": "bf16", "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, "layer_types": [ "sliding_attention", "sliding_attention", "compressed_sparse_attention", "heavily_compressed_attention", "compressed_sparse_attention", "heavily_compressed_attention", "compressed_sparse_attention", "heavily_compressed_attention", "compressed_sparse_attention", "heavily_compressed_attention", "compressed_sparse_attention", "heavily_compressed_attention", "compressed_sparse_attention", "heavily_compressed_attention", "compressed_sparse_attention", "heavily_compressed_attention", "compressed_sparse_attention", "heavily_compressed_attention", "compressed_sparse_attention", "heavily_compressed_attention", "compressed_sparse_attention", "heavily_compressed_attention", "compressed_sparse_attention", "heavily_compressed_attention", "compressed_sparse_attention", "heavily_compressed_attention", "compressed_sparse_attention", "heavily_compressed_attention", "compressed_sparse_attention", "heavily_compressed_attention", "compressed_sparse_attention", "heavily_compressed_attention", "compressed_sparse_attention", "heavily_compressed_attention", "compressed_sparse_attention", "heavily_compressed_attention", "compressed_sparse_attention", "heavily_compressed_attention", "compressed_sparse_attention", "heavily_compressed_attention", "compressed_sparse_attention", "heavily_compressed_attention", "compressed_sparse_attention" ], "max_position_embeddings": 1048576, "mlp_bias": false, "mlp_layer_types": [ "hash_moe", "hash_moe", "hash_moe", "moe", "moe", "moe", "moe", "moe", "moe", "moe", "moe", "moe", "moe", "moe", "moe", "moe", "moe", "moe", "moe", "moe", "moe", "moe", "moe", "moe", "moe", "moe", "moe", "moe", "moe", "moe", "moe", "moe", "moe", "moe", "moe", "moe", "moe", "moe", "moe", "moe", "moe", "moe", "moe" ], "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_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, "q_lora_rank": 1024, "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\\.(wq_a|wq_b|wkv|wo_a|wo_b|fused_wqa_wkv|q_a_proj|q_b_proj|kv_proj|o_a_proj|o_b_proj)$" ], "weights": { "actorder": null, "block_structure": [ 128, 128 ], "dynamic": false, "group_size": null, "num_bits": 8, "observer": "memoryless_minmax", "observer_kwargs": {}, "scale_dtype": null, "strategy": "block", "symmetric": true, "type": "float", "zp_dtype": null } }, "group_1": { "format": "pack-quantized", "input_activations": { "num_bits": 8, "type": "float", "strategy": "token", "dynamic": true, "symmetric": true, "group_size": null, "block_structure": null, "actorder": null, "observer": null, "observer_kwargs": {}, "scale_dtype": null, "zp_dtype": null }, "output_activations": null, "targets": [ "re:.*experts\\.\\d+\\.(w1|w2|w3|gate_proj|up_proj|down_proj|gate_up_proj)$" ], "weights": { "actorder": "static", "block_structure": null, "dynamic": false, "group_size": 128, "num_bits": 4, "observer": "memoryless_minmax", "observer_kwargs": {}, "scale_dtype": null, "strategy": "group", "symmetric": true, "type": "int", "zp_dtype": null } } }, "format": "mixed-precision", "global_compression_ratio": null, "ignore": [ "layers.0.ffn.shared_experts.w1", "layers.0.ffn.shared_experts.w2", "layers.0.ffn.shared_experts.w3", "layers.1.ffn.shared_experts.w1", "layers.1.ffn.shared_experts.w2", "layers.1.ffn.shared_experts.w3", "layers.2.ffn.shared_experts.w1", "layers.2.ffn.shared_experts.w2", "layers.2.ffn.shared_experts.w3", "layers.3.ffn.shared_experts.w1", "layers.3.ffn.shared_experts.w2", "layers.3.ffn.shared_experts.w3", "layers.4.ffn.shared_experts.w1", "layers.4.ffn.shared_experts.w2", "layers.4.ffn.shared_experts.w3", "layers.5.ffn.shared_experts.w1", "layers.5.ffn.shared_experts.w2", "layers.5.ffn.shared_experts.w3", "layers.6.ffn.shared_experts.w1", "layers.6.ffn.shared_experts.w2", "layers.6.ffn.shared_experts.w3", "layers.7.ffn.shared_experts.w1", "layers.7.ffn.shared_experts.w2", "layers.7.ffn.shared_experts.w3", "layers.8.ffn.shared_experts.w1", "layers.8.ffn.shared_experts.w2", "layers.8.ffn.shared_experts.w3", "layers.9.ffn.shared_experts.w1", "layers.9.ffn.shared_experts.w2", "layers.9.ffn.shared_experts.w3", "layers.10.ffn.shared_experts.w1", "layers.10.ffn.shared_experts.w2", "layers.10.ffn.shared_experts.w3", "layers.11.ffn.shared_experts.w1", "layers.11.ffn.shared_experts.w2", "layers.11.ffn.shared_experts.w3", "layers.12.ffn.shared_experts.w1", "layers.12.ffn.shared_experts.w2", "layers.12.ffn.shared_experts.w3", "layers.13.ffn.shared_experts.w1", "layers.13.ffn.shared_experts.w2", "layers.13.ffn.shared_experts.w3", "layers.14.ffn.shared_experts.w1", "layers.14.ffn.shared_experts.w2", "layers.14.ffn.shared_experts.w3", "layers.15.ffn.shared_experts.w1", "layers.15.ffn.shared_experts.w2", "layers.15.ffn.shared_experts.w3", "layers.16.ffn.shared_experts.w1", "layers.16.ffn.shared_experts.w2", "layers.16.ffn.shared_experts.w3", "layers.17.ffn.shared_experts.w1", "layers.17.ffn.shared_experts.w2", "layers.17.ffn.shared_experts.w3", "layers.18.ffn.shared_experts.w1", "layers.18.ffn.shared_experts.w2", "layers.18.ffn.shared_experts.w3", "layers.19.ffn.shared_experts.w1", "layers.19.ffn.shared_experts.w2", "layers.19.ffn.shared_experts.w3", "layers.20.ffn.shared_experts.w1", "layers.20.ffn.shared_experts.w2", "layers.20.ffn.shared_experts.w3", "layers.21.ffn.shared_experts.w1", "layers.21.ffn.shared_experts.w2", "layers.21.ffn.shared_experts.w3", "layers.22.ffn.shared_experts.w1", "layers.22.ffn.shared_experts.w2", "layers.22.ffn.shared_experts.w3", "layers.23.ffn.shared_experts.w1", "layers.23.ffn.shared_experts.w2", "layers.23.ffn.shared_experts.w3", "layers.24.ffn.shared_experts.w1", "layers.24.ffn.shared_experts.w2", "layers.24.ffn.shared_experts.w3", "layers.25.ffn.shared_experts.w1", "layers.25.ffn.shared_experts.w2", "layers.25.ffn.shared_experts.w3", "layers.26.ffn.shared_experts.w1", "layers.26.ffn.shared_experts.w2", "layers.26.ffn.shared_experts.w3", "layers.27.ffn.shared_experts.w1", "layers.27.ffn.shared_experts.w2", "layers.27.ffn.shared_experts.w3", "layers.28.ffn.shared_experts.w1", "layers.28.ffn.shared_experts.w2", "layers.28.ffn.shared_experts.w3", "layers.29.ffn.shared_experts.w1", "layers.29.ffn.shared_experts.w2", "layers.29.ffn.shared_experts.w3", "layers.30.ffn.shared_experts.w1", "layers.30.ffn.shared_experts.w2", "layers.30.ffn.shared_experts.w3", "layers.31.ffn.shared_experts.w1", "layers.31.ffn.shared_experts.w2", "layers.31.ffn.shared_experts.w3", "layers.32.ffn.shared_experts.w1", "layers.32.ffn.shared_experts.w2", "layers.32.ffn.shared_experts.w3", "layers.33.ffn.shared_experts.w1", "layers.33.ffn.shared_experts.w2", "layers.33.ffn.shared_experts.w3", "layers.34.ffn.shared_experts.w1", "layers.34.ffn.shared_experts.w2", "layers.34.ffn.shared_experts.w3", "layers.35.ffn.shared_experts.w1", "layers.35.ffn.shared_experts.w2", "layers.35.ffn.shared_experts.w3", "layers.36.ffn.shared_experts.w1", "layers.36.ffn.shared_experts.w2", "layers.36.ffn.shared_experts.w3", "layers.37.ffn.shared_experts.w1", "layers.37.ffn.shared_experts.w2", "layers.37.ffn.shared_experts.w3", "layers.38.ffn.shared_experts.w1", "layers.38.ffn.shared_experts.w2", "layers.38.ffn.shared_experts.w3", "layers.39.ffn.shared_experts.w1", "layers.39.ffn.shared_experts.w2", "layers.39.ffn.shared_experts.w3", "layers.40.ffn.shared_experts.w1", "layers.40.ffn.shared_experts.w2", "layers.40.ffn.shared_experts.w3", "layers.41.ffn.shared_experts.w1", "layers.41.ffn.shared_experts.w2", "layers.41.ffn.shared_experts.w3", "layers.42.ffn.shared_experts.w1", "layers.42.ffn.shared_experts.w2", "layers.42.ffn.shared_experts.w3", "re:^layers\\.43\\.", "re:^model\\.layers\\.43\\.", "lm_head", "layers.0.attn.compressor.wgate", "layers.0.attn.compressor.wkv", "layers.0.attn.compressor.fused_wkv_wgate", "layers.0.attn.compressor.gate_proj", "layers.0.attn.compressor.kv_proj", "layers.0.attn.indexer.weights_proj", "layers.0.attn.indexer.wq_b", "layers.0.attn.indexer.q_b_proj", "layers.0.attn.indexer.compressor.wgate", "layers.0.attn.indexer.compressor.wkv", "layers.0.attn.indexer.compressor.gate_proj", "layers.0.attn.indexer.compressor.kv_proj", "layers.1.attn.compressor.wgate", "layers.1.attn.compressor.wkv", "layers.1.attn.compressor.fused_wkv_wgate", "layers.1.attn.compressor.gate_proj", "layers.1.attn.compressor.kv_proj", "layers.1.attn.indexer.weights_proj", "layers.1.attn.indexer.wq_b", "layers.1.attn.indexer.q_b_proj", "layers.1.attn.indexer.compressor.wgate", "layers.1.attn.indexer.compressor.wkv", "layers.1.attn.indexer.compressor.gate_proj", "layers.1.attn.indexer.compressor.kv_proj", "layers.2.attn.compressor.wgate", "layers.2.attn.compressor.wkv", "layers.2.attn.compressor.fused_wkv_wgate", "layers.2.attn.compressor.gate_proj", "layers.2.attn.compressor.kv_proj", "layers.2.attn.indexer.weights_proj", "layers.2.attn.indexer.wq_b", "layers.2.attn.indexer.q_b_proj", "layers.2.attn.indexer.compressor.wgate", "layers.2.attn.indexer.compressor.wkv", "layers.2.attn.indexer.compressor.gate_proj", "layers.2.attn.indexer.compressor.kv_proj", "layers.3.attn.compressor.wgate", "layers.3.attn.compressor.wkv", "layers.3.attn.compressor.fused_wkv_wgate", "layers.3.attn.compressor.gate_proj", "layers.3.attn.compressor.kv_proj", "layers.3.attn.indexer.weights_proj", "layers.3.attn.indexer.wq_b", "layers.3.attn.indexer.q_b_proj", "layers.3.attn.indexer.compressor.wgate", "layers.3.attn.indexer.compressor.wkv", "layers.3.attn.indexer.compressor.gate_proj", "layers.3.attn.indexer.compressor.kv_proj", "layers.4.attn.compressor.wgate", "layers.4.attn.compressor.wkv", "layers.4.attn.compressor.fused_wkv_wgate", "layers.4.attn.compressor.gate_proj", "layers.4.attn.compressor.kv_proj", "layers.4.attn.indexer.weights_proj", "layers.4.attn.indexer.wq_b", "layers.4.attn.indexer.q_b_proj", "layers.4.attn.indexer.compressor.wgate", "layers.4.attn.indexer.compressor.wkv", "layers.4.attn.indexer.compressor.gate_proj", "layers.4.attn.indexer.compressor.kv_proj", "layers.5.attn.compressor.wgate", "layers.5.attn.compressor.wkv", "layers.5.attn.compressor.fused_wkv_wgate", "layers.5.attn.compressor.gate_proj", "layers.5.attn.compressor.kv_proj", "layers.5.attn.indexer.weights_proj", "layers.5.attn.indexer.wq_b", "layers.5.attn.indexer.q_b_proj", "layers.5.attn.indexer.compressor.wgate", "layers.5.attn.indexer.compressor.wkv", "layers.5.attn.indexer.compressor.gate_proj", "layers.5.attn.indexer.compressor.kv_proj", "layers.6.attn.compressor.wgate", "layers.6.attn.compressor.wkv", "layers.6.attn.compressor.fused_wkv_wgate", "layers.6.attn.compressor.gate_proj", "layers.6.attn.compressor.kv_proj", "layers.6.attn.indexer.weights_proj", "layers.6.attn.indexer.wq_b", "layers.6.attn.indexer.q_b_proj", "layers.6.attn.indexer.compressor.wgate", "layers.6.attn.indexer.compressor.wkv", "layers.6.attn.indexer.compressor.gate_proj", "layers.6.attn.indexer.compressor.kv_proj", "layers.7.attn.compressor.wgate", "layers.7.attn.compressor.wkv", "layers.7.attn.compressor.fused_wkv_wgate", "layers.7.attn.compressor.gate_proj", "layers.7.attn.compressor.kv_proj", "layers.7.attn.indexer.weights_proj", "layers.7.attn.indexer.wq_b", "layers.7.attn.indexer.q_b_proj", "layers.7.attn.indexer.compressor.wgate", "layers.7.attn.indexer.compressor.wkv", "layers.7.attn.indexer.compressor.gate_proj", "layers.7.attn.indexer.compressor.kv_proj", "layers.8.attn.compressor.wgate", "layers.8.attn.compressor.wkv", "layers.8.attn.compressor.fused_wkv_wgate", "layers.8.attn.compressor.gate_proj", "layers.8.attn.compressor.kv_proj", "layers.8.attn.indexer.weights_proj", "layers.8.attn.indexer.wq_b", "layers.8.attn.indexer.q_b_proj", "layers.8.attn.indexer.compressor.wgate", "layers.8.attn.indexer.compressor.wkv", "layers.8.attn.indexer.compressor.gate_proj", "layers.8.attn.indexer.compressor.kv_proj", "layers.9.attn.compressor.wgate", "layers.9.attn.compressor.wkv", "layers.9.attn.compressor.fused_wkv_wgate", "layers.9.attn.compressor.gate_proj", "layers.9.attn.compressor.kv_proj", "layers.9.attn.indexer.weights_proj", "layers.9.attn.indexer.wq_b", "layers.9.attn.indexer.q_b_proj", "layers.9.attn.indexer.compressor.wgate", "layers.9.attn.indexer.compressor.wkv", "layers.9.attn.indexer.compressor.gate_proj", "layers.9.attn.indexer.compressor.kv_proj", "layers.10.attn.compressor.wgate", "layers.10.attn.compressor.wkv", "layers.10.attn.compressor.fused_wkv_wgate", "layers.10.attn.compressor.gate_proj", "layers.10.attn.compressor.kv_proj", "layers.10.attn.indexer.weights_proj", "layers.10.attn.indexer.wq_b", "layers.10.attn.indexer.q_b_proj", "layers.10.attn.indexer.compressor.wgate", "layers.10.attn.indexer.compressor.wkv", "layers.10.attn.indexer.compressor.gate_proj", "layers.10.attn.indexer.compressor.kv_proj", "layers.11.attn.compressor.wgate", "layers.11.attn.compressor.wkv", "layers.11.attn.compressor.fused_wkv_wgate", "layers.11.attn.compressor.gate_proj", "layers.11.attn.compressor.kv_proj", "layers.11.attn.indexer.weights_proj", "layers.11.attn.indexer.wq_b", "layers.11.attn.indexer.q_b_proj", "layers.11.attn.indexer.compressor.wgate", "layers.11.attn.indexer.compressor.wkv", "layers.11.attn.indexer.compressor.gate_proj", "layers.11.attn.indexer.compressor.kv_proj", "layers.12.attn.compressor.wgate", "layers.12.attn.compressor.wkv", "layers.12.attn.compressor.fused_wkv_wgate", "layers.12.attn.compressor.gate_proj", "layers.12.attn.compressor.kv_proj", "layers.12.attn.indexer.weights_proj", "layers.12.attn.indexer.wq_b", "layers.12.attn.indexer.q_b_proj", "layers.12.attn.indexer.compressor.wgate", "layers.12.attn.indexer.compressor.wkv", "layers.12.attn.indexer.compressor.gate_proj", "layers.12.attn.indexer.compressor.kv_proj", "layers.13.attn.compressor.wgate", "layers.13.attn.compressor.wkv", "layers.13.attn.compressor.fused_wkv_wgate", "layers.13.attn.compressor.gate_proj", "layers.13.attn.compressor.kv_proj", "layers.13.attn.indexer.weights_proj", "layers.13.attn.indexer.wq_b", "layers.13.attn.indexer.q_b_proj", "layers.13.attn.indexer.compressor.wgate", "layers.13.attn.indexer.compressor.wkv", "layers.13.attn.indexer.compressor.gate_proj", "layers.13.attn.indexer.compressor.kv_proj", "layers.14.attn.compressor.wgate", "layers.14.attn.compressor.wkv", "layers.14.attn.compressor.fused_wkv_wgate", "layers.14.attn.compressor.gate_proj", "layers.14.attn.compressor.kv_proj", "layers.14.attn.indexer.weights_proj", "layers.14.attn.indexer.wq_b", "layers.14.attn.indexer.q_b_proj", "layers.14.attn.indexer.compressor.wgate", "layers.14.attn.indexer.compressor.wkv", "layers.14.attn.indexer.compressor.gate_proj", "layers.14.attn.indexer.compressor.kv_proj", "layers.15.attn.compressor.wgate", "layers.15.attn.compressor.wkv", "layers.15.attn.compressor.fused_wkv_wgate", "layers.15.attn.compressor.gate_proj", "layers.15.attn.compressor.kv_proj", "layers.15.attn.indexer.weights_proj", "layers.15.attn.indexer.wq_b", "layers.15.attn.indexer.q_b_proj", "layers.15.attn.indexer.compressor.wgate", "layers.15.attn.indexer.compressor.wkv", "layers.15.attn.indexer.compressor.gate_proj", "layers.15.attn.indexer.compressor.kv_proj", "layers.16.attn.compressor.wgate", "layers.16.attn.compressor.wkv", "layers.16.attn.compressor.fused_wkv_wgate", "layers.16.attn.compressor.gate_proj", "layers.16.attn.compressor.kv_proj", "layers.16.attn.indexer.weights_proj", "layers.16.attn.indexer.wq_b", "layers.16.attn.indexer.q_b_proj", "layers.16.attn.indexer.compressor.wgate", "layers.16.attn.indexer.compressor.wkv", "layers.16.attn.indexer.compressor.gate_proj", "layers.16.attn.indexer.compressor.kv_proj", "layers.17.attn.compressor.wgate", "layers.17.attn.compressor.wkv", "layers.17.attn.compressor.fused_wkv_wgate", "layers.17.attn.compressor.gate_proj", "layers.17.attn.compressor.kv_proj", "layers.17.attn.indexer.weights_proj", "layers.17.attn.indexer.wq_b", "layers.17.attn.indexer.q_b_proj", "layers.17.attn.indexer.compressor.wgate", "layers.17.attn.indexer.compressor.wkv", "layers.17.attn.indexer.compressor.gate_proj", "layers.17.attn.indexer.compressor.kv_proj", "layers.18.attn.compressor.wgate", "layers.18.attn.compressor.wkv", "layers.18.attn.compressor.fused_wkv_wgate", "layers.18.attn.compressor.gate_proj", "layers.18.attn.compressor.kv_proj", "layers.18.attn.indexer.weights_proj", "layers.18.attn.indexer.wq_b", "layers.18.attn.indexer.q_b_proj", "layers.18.attn.indexer.compressor.wgate", "layers.18.attn.indexer.compressor.wkv", "layers.18.attn.indexer.compressor.gate_proj", "layers.18.attn.indexer.compressor.kv_proj", "layers.19.attn.compressor.wgate", "layers.19.attn.compressor.wkv", "layers.19.attn.compressor.fused_wkv_wgate", "layers.19.attn.compressor.gate_proj", "layers.19.attn.compressor.kv_proj", "layers.19.attn.indexer.weights_proj", "layers.19.attn.indexer.wq_b", "layers.19.attn.indexer.q_b_proj", "layers.19.attn.indexer.compressor.wgate", "layers.19.attn.indexer.compressor.wkv", "layers.19.attn.indexer.compressor.gate_proj", "layers.19.attn.indexer.compressor.kv_proj", "layers.20.attn.compressor.wgate", "layers.20.attn.compressor.wkv", "layers.20.attn.compressor.fused_wkv_wgate", "layers.20.attn.compressor.gate_proj", "layers.20.attn.compressor.kv_proj", "layers.20.attn.indexer.weights_proj", "layers.20.attn.indexer.wq_b", "layers.20.attn.indexer.q_b_proj", "layers.20.attn.indexer.compressor.wgate", "layers.20.attn.indexer.compressor.wkv", "layers.20.attn.indexer.compressor.gate_proj", "layers.20.attn.indexer.compressor.kv_proj", "layers.21.attn.compressor.wgate", "layers.21.attn.compressor.wkv", "layers.21.attn.compressor.fused_wkv_wgate", "layers.21.attn.compressor.gate_proj", "layers.21.attn.compressor.kv_proj", "layers.21.attn.indexer.weights_proj", "layers.21.attn.indexer.wq_b", "layers.21.attn.indexer.q_b_proj", "layers.21.attn.indexer.compressor.wgate", "layers.21.attn.indexer.compressor.wkv", "layers.21.attn.indexer.compressor.gate_proj", "layers.21.attn.indexer.compressor.kv_proj", "layers.22.attn.compressor.wgate", "layers.22.attn.compressor.wkv", "layers.22.attn.compressor.fused_wkv_wgate", "layers.22.attn.compressor.gate_proj", "layers.22.attn.compressor.kv_proj", "layers.22.attn.indexer.weights_proj", "layers.22.attn.indexer.wq_b", "layers.22.attn.indexer.q_b_proj", "layers.22.attn.indexer.compressor.wgate", "layers.22.attn.indexer.compressor.wkv", "layers.22.attn.indexer.compressor.gate_proj", "layers.22.attn.indexer.compressor.kv_proj", "layers.23.attn.compressor.wgate", "layers.23.attn.compressor.wkv", "layers.23.attn.compressor.fused_wkv_wgate", "layers.23.attn.compressor.gate_proj", "layers.23.attn.compressor.kv_proj", "layers.23.attn.indexer.weights_proj", "layers.23.attn.indexer.wq_b", "layers.23.attn.indexer.q_b_proj", "layers.23.attn.indexer.compressor.wgate", "layers.23.attn.indexer.compressor.wkv", "layers.23.attn.indexer.compressor.gate_proj", "layers.23.attn.indexer.compressor.kv_proj", "layers.24.attn.compressor.wgate", "layers.24.attn.compressor.wkv", "layers.24.attn.compressor.fused_wkv_wgate", "layers.24.attn.compressor.gate_proj", "layers.24.attn.compressor.kv_proj", "layers.24.attn.indexer.weights_proj", "layers.24.attn.indexer.wq_b", "layers.24.attn.indexer.q_b_proj", "layers.24.attn.indexer.compressor.wgate", "layers.24.attn.indexer.compressor.wkv", "layers.24.attn.indexer.compressor.gate_proj", "layers.24.attn.indexer.compressor.kv_proj", "layers.25.attn.compressor.wgate", "layers.25.attn.compressor.wkv", "layers.25.attn.compressor.fused_wkv_wgate", "layers.25.attn.compressor.gate_proj", "layers.25.attn.compressor.kv_proj", "layers.25.attn.indexer.weights_proj", "layers.25.attn.indexer.wq_b", "layers.25.attn.indexer.q_b_proj", "layers.25.attn.indexer.compressor.wgate", "layers.25.attn.indexer.compressor.wkv", "layers.25.attn.indexer.compressor.gate_proj", "layers.25.attn.indexer.compressor.kv_proj", "layers.26.attn.compressor.wgate", "layers.26.attn.compressor.wkv", "layers.26.attn.compressor.fused_wkv_wgate", "layers.26.attn.compressor.gate_proj", "layers.26.attn.compressor.kv_proj", "layers.26.attn.indexer.weights_proj", "layers.26.attn.indexer.wq_b", "layers.26.attn.indexer.q_b_proj", "layers.26.attn.indexer.compressor.wgate", "layers.26.attn.indexer.compressor.wkv", "layers.26.attn.indexer.compressor.gate_proj", "layers.26.attn.indexer.compressor.kv_proj", "layers.27.attn.compressor.wgate", "layers.27.attn.compressor.wkv", "layers.27.attn.compressor.fused_wkv_wgate", "layers.27.attn.compressor.gate_proj", "layers.27.attn.compressor.kv_proj", "layers.27.attn.indexer.weights_proj", "layers.27.attn.indexer.wq_b", "layers.27.attn.indexer.q_b_proj", "layers.27.attn.indexer.compressor.wgate", "layers.27.attn.indexer.compressor.wkv", "layers.27.attn.indexer.compressor.gate_proj", "layers.27.attn.indexer.compressor.kv_proj", "layers.28.attn.compressor.wgate", "layers.28.attn.compressor.wkv", "layers.28.attn.compressor.fused_wkv_wgate", "layers.28.attn.compressor.gate_proj", "layers.28.attn.compressor.kv_proj", "layers.28.attn.indexer.weights_proj", "layers.28.attn.indexer.wq_b", "layers.28.attn.indexer.q_b_proj", "layers.28.attn.indexer.compressor.wgate", "layers.28.attn.indexer.compressor.wkv", "layers.28.attn.indexer.compressor.gate_proj", "layers.28.attn.indexer.compressor.kv_proj", "layers.29.attn.compressor.wgate", "layers.29.attn.compressor.wkv", "layers.29.attn.compressor.fused_wkv_wgate", "layers.29.attn.compressor.gate_proj", "layers.29.attn.compressor.kv_proj", "layers.29.attn.indexer.weights_proj", "layers.29.attn.indexer.wq_b", "layers.29.attn.indexer.q_b_proj", "layers.29.attn.indexer.compressor.wgate", "layers.29.attn.indexer.compressor.wkv", "layers.29.attn.indexer.compressor.gate_proj", "layers.29.attn.indexer.compressor.kv_proj", "layers.30.attn.compressor.wgate", "layers.30.attn.compressor.wkv", "layers.30.attn.compressor.fused_wkv_wgate", "layers.30.attn.compressor.gate_proj", "layers.30.attn.compressor.kv_proj", "layers.30.attn.indexer.weights_proj", "layers.30.attn.indexer.wq_b", "layers.30.attn.indexer.q_b_proj", "layers.30.attn.indexer.compressor.wgate", "layers.30.attn.indexer.compressor.wkv", "layers.30.attn.indexer.compressor.gate_proj", "layers.30.attn.indexer.compressor.kv_proj", "layers.31.attn.compressor.wgate", "layers.31.attn.compressor.wkv", "layers.31.attn.compressor.fused_wkv_wgate", "layers.31.attn.compressor.gate_proj", "layers.31.attn.compressor.kv_proj", "layers.31.attn.indexer.weights_proj", "layers.31.attn.indexer.wq_b", "layers.31.attn.indexer.q_b_proj", "layers.31.attn.indexer.compressor.wgate", "layers.31.attn.indexer.compressor.wkv", "layers.31.attn.indexer.compressor.gate_proj", "layers.31.attn.indexer.compressor.kv_proj", "layers.32.attn.compressor.wgate", "layers.32.attn.compressor.wkv", "layers.32.attn.compressor.fused_wkv_wgate", "layers.32.attn.compressor.gate_proj", "layers.32.attn.compressor.kv_proj", "layers.32.attn.indexer.weights_proj", "layers.32.attn.indexer.wq_b", "layers.32.attn.indexer.q_b_proj", "layers.32.attn.indexer.compressor.wgate", "layers.32.attn.indexer.compressor.wkv", "layers.32.attn.indexer.compressor.gate_proj", "layers.32.attn.indexer.compressor.kv_proj", "layers.33.attn.compressor.wgate", "layers.33.attn.compressor.wkv", "layers.33.attn.compressor.fused_wkv_wgate", "layers.33.attn.compressor.gate_proj", "layers.33.attn.compressor.kv_proj", "layers.33.attn.indexer.weights_proj", "layers.33.attn.indexer.wq_b", "layers.33.attn.indexer.q_b_proj", "layers.33.attn.indexer.compressor.wgate", "layers.33.attn.indexer.compressor.wkv", "layers.33.attn.indexer.compressor.gate_proj", "layers.33.attn.indexer.compressor.kv_proj", "layers.34.attn.compressor.wgate", "layers.34.attn.compressor.wkv", "layers.34.attn.compressor.fused_wkv_wgate", "layers.34.attn.compressor.gate_proj", "layers.34.attn.compressor.kv_proj", "layers.34.attn.indexer.weights_proj", "layers.34.attn.indexer.wq_b", "layers.34.attn.indexer.q_b_proj", "layers.34.attn.indexer.compressor.wgate", "layers.34.attn.indexer.compressor.wkv", "layers.34.attn.indexer.compressor.gate_proj", "layers.34.attn.indexer.compressor.kv_proj", "layers.35.attn.compressor.wgate", "layers.35.attn.compressor.wkv", "layers.35.attn.compressor.fused_wkv_wgate", "layers.35.attn.compressor.gate_proj", "layers.35.attn.compressor.kv_proj", "layers.35.attn.indexer.weights_proj", "layers.35.attn.indexer.wq_b", "layers.35.attn.indexer.q_b_proj", "layers.35.attn.indexer.compressor.wgate", "layers.35.attn.indexer.compressor.wkv", "layers.35.attn.indexer.compressor.gate_proj", "layers.35.attn.indexer.compressor.kv_proj", "layers.36.attn.compressor.wgate", "layers.36.attn.compressor.wkv", "layers.36.attn.compressor.fused_wkv_wgate", "layers.36.attn.compressor.gate_proj", "layers.36.attn.compressor.kv_proj", "layers.36.attn.indexer.weights_proj", "layers.36.attn.indexer.wq_b", "layers.36.attn.indexer.q_b_proj", "layers.36.attn.indexer.compressor.wgate", "layers.36.attn.indexer.compressor.wkv", "layers.36.attn.indexer.compressor.gate_proj", "layers.36.attn.indexer.compressor.kv_proj", "layers.37.attn.compressor.wgate", "layers.37.attn.compressor.wkv", "layers.37.attn.compressor.fused_wkv_wgate", "layers.37.attn.compressor.gate_proj", "layers.37.attn.compressor.kv_proj", "layers.37.attn.indexer.weights_proj", "layers.37.attn.indexer.wq_b", "layers.37.attn.indexer.q_b_proj", "layers.37.attn.indexer.compressor.wgate", "layers.37.attn.indexer.compressor.wkv", "layers.37.attn.indexer.compressor.gate_proj", "layers.37.attn.indexer.compressor.kv_proj", "layers.38.attn.compressor.wgate", "layers.38.attn.compressor.wkv", "layers.38.attn.compressor.fused_wkv_wgate", "layers.38.attn.compressor.gate_proj", "layers.38.attn.compressor.kv_proj", "layers.38.attn.indexer.weights_proj", "layers.38.attn.indexer.wq_b", "layers.38.attn.indexer.q_b_proj", "layers.38.attn.indexer.compressor.wgate", "layers.38.attn.indexer.compressor.wkv", "layers.38.attn.indexer.compressor.gate_proj", "layers.38.attn.indexer.compressor.kv_proj", "layers.39.attn.compressor.wgate", "layers.39.attn.compressor.wkv", "layers.39.attn.compressor.fused_wkv_wgate", "layers.39.attn.compressor.gate_proj", "layers.39.attn.compressor.kv_proj", "layers.39.attn.indexer.weights_proj", "layers.39.attn.indexer.wq_b", "layers.39.attn.indexer.q_b_proj", "layers.39.attn.indexer.compressor.wgate", "layers.39.attn.indexer.compressor.wkv", "layers.39.attn.indexer.compressor.gate_proj", "layers.39.attn.indexer.compressor.kv_proj", "layers.40.attn.compressor.wgate", "layers.40.attn.compressor.wkv", "layers.40.attn.compressor.fused_wkv_wgate", "layers.40.attn.compressor.gate_proj", "layers.40.attn.compressor.kv_proj", "layers.40.attn.indexer.weights_proj", "layers.40.attn.indexer.wq_b", "layers.40.attn.indexer.q_b_proj", "layers.40.attn.indexer.compressor.wgate", "layers.40.attn.indexer.compressor.wkv", "layers.40.attn.indexer.compressor.gate_proj", "layers.40.attn.indexer.compressor.kv_proj", "layers.41.attn.compressor.wgate", "layers.41.attn.compressor.wkv", "layers.41.attn.compressor.fused_wkv_wgate", "layers.41.attn.compressor.gate_proj", "layers.41.attn.compressor.kv_proj", "layers.41.attn.indexer.weights_proj", "layers.41.attn.indexer.wq_b", "layers.41.attn.indexer.q_b_proj", "layers.41.attn.indexer.compressor.wgate", "layers.41.attn.indexer.compressor.wkv", "layers.41.attn.indexer.compressor.gate_proj", "layers.41.attn.indexer.compressor.kv_proj", "layers.42.attn.compressor.wgate", "layers.42.attn.compressor.wkv", "layers.42.attn.compressor.fused_wkv_wgate", "layers.42.attn.compressor.gate_proj", "layers.42.attn.compressor.kv_proj", "layers.42.attn.indexer.weights_proj", "layers.42.attn.indexer.wq_b", "layers.42.attn.indexer.q_b_proj", "layers.42.attn.indexer.compressor.wgate", "layers.42.attn.indexer.compressor.wkv", "layers.42.attn.indexer.compressor.gate_proj", "layers.42.attn.indexer.compressor.kv_proj", "layers.43.attn.compressor.wgate", "layers.43.attn.compressor.wkv", "layers.43.attn.compressor.fused_wkv_wgate", "layers.43.attn.compressor.gate_proj", "layers.43.attn.compressor.kv_proj", "layers.43.attn.indexer.weights_proj", "layers.43.attn.indexer.wq_b", "layers.43.attn.indexer.q_b_proj", "layers.43.attn.indexer.compressor.wgate", "layers.43.attn.indexer.compressor.wkv", "layers.43.attn.indexer.compressor.gate_proj", "layers.43.attn.indexer.compressor.kv_proj", "layers.44.attn.compressor.wgate", "layers.44.attn.compressor.wkv", "layers.44.attn.compressor.fused_wkv_wgate", "layers.44.attn.compressor.gate_proj", "layers.44.attn.compressor.kv_proj", "layers.44.attn.indexer.weights_proj", "layers.44.attn.indexer.wq_b", "layers.44.attn.indexer.q_b_proj", "layers.44.attn.indexer.compressor.wgate", "layers.44.attn.indexer.compressor.wkv", "layers.44.attn.indexer.compressor.gate_proj", "layers.44.attn.indexer.compressor.kv_proj", "layers.45.attn.compressor.wgate", "layers.45.attn.compressor.wkv", "layers.45.attn.compressor.fused_wkv_wgate", "layers.45.attn.compressor.gate_proj", "layers.45.attn.compressor.kv_proj", "layers.45.attn.indexer.weights_proj", "layers.45.attn.indexer.wq_b", "layers.45.attn.indexer.q_b_proj", "layers.45.attn.indexer.compressor.wgate", "layers.45.attn.indexer.compressor.wkv", "layers.45.attn.indexer.compressor.gate_proj", "layers.45.attn.indexer.compressor.kv_proj", "layers.46.attn.compressor.wgate", "layers.46.attn.compressor.wkv", "layers.46.attn.compressor.fused_wkv_wgate", "layers.46.attn.compressor.gate_proj", "layers.46.attn.compressor.kv_proj", "layers.46.attn.indexer.weights_proj", "layers.46.attn.indexer.wq_b", "layers.46.attn.indexer.q_b_proj", "layers.46.attn.indexer.compressor.wgate", "layers.46.attn.indexer.compressor.wkv", "layers.46.attn.indexer.compressor.gate_proj", "layers.46.attn.indexer.compressor.kv_proj", "layers.47.attn.compressor.wgate", "layers.47.attn.compressor.wkv", "layers.47.attn.compressor.fused_wkv_wgate", "layers.47.attn.compressor.gate_proj", "layers.47.attn.compressor.kv_proj", "layers.47.attn.indexer.weights_proj", "layers.47.attn.indexer.wq_b", "layers.47.attn.indexer.q_b_proj", "layers.47.attn.indexer.compressor.wgate", "layers.47.attn.indexer.compressor.wkv", "layers.47.attn.indexer.compressor.gate_proj", "layers.47.attn.indexer.compressor.kv_proj", "layers.48.attn.compressor.wgate", "layers.48.attn.compressor.wkv", "layers.48.attn.compressor.fused_wkv_wgate", "layers.48.attn.compressor.gate_proj", "layers.48.attn.compressor.kv_proj", "layers.48.attn.indexer.weights_proj", "layers.48.attn.indexer.wq_b", "layers.48.attn.indexer.q_b_proj", "layers.48.attn.indexer.compressor.wgate", "layers.48.attn.indexer.compressor.wkv", "layers.48.attn.indexer.compressor.gate_proj", "layers.48.attn.indexer.compressor.kv_proj", "layers.49.attn.compressor.wgate", "layers.49.attn.compressor.wkv", "layers.49.attn.compressor.fused_wkv_wgate", "layers.49.attn.compressor.gate_proj", "layers.49.attn.compressor.kv_proj", "layers.49.attn.indexer.weights_proj", "layers.49.attn.indexer.wq_b", "layers.49.attn.indexer.q_b_proj", "layers.49.attn.indexer.compressor.wgate", "layers.49.attn.indexer.compressor.wkv", "layers.49.attn.indexer.compressor.gate_proj", "layers.49.attn.indexer.compressor.kv_proj", "layers.50.attn.compressor.wgate", "layers.50.attn.compressor.wkv", "layers.50.attn.compressor.fused_wkv_wgate", "layers.50.attn.compressor.gate_proj", "layers.50.attn.compressor.kv_proj", "layers.50.attn.indexer.weights_proj", "layers.50.attn.indexer.wq_b", "layers.50.attn.indexer.q_b_proj", "layers.50.attn.indexer.compressor.wgate", "layers.50.attn.indexer.compressor.wkv", "layers.50.attn.indexer.compressor.gate_proj", "layers.50.attn.indexer.compressor.kv_proj", "layers.51.attn.compressor.wgate", "layers.51.attn.compressor.wkv", "layers.51.attn.compressor.fused_wkv_wgate", "layers.51.attn.compressor.gate_proj", "layers.51.attn.compressor.kv_proj", "layers.51.attn.indexer.weights_proj", "layers.51.attn.indexer.wq_b", "layers.51.attn.indexer.q_b_proj", "layers.51.attn.indexer.compressor.wgate", "layers.51.attn.indexer.compressor.wkv", "layers.51.attn.indexer.compressor.gate_proj", "layers.51.attn.indexer.compressor.kv_proj", "layers.52.attn.compressor.wgate", "layers.52.attn.compressor.wkv", "layers.52.attn.compressor.fused_wkv_wgate", "layers.52.attn.compressor.gate_proj", "layers.52.attn.compressor.kv_proj", "layers.52.attn.indexer.weights_proj", "layers.52.attn.indexer.wq_b", "layers.52.attn.indexer.q_b_proj", "layers.52.attn.indexer.compressor.wgate", "layers.52.attn.indexer.compressor.wkv", "layers.52.attn.indexer.compressor.gate_proj", "layers.52.attn.indexer.compressor.kv_proj", "layers.53.attn.compressor.wgate", "layers.53.attn.compressor.wkv", "layers.53.attn.compressor.fused_wkv_wgate", "layers.53.attn.compressor.gate_proj", "layers.53.attn.compressor.kv_proj", "layers.53.attn.indexer.weights_proj", "layers.53.attn.indexer.wq_b", "layers.53.attn.indexer.q_b_proj", "layers.53.attn.indexer.compressor.wgate", "layers.53.attn.indexer.compressor.wkv", "layers.53.attn.indexer.compressor.gate_proj", "layers.53.attn.indexer.compressor.kv_proj", "layers.54.attn.compressor.wgate", "layers.54.attn.compressor.wkv", "layers.54.attn.compressor.fused_wkv_wgate", "layers.54.attn.compressor.gate_proj", "layers.54.attn.compressor.kv_proj", "layers.54.attn.indexer.weights_proj", "layers.54.attn.indexer.wq_b", "layers.54.attn.indexer.q_b_proj", "layers.54.attn.indexer.compressor.wgate", "layers.54.attn.indexer.compressor.wkv", "layers.54.attn.indexer.compressor.gate_proj", "layers.54.attn.indexer.compressor.kv_proj", "layers.55.attn.compressor.wgate", "layers.55.attn.compressor.wkv", "layers.55.attn.compressor.fused_wkv_wgate", "layers.55.attn.compressor.gate_proj", "layers.55.attn.compressor.kv_proj", "layers.55.attn.indexer.weights_proj", "layers.55.attn.indexer.wq_b", "layers.55.attn.indexer.q_b_proj", "layers.55.attn.indexer.compressor.wgate", "layers.55.attn.indexer.compressor.wkv", "layers.55.attn.indexer.compressor.gate_proj", "layers.55.attn.indexer.compressor.kv_proj", "layers.56.attn.compressor.wgate", "layers.56.attn.compressor.wkv", "layers.56.attn.compressor.fused_wkv_wgate", "layers.56.attn.compressor.gate_proj", "layers.56.attn.compressor.kv_proj", "layers.56.attn.indexer.weights_proj", "layers.56.attn.indexer.wq_b", "layers.56.attn.indexer.q_b_proj", "layers.56.attn.indexer.compressor.wgate", "layers.56.attn.indexer.compressor.wkv", "layers.56.attn.indexer.compressor.gate_proj", "layers.56.attn.indexer.compressor.kv_proj", "layers.57.attn.compressor.wgate", "layers.57.attn.compressor.wkv", "layers.57.attn.compressor.fused_wkv_wgate", "layers.57.attn.compressor.gate_proj", "layers.57.attn.compressor.kv_proj", "layers.57.attn.indexer.weights_proj", "layers.57.attn.indexer.wq_b", "layers.57.attn.indexer.q_b_proj", "layers.57.attn.indexer.compressor.wgate", "layers.57.attn.indexer.compressor.wkv", "layers.57.attn.indexer.compressor.gate_proj", "layers.57.attn.indexer.compressor.kv_proj", "layers.58.attn.compressor.wgate", "layers.58.attn.compressor.wkv", "layers.58.attn.compressor.fused_wkv_wgate", "layers.58.attn.compressor.gate_proj", "layers.58.attn.compressor.kv_proj", "layers.58.attn.indexer.weights_proj", "layers.58.attn.indexer.wq_b", "layers.58.attn.indexer.q_b_proj", "layers.58.attn.indexer.compressor.wgate", "layers.58.attn.indexer.compressor.wkv", "layers.58.attn.indexer.compressor.gate_proj", "layers.58.attn.indexer.compressor.kv_proj", "layers.59.attn.compressor.wgate", "layers.59.attn.compressor.wkv", "layers.59.attn.compressor.fused_wkv_wgate", "layers.59.attn.compressor.gate_proj", "layers.59.attn.compressor.kv_proj", "layers.59.attn.indexer.weights_proj", "layers.59.attn.indexer.wq_b", "layers.59.attn.indexer.q_b_proj", "layers.59.attn.indexer.compressor.wgate", "layers.59.attn.indexer.compressor.wkv", "layers.59.attn.indexer.compressor.gate_proj", "layers.59.attn.indexer.compressor.kv_proj", "layers.60.attn.compressor.wgate", "layers.60.attn.compressor.wkv", "layers.60.attn.compressor.fused_wkv_wgate", "layers.60.attn.compressor.gate_proj", "layers.60.attn.compressor.kv_proj", "layers.60.attn.indexer.weights_proj", "layers.60.attn.indexer.wq_b", "layers.60.attn.indexer.q_b_proj", "layers.60.attn.indexer.compressor.wgate", "layers.60.attn.indexer.compressor.wkv", "layers.60.attn.indexer.compressor.gate_proj", "layers.60.attn.indexer.compressor.kv_proj" ], "kv_cache_scheme": null, "quant_method": "compressed-tensors", "quantization_status": "compressed", "sparsity_config": {}, "transform_config": {}, "version": "0.15.1.a20260515", "scale_fmt": "ue8m0" }, "rms_norm_eps": 1e-06, "rope_parameters": { "compress": { "attention_factor": 1.0, "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" }, "main": { "partial_rotary_factor": 0.125, "rope_theta": 10000, "rope_type": "default" }, "partial_rotary_factor": 0.125, "rope_theta": 10000, "rope_type": "default" }, "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_method": "noaux_tc", "transformers_version": "5.8.1", "use_cache": true, "vocab_size": 129280, "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 ], "num_hash_layers": 3, "rope_scaling": { "beta_fast": 32, "beta_slow": 1, "factor": 16, "original_max_position_embeddings": 65536, "type": "yarn" }, "torch_dtype": "bfloat16", "_w4a8_conversion": "experts input_activations: null -> fp8 dynamic token (Claude/Evrard 2026-06-26)" }