{ "architectures": [ "Qwen3ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "eos_token_id": 151645, "head_dim": 128, "hidden_act": "silu", "hidden_size": 5120, "initializer_range": 0.02, "intermediate_size": 17408, "max_position_embeddings": 40960, "max_window_layers": 40, "model_type": "qwen3", "num_attention_heads": 40, "num_hidden_layers": 40, "num_key_value_heads": 8, "pad_token_id": 151654, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 1000000, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.52.0.dev0", "unsloth_fixed": true, "use_cache": true, "use_sliding_window": false, "vocab_size": 151936 }