{ "_entry_class": "SingleModelCacheEntry", "_model_id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B", "_task": "text-generation", "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "hidden_act": "silu", "hidden_size": 3584, "initializer_range": 0.02, "intermediate_size": 18944, "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" ], "max_position_embeddings": 131072, "max_window_layers": 28, "model_type": "qwen2", "neuron": { "_serialized_key": "NxDNeuronConfig", "batch_size": 4, "capacity_factor": null, "checkpoint_id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B", "checkpoint_revision": "916b56a44061fd5cd7d6a8fb632557ed4f724f60", "continuous_batching": true, "enable_bucketing": false, "ep_degree": 1, "fused_qkv": false, "glu_mlp": true, "local_ranks_size": 2, "logical_nc_config": 1, "max_batch_size": 4, "max_context_length": 4096, "max_topk": 256, "n_active_tokens": 4096, "neuronxcc_version": "2.19.8089.0+8ab9f450", "on_device_sampling": false, "optimum_neuron_version": "0.3.1.dev5", "output_logits": false, "pp_degree": 1, "sequence_length": 4096, "speculation_length": 0, "start_rank_id": 0, "target": null, "torch_dtype": "bfloat16", "tp_degree": 2 }, "num_attention_heads": 28, "num_hidden_layers": 28, "num_key_value_heads": 4, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 10000, "sliding_window": null, "tie_word_embeddings": false, "use_cache": true, "use_mrope": false, "use_sliding_window": false, "vocab_size": 152064 }