{ "architectures": [ "Qwen2ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "dtype": "float32", "eos_token_id": 2, "head_dim": 64, "hidden_act": "silu", "hidden_size": 256, "initializer_range": 0.02, "intermediate_size": 768, "layer_types": [ "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention", "full_attention" ], "max_position_embeddings": 8192, "max_window_layers": 64, "mlp_bias": false, "model_type": "qwen2", "num_attention_heads": 4, "num_hidden_layers": 64, "num_key_value_heads": 4, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": { "factor": 4.0, "original_max_position_embeddings": 2048, "rope_type": "yarn", "type": "yarn" }, "rope_theta": 10000, "sliding_window": null, "tie_word_embeddings": true, "transformers_version": "4.57.1", "use_cache": true, "use_sliding_window": false, "vocab_size": 8192 }