{ "_name_or_path": "/storage/openpsi/experiments/checkpoints/admin/ds-r1-distill-qwen-32b-sft/20250317-1-light-r1-200-lr-1e-5-p1m4-bf16/default/epoch97epochstep4globalstep304", "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "hidden_act": "silu", "hidden_size": 5120, "initializer_range": 0.02, "intermediate_size": 27648, "max_position_embeddings": 131072, "max_window_layers": 28, "model_type": "qwen2", "num_attention_heads": 40, "num_hidden_layers": 64, "num_key_value_heads": 8, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 1000000.0, "sliding_window": null, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.48.3", "use_cache": true, "use_sliding_window": false, "vocab_size": 152064 }