{ "architectures": [ "Qwen3ForCausalLM" ], "model_type": "qwen3", "vocab_size": 259, "hidden_size": 512, "num_hidden_layers": 16, "intermediate_size": 1536, "num_attention_heads": 4, "num_key_value_heads": 2, "head_dim": 128, "hidden_act": "silu", "rms_norm_eps": 1e-06, "max_position_embeddings": 4096, "rope_theta": 1000000.0, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "tie_word_embeddings": false, "use_cache": true, "bos_token_id": 256, "eos_token_id": 257, "pad_token_id": 258, "torch_dtype": "float32" }