{ "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151643, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 11008, "max_position_embeddings": 32768, "max_window_layers": 36, "model_type": "qwen2", "num_attention_heads": 16, "num_hidden_layers": 36, "num_key_value_heads": 2, "quantization": { "group_size": 64, "bits": 8 }, "quantization_config": { "group_size": 64, "bits": 8 }, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "sliding_window": 32768, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "transformers_version": "4.40.1", "use_cache": true, "use_mrope": false, "use_sliding_window": false, "vocab_size": 151936 }