{ "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151645, "hidden_act": "silu", "hidden_size": 896, "initializer_range": 0.02, "intermediate_size": 4864, "max_position_embeddings": 32768, "max_window_layers": 21, "model_type": "qwen2", "num_attention_heads": 14, "num_hidden_layers": 24, "num_key_value_heads": 2, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "sliding_window": 32768, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "transformers_version": "4.43.1", "use_cache": true, "use_sliding_window": false, "vocab_size": 151936, "quantization_config": { "quant_method": "exl2", "version": "0.2.4", "bits": 2.0, "head_bits": 6, "calibration": { "rows": 115, "length": 2048, "dataset": "(default)" } } }