{ "_name_or_path": "/home/aiops/chency/repo/sailor2-proj/Sailor2-NeMo-Aligner/results/sailor2/14B/sailor2-14B-dpo_beta0.01-lenreg0.0-sea-uf-llama3-4o-lid_0213T10:48:21/saved_models/step_00356", "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151643, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 13368, "max_position_embeddings": 131072, "max_window_layers": 48, "model_type": "qwen2", "num_attention_heads": 32, "num_hidden_layers": 64, "num_key_value_heads": 8, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.45.2", "use_cache": false, "use_sliding_window": false, "vocab_size": 151936 }