{ "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 151644, "eos_token_id": 151645, "hidden_act": "silu", "hidden_size": 8192, "initializer_range": 0.02, "intermediate_size": 29568, "max_position_embeddings": 32768, "max_window_layers": 80, "model_type": "qwen2", "num_attention_heads": 64, "num_hidden_layers": 86, "num_key_value_heads": 8, "pad_token_id": 151645, "quantization": { "group_size": 64, "bits": 4 }, "quantization_config": { "group_size": 64, "bits": 4 }, "rms_norm_eps": 1e-06, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.44.2", "use_cache": false, "use_sliding_window": false, "vocab_size": 151646 }