neuronxcc-2.13.66.0+6dfecc895/0_REGISTRY/0.0.24.dev0/training/llama/meta-llama/Meta-Llama-3-8b/eb776d8f1c8a395541f5.json

{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": 128001, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "llama", "neuron": {"compiler_version": "2.13.66.0+6dfecc895", "input_specs": {"input_ids": [1, 2048], "labels": [1, 2048]}, "model_class": "LlamaForCausalLM", "num_neuron_cores_per_node": 32, "pipeline_parallel_size": 1, "precision": "bfloat16", "tensor_parallel_size": 8, "training": true}, "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "use_cache": false, "vocab_size": 128256}