{ "architectures": [ "Qwen3MoeForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 151643, "decoder_sparse_step": 1, "dtype": "bfloat16", "eos_token_id": 151645, "head_dim": 128, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 6144, "max_position_embeddings": 40960, "max_window_layers": 48, "mlp_only_layers": [], "model_type": "qwen3_moe", "moe_intermediate_size": 768, "norm_topk_prob": true, "num_attention_heads": 32, "num_experts": 128, "num_experts_per_tok": 8, "num_hidden_layers": 48, "num_key_value_heads": 4, "output_router_logits": false, "quantization_config": { "config_groups": { "group_0": { "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": [ "Linear" ], "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": "nvfp4-pack-quantized", "global_compression_ratio": null, "ignore": [ "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_scaling": null, "rope_theta": 1000000.0, "router_aux_loss_coef": 0.001, "sliding_window": null, "tie_word_embeddings": false, "transformers_version": "4.57.6", "use_cache": true, "use_sliding_window": false, "vocab_size": 151936 }