{ "_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--deepseek-ai--DeepSeek-R1-Distill-Qwen-7B/snapshots/916b56a44061fd5cd7d6a8fb632557ed4f724f60", "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151643, "hidden_act": "silu", "hidden_size": 3584, "initializer_range": 0.02, "intermediate_size": 18944, "max_position_embeddings": 131072, "max_window_layers": 28, "model_type": "qwen2", "num_attention_heads": 28, "num_hidden_layers": 28, "num_key_value_heads": 4, "quantization_config": { "quant_dtype": "float8_e4m3fn", "quant_method": "smooth_quant" }, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 10000, "sliding_window": 4096, "tie_word_embeddings": false, "torch_dtype": "float16", "transformers_version": "4.50.0.dev0", "use_cache": false, "use_mrope": false, "use_sliding_window": false, "vocab_size": 152064 }