cuda/cuda-fp16/genai_config.json

{
    "model": {
        "bos_token_id": 128000,
        "context_length": 131072,
        "decoder": {
            "session_options": {
                "log_id": "onnxruntime-genai",
                "provider_options": [
                    {
                        "cuda": {
                            "enable_cuda_graph": "0"
                        }
                    }
                ]
            },
            "filename": "model.onnx",
            "head_size": 64,
            "hidden_size": 2048,
            "inputs": {
                "input_ids": "input_ids",
                "attention_mask": "attention_mask",
                "past_key_names": "past_key_values.%d.key",
                "past_value_names": "past_key_values.%d.value"
            },
            "outputs": {
                "logits": "logits",
                "present_key_names": "present.%d.key",
                "present_value_names": "present.%d.value"
            },
            "num_attention_heads": 32,
            "num_hidden_layers": 16,
            "num_key_value_heads": 8
        },
        "eos_token_id": [
            128001,
            128008,
            128009
        ],
        "pad_token_id": 128001,
        "type": "llama",
        "vocab_size": 128256
    },
    "search": {
        "diversity_penalty": 0.0,
        "do_sample": true,
        "early_stopping": true,
        "length_penalty": 1.0,
        "max_length": 131072,
        "min_length": 0,
        "no_repeat_ngram_size": 0,
        "num_beams": 1,
        "num_return_sequences": 1,
        "past_present_share_buffer": true,
        "repetition_penalty": 1.0,
        "temperature": 0.6,
        "top_k": 1,
        "top_p": 0.9
    }
}