optimum-neuron-cache / neuronxcc-2.19.8089.0+8ab9f450 /0_REGISTRY /0.3.1.dev3 /qwen2 /deepseek-ai /DeepSeek-R1-Distill-Qwen-14B /d8f035e13099896f48bb.json
| { | |
| "_entry_class": "SingleModelCacheEntry", | |
| "_model_id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B", | |
| "_task": "text-generation", | |
| "architectures": [ | |
| "Qwen2ForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 13824, | |
| "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" | |
| ], | |
| "max_position_embeddings": 131072, | |
| "max_window_layers": 48, | |
| "model_type": "qwen2", | |
| "neuron": { | |
| "_serialized_key": "NxDNeuronConfig", | |
| "async_mode": false, | |
| "attn_kernel_enabled": false, | |
| "batch_size": 1, | |
| "capacity_factor": null, | |
| "cc_pipeline_tiling_factor": 2, | |
| "checkpoint_id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B", | |
| "checkpoint_revision": "1df8507178afcc1bef68cd8c393f61a886323761", | |
| "continuous_batching": false, | |
| "enable_bucketing": false, | |
| "ep_degree": 1, | |
| "flash_decoding_enabled": false, | |
| "fused_qkv": false, | |
| "glu_mlp": true, | |
| "is_chunked_prefill": false, | |
| "local_ranks_size": 8, | |
| "logical_nc_config": 1, | |
| "max_batch_size": 1, | |
| "max_context_length": 4096, | |
| "max_topk": 256, | |
| "mlp_kernel_enabled": false, | |
| "mlp_kernel_fuse_residual_add": false, | |
| "n_active_tokens": 4096, | |
| "neuronxcc_version": "2.19.8089.0+8ab9f450", | |
| "num_cores_per_group": 1, | |
| "on_device_sampling": true, | |
| "optimum_neuron_version": "0.3.1.dev3", | |
| "output_logits": false, | |
| "padding_side": "right", | |
| "pp_degree": 1, | |
| "qkv_kernel_enabled": false, | |
| "rpl_reduce_dtype": "bfloat16", | |
| "sequence_length": 4096, | |
| "sequence_parallel_enabled": false, | |
| "speculation_length": 0, | |
| "start_rank_id": 0, | |
| "target": null, | |
| "torch_dtype": "bfloat16", | |
| "tp_degree": 8, | |
| "vocab_parallel": false | |
| }, | |
| "num_attention_heads": 40, | |
| "num_hidden_layers": 48, | |
| "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 | |
| } |