optimum-neuron-cache
/
neuronxcc-2.12.68.0+4480452af
/0_REGISTRY
/0.0.19
/inference
/llama
/meta-llama
/Llama-2-7b-chat-hf
/15e8c952b3c81fd87a57.json
{"vocab_size": 32000, "max_position_embeddings": 4096, "hidden_size": 4096, "intermediate_size": 11008, "num_hidden_layers": 32, "num_attention_heads": 32, "num_key_value_heads": 32, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000.0, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "torch_dtype": "float16", "tie_word_embeddings": false, "architectures": ["LlamaForCausalLM"], "bos_token_id": 1, "eos_token_id": 2, "model_type": "llama", "neuron": {"task": "text-generation", "batch_size": 4, "num_cores": 24, "auto_cast_type": "fp16", "sequence_length": 4096, "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "checkpoint_id": "meta-llama/Llama-2-7b-chat-hf", "checkpoint_revision": "c1b0db933684edbfe29a06fa47eb19cc48025e93"}} |