我使用了mindie-service进行qwen1的服务化，但是感觉接口的推理有点异常：system这样添加好像有点问题，并且qwen2部署不成功，报错如下：

qwen1可以推理的mindie的config如下：

{

"OtherParam":

{

"ResourceParam":

{

"cacheBlockSize": 128,

"preAllocBlocks": 4

},

"LogParam":

{

"logLevel": "Info",

"logPath": "/logs/mindservice.log"

},

"ServeParam":

{

"ipAddress": "127.0.0.1",

"port": 1025,

"maxLinkNum": 300,

"httpsEnabled": false,

"tlsCaPath": "security/ca/",

"tlsCaFile": ["ca.pem"],

"tlsCert": "security/certs/server.pem",

"tlsPk": "security/keys/server.key.pem",

"tlsPkPwd": "security/pass/mindie_server_key_pwd.txt",

"kmcKsfMaster": "tools/pmt/master/ksfa",

"kmcKsfStandby": "tools/pmt/standby/ksfb",

"tlsCrl": "security/certs/server_crl.pem"

}

},

"WorkFlowParam":

{

"TemplateParam":

{

"templateType": "Standard",

"templateName": "Standard_llama",

"pipelineNumber": 1

}

},

"ModelDeployParam":

{

"maxSeqLen": 8192,

"npuDeviceIds": [[4, 5, 6, 7]],

"ModelParam": [

{

"modelInstanceType": "Standard",

"modelName": "qwen72b",

"modelWeightPath": "/data38/shares/yuchen45/models/qwen/Qwen-72B-Chat/Qwen/Qwen-72B-Chat",

"worldSize": 4,

"cpuMemSize": 5,

"npuMemSize": 8,

"backendType": "atb"

}

]

},

"ScheduleParam":

{

"maxPrefillBatchSize": 50,

"maxPrefillTokens": 8192,

"prefillTimeMsPerReq": 150,

"prefillPolicyType": 0,

"decodeTimeMsPerReq": 50,

"decodePolicyType": 0,

"maxBatchSize": 200,

"maxIterTimes": 512,

"maxPreemptCount": 200,

"supportSelectBatch": false,

"maxQueueDelayMicroseconds": 5000

}

}

qwen1.5部署报错的mindie同上，只修改了模型路径，qwen1.5模型的config如下：

{

"architectures": [

"Qwen2ForCausalLM"

],

"attention_dropout": 0.0,

"bos_token_id": 151643,

"eos_token_id": 151645,

"hidden_act": "silu",

"hidden_size": 5120,

"initializer_range": 0.02,

"intermediate_size": 27392,

"max_position_embeddings": 32768,

"seq_length": 2048,

"max_window_layers": 35,

"model_type": "qwen2",

"num_attention_heads": 40,

"num_hidden_layers": 64,

"num_key_value_heads": 8,

"rms_norm_eps": 1e-06,

"rope_theta": 1000000.0,

"sliding_window": 32768,

"tie_word_embeddings": false,

"torch_dtype": "float16",

"quantize": null,

"transformers_version": "4.37.2",

"use_cache": true,

"use_sliding_window": false,

"vocab_size": 152064

}