{ "architectures": [ "HYV3ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 120000, "dtype": "bfloat16", "enable_attention_fp32_softmax": false, "enable_lm_head_fp32": true, "enable_moe_fp32_combine": false, "eod_token_id": 120026, "eos_token_id": 120025, "expert_hidden_dim": 1536, "first_k_dense_replace": 1, "head_dim": 128, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.006, "intermediate_size": 13312, "max_position_embeddings": 262144, "mlp_bias": false, "mlp_layer_types": [ "dense", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse", "sparse" ], "model_type": "hy_v3", "moe_intermediate_size": 1536, "moe_router_enable_expert_bias": true, "moe_router_use_sigmoid": true, "num_attention_heads": 64, "num_experts": 192, "num_experts_per_tok": 8, "num_hidden_layers": 80, "num_key_value_heads": 8, "num_nextn_predict_layers": 1, "num_shared_experts": 1, "output_router_logits": true, "pad_token_id": 120002, "qk_norm": true, "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:.*self_attn\\..*" ], "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:.*mlp.*" ], "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": [ "model.layers.1.mlp.gate", "model.layers.2.mlp.gate", "model.layers.3.mlp.gate", "model.layers.4.mlp.gate", "model.layers.5.mlp.gate", "model.layers.6.mlp.gate", "model.layers.7.mlp.gate", "model.layers.8.mlp.gate", "model.layers.9.mlp.gate", "model.layers.10.mlp.gate", "model.layers.11.mlp.gate", "model.layers.12.mlp.gate", "model.layers.13.mlp.gate", "model.layers.14.mlp.gate", "model.layers.15.mlp.gate", "model.layers.16.mlp.gate", "model.layers.17.mlp.gate", "model.layers.18.mlp.gate", "model.layers.19.mlp.gate", "model.layers.20.mlp.gate", "model.layers.21.mlp.gate", "model.layers.22.mlp.gate", "model.layers.23.mlp.gate", "model.layers.24.mlp.gate", "model.layers.25.mlp.gate", "model.layers.26.mlp.gate", "model.layers.27.mlp.gate", "model.layers.28.mlp.gate", "model.layers.29.mlp.gate", "model.layers.30.mlp.gate", "model.layers.31.mlp.gate", "model.layers.32.mlp.gate", "model.layers.33.mlp.gate", "model.layers.34.mlp.gate", "model.layers.35.mlp.gate", "model.layers.36.mlp.gate", "model.layers.37.mlp.gate", "model.layers.38.mlp.gate", "model.layers.39.mlp.gate", "model.layers.40.mlp.gate", "model.layers.41.mlp.gate", "model.layers.42.mlp.gate", "model.layers.43.mlp.gate", "model.layers.44.mlp.gate", "model.layers.45.mlp.gate", "model.layers.46.mlp.gate", "model.layers.47.mlp.gate", "model.layers.48.mlp.gate", "model.layers.49.mlp.gate", "model.layers.50.mlp.gate", "model.layers.51.mlp.gate", "model.layers.52.mlp.gate", "model.layers.53.mlp.gate", "model.layers.54.mlp.gate", "model.layers.55.mlp.gate", "model.layers.56.mlp.gate", "model.layers.57.mlp.gate", "model.layers.58.mlp.gate", "model.layers.59.mlp.gate", "model.layers.60.mlp.gate", "model.layers.61.mlp.gate", "model.layers.62.mlp.gate", "model.layers.63.mlp.gate", "model.layers.64.mlp.gate", "model.layers.65.mlp.gate", "model.layers.66.mlp.gate", "model.layers.67.mlp.gate", "model.layers.68.mlp.gate", "model.layers.69.mlp.gate", "model.layers.70.mlp.gate", "model.layers.71.mlp.gate", "model.layers.72.mlp.gate", "model.layers.73.mlp.gate", "model.layers.74.mlp.gate", "model.layers.75.mlp.gate", "model.layers.76.mlp.gate", "model.layers.77.mlp.gate", "model.layers.78.mlp.gate", "model.layers.79.mlp.gate", "lm_head", "re:^model.layers.80.*" ], "kv_cache_scheme": null, "quant_method": "compressed-tensors", "quantization_status": "compressed", "sparsity_config": {}, "transform_config": {}, "version": "0.17.1.dev6+g3d7e616.d20260611" }, "rms_norm_eps": 1e-05, "rope_parameters": { "rope_theta": 11158840.0, "rope_type": "default" }, "route_norm": true, "router_scaling_factor": 2.826, "sep_token_id": 120007, "tie_word_embeddings": false, "transformers_version": "5.14.0.dev0", "use_cache": true, "use_grouped_mm": false, "vocab_size": 120832 }