optimum-neuron-cache
/
neuronxcc-2.15.143.0+e39249ad
/0_REGISTRY
/0.0.28.dev0
/inference
/qwen2
/deepseek-ai
/DeepSeek-R1-Distill-Qwen-14B
/6da6ace13bab9e22cf40.json
{"architectures": ["Qwen2ForCausalLM"], "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151643, "hidden_act": "silu", "hidden_size": 5120, "initializer_range": 0.02, "intermediate_size": 13824, "max_position_embeddings": 131072, "max_window_layers": 48, "model_type": "qwen2", "neuron": {"auto_cast_type": "bf16", "batch_size": 1, "checkpoint_id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B", "checkpoint_revision": "43388607a61ba60e6dd3e349eb5f55c94e984bc0", "compiler_type": "neuronx-cc", "compiler_version": "2.15.143.0+e39249ad", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}, "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, "torch_dtype": "bfloat16", "use_cache": true, "use_sliding_window": false, "vocab_size": 152064} |