aihub models run failure

[1826133674]

Hello, regarding the binary files of compiled LLMs that can be directly downloaded from AIhub, what is the target device for these files? Can they run on an 8Gen3 chipset?

When I attempted to run inference on them using an 8gen3 smartphone, I encountered the following error:

./genie-t2t-run -c qwen2_7b_instruct_quantized.json -p "<|begin_of_text|><|start_header_id|>user<|end_header_id|>\n\nWhat is France's capital?<|eot_id|><|start_header_id|>assistant<|end_header_id|>"

[INFO]  "Using create From Binary"
[INFO]  "Allocated total size = 174998016 across 8 buffers"
[ERROR] "Could not create context from binary for context index = 0 : err 5005"
[ERROR] "Create From Binary FAILED!"

qwen2_7b_instruct_quantized.json :

{
    "dialog": {
        "version": 1,
        "type": "basic",
        "context": {
            "version": 1,
            "size": 4096,
            "n-vocab": 152064,
            "bos-token": -1,
            "eos-token": 151645
        },
        "sampler": {
            "version": 1,
            "seed": 42,
            "temp": 0.8,
            "top-k": 40,
            "top-p": 0.95
        },
        "tokenizer": {
            "version": 1,
            "path": "tokenizer.json"
        },
        "engine": {
            "version": 1,
            "n-threads": 3,
            "backend": {
                "version": 1,
                "type": "QnnHtp",
                "QnnHtp": {
                    "version": 1,
                    "use-mmap": true,
                    "spill-fill-bufsize": 0,
                    "mmap-budget": 0,
                    "poll": false,
                    "pos-id-dim": 64,
                    "cpu-mask": "0xe0",
                    "kv-dim": 128,
                    "rope-theta": 1000000,
                    "allow-async-init": false
                },
                "extensions": "htp_backend_ext_config.json"
            },
            "model": {
                "version": 1,
                "type": "binary",
                "binary": {
                    "version": 1,
                    "ctx-bins": [
                        "weight_sharing_model_1_of_4.serialized.bin",
                        "weight_sharing_model_2_of_4.serialized.bin",
                        "weight_sharing_model_3_of_4.serialized.bin",
                        "weight_sharing_model_4_of_4.serialized.bin"
                    ]
                }
            }
        }
    }
}

htp_backend_ext_config.json

{
    "devices": [
        {

            "dsp_arch": "v75",
            "cores": [
                {
                    "core_id": 0,
                    "perf_profile": "burst",
                    "rpc_control_latency": 100
                }
            ]
        }
    ],
    "memory": {
        "mem_type": "shared_buffer"
    },
    "context": {
        "weight_sharing_enabled": true
    }
}