neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.20/inference/llama/codellama/CodeLlama-7b-hf/e3b9c0ce479aacf9b6d1.json

{"vocab_size": 32016, "max_position_embeddings": 16384, "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": 1000000, "rope_scaling": null, "attention_bias": false, "attention_dropout": 0.0, "torch_dtype": "bfloat16", "tie_word_embeddings": false, "architectures": ["LlamaForCausalLM"], "bos_token_id": 1, "eos_token_id": 2, "model_type": "llama", "neuron": {"auto_cast_type": "fp16", "batch_size": 1, "checkpoint_id": "codellama/CodeLlama-7b-hf", "checkpoint_revision": "7f22f0a5f7991355a2c3867923359ec4ed0b58bf", "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "num_cores": 2, "sequence_length": 2048, "task": "text-generation"}}