curl -H "Accept: application/json" -H "Content-type: application/json" --cacert ca.pem --cert client.pem --key client.key.pem -X POST -d '{
"id": "42",
"inputs": [{
"name": "input0",
"shape": [
1,
10
],
"datatype": "UINT32",
"data": [
396, 319, 13996, 29877, 29901, 29907, 3333, 20718, 316, 23924
]
}],
"outputs": [{
"name": "output0"
}],
"parameters": {
"temperature": 0.5,
"top_k": 10,
"top_p": 0.95,
"do_sample": true,
"seed": null,
"repetition_penalty": 1.03,
"max_new_tokens": 20,
"watermark": true
}
}' https://127.0.0.1:1025/v2/models/llama_65b/infer curl -H "Accept: application/json" -H "Content-type: application/json" --cacert ca.pem --cert client.pem --key client.key.pem -X POST -d '{
"id":"a123",
"text_input": "My name is Olivier and I",
"parameters": {
"details": true,
"do_sample": true,
"max_new_tokens":250,
"repetition_penalty": 1.1,
"seed": 123,
"temperature": 1,
"top_k": 10,
"top_p": 0.99,
"batch_size":100,
"typical_p": 0.5,
"watermark": false,
"perf_stat": false
}
}' https://127.0.0.1:1025/v2/models/llama_65b/generatecurl -H "Accept: application/json" -H "Content-type: application/json" --cacert ca.pem --cert client.pem --key client.key.pem -X POST -d '{
"id":"a123",
"text_input": "My name is Olivier and I",
"parameters": {
"details": true,
"do_sample": true,
"max_new_tokens":200,
"repetition_penalty": 1.1,
"seed": 123,
"temperature": 1,
"top_k": 10,
"top_p": 0.99,
"batch_size":100,
"typical_p": 0.5,
"watermark": false,
"perf_stat": false
}
}' https://127.0.0.1:1025/v2/models/llama_65b/generate_stream其他接口请参见兼容Triton接口章节。