neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.19/inference/llama/OpenAssistant/llama2-13b-orca-8k-3319/20d2823c7da1d74be70d.json

{"vocab_size": 32016, "max_position_embeddings": 8192, "hidden_size": 5120, "intermediate_size": 13824, "num_hidden_layers": 40, "num_attention_heads": 40, "num_key_value_heads": 40, "hidden_act": "silu", "initializer_range": 0.02, "rms_norm_eps": 1e-05, "pretraining_tp": 1, "use_cache": true, "rope_theta": 10000.0, "rope_scaling": {"factor": 2.0, "type": "linear"}, "attention_bias": false, "attention_dropout": 0.0, "torch_dtype": "float16", "tie_word_embeddings": false, "max_length": 8192, "architectures": ["LlamaForCausalLM"], "bos_token_id": 1, "pad_token_id": 0, "eos_token_id": 2, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 4, "checkpoint_id": "OpenAssistant/llama2-13b-orca-8k-3319", "checkpoint_revision": "b02bf240968a60674d9e1afc73f83868ae52fee0", "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "num_cores": 8, "sequence_length": 4096, "task": "text-generation"}}