{ "architectures": [ "Qwen3ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151645, "head_dim": 128, "hidden_act": "silu", "hidden_size": 1536, "initializer_range": 0.02, "intermediate_size": 4096, "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" ], "max_position_embeddings": 8192, "max_window_layers": 24, "model_type": "qwen3", "num_attention_heads": 12, "num_hidden_layers": 24, "num_key_value_heads": 6, "pad_token_id": 151654, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 10000.0, "sliding_window": 4096, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "transformers_version": "4.54.0.dev0", "unsloth_version": "2025.7.11", "use_cache": true, "use_sliding_window": true, "vocab_size": 151936 }