{ "architectures": [ "Qwen3ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "decoder_start_token_id": 128000, "dtype": "bfloat16", "eos_token_id": 128001, "head_dim": 128, "hidden_act": "silu", "hidden_size": 5376, "initializer_range": 0.02, "intermediate_size": 21504, "layer_types": [ "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention" ], "max_position_embeddings": 16384, "max_window_layers": 28, "model_type": "qwen3", "no_bias": true, "num_attention_heads": 42, "num_hidden_layers": 51, "num_key_value_heads": 42, "pad_token_id": 128001, "rms_norm_eps": 1e-05, "rope_scaling": { "factor": 8.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3" }, "rope_theta": 500000, "sliding_window": null, "tie_word_embeddings": false, "transformers_version": "4.57.6", "use_cache": true, "use_sliding_window": false, "vocab_size": 128256 }