{ "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "alpha_pattern": {}, "auto_mapping": null, "base_model_name_or_path": "Qwen/Qwen2.5-Coder-1.5B-Instruct", "bias": "none", "fan_in_fan_out": false, "hidden_act": "silu", "hidden_size": 1536, "initializer_range": 0.02, "intermediate_size": 8960, "inference_mode": true, "init_lora_weights": true, "layer_replication": null, "model_type": "qwen2", "layers_pattern": null, "layers_to_transform": null, "loftq_config": {}, "lora_alpha": 16, "lora_dropout": 0.1, "max_position_embeddings": 32768, "max_window_layers": 21, "megatron_config": null, "megatron_core": "megatron.core", "modules_to_save": null, "num_attention_heads": 12, "num_hidden_layers": 28, "num_key_value_heads": 2, "peft_type": "LORA", "r": 8, "rank_pattern": {}, "revision": null, "rope_theta": 1000000.0, "sliding_window": 131072, "task_type": "CAUSAL_LM", "tie_word_embeddings": true, "torch_dtype": "bfloat16", "transformers_version": "4.44.0", "use_cache": true, "use_dora": false, "use_rslora": false, "use_sliding_window": false, "vocab_size": 151936, "bos_token_id": 151643, "eos_token_id": 151643 }