optimum-neuron-cache / neuronxcc-2.19.8089.0+8ab9f450 /0_REGISTRY /0.3.1.dev5 /qwen2 /deepseek-ai /DeepSeek-R1-Distill-Qwen-32B /cf2f5cb2366760ef6c31.json
| { | |
| "_entry_class": "SingleModelCacheEntry", | |
| "_model_id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", | |
| "_task": "text-generation", | |
| "architectures": [ | |
| "Qwen2ForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 27648, | |
| "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", | |
| "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", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention", | |
| "full_attention" | |
| ], | |
| "max_position_embeddings": 131072, | |
| "max_window_layers": 64, | |
| "model_type": "qwen2", | |
| "neuron": { | |
| "_serialized_key": "NxDNeuronConfig", | |
| "batch_size": 8, | |
| "capacity_factor": null, | |
| "checkpoint_id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", | |
| "checkpoint_revision": "711ad2ea6aa40cfca18895e8aca02ab92df1a746", | |
| "continuous_batching": true, | |
| "enable_bucketing": false, | |
| "ep_degree": 1, | |
| "fused_qkv": false, | |
| "glu_mlp": true, | |
| "local_ranks_size": 8, | |
| "logical_nc_config": 1, | |
| "max_batch_size": 8, | |
| "max_context_length": 4096, | |
| "max_topk": 256, | |
| "n_active_tokens": 4096, | |
| "neuronxcc_version": "2.19.8089.0+8ab9f450", | |
| "on_device_sampling": true, | |
| "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": 8 | |
| }, | |
| "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, | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 152064 | |
| } |