{ "architectures": [ "Qwen2ForCausalLM" ], "attention_bias": false, "bos_token_id": 151643, "eos_token_id": [151645, 151643], "hidden_act": "silu", "hidden_size": 2560, "initializer_range": 0.02, "intermediate_size": 9728, "max_position_embeddings": 262144, "model_type": "qwen2", "num_attention_heads": 32, "num_hidden_layers": 36, "num_key_value_heads": 8, "rms_norm_eps": 1e-06, "rope_theta": 5000000.0, "sliding_window": null, "tie_word_embeddings": true, "torch_dtype": "float32", "transformers_version": "4.37.0", "use_cache": true, "vocab_size": 151936, "quantization_config": { "quant_method": "mlc", "bits": 4, "group_size": 32, "desc_act": false } }