mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 04:04:14 +00:00
78 lines
2.1 KiB
JSON
78 lines
2.1 KiB
JSON
{
|
|
"request": {
|
|
"method": "POST",
|
|
"url": "http://localhost:8000/v1/v1/completions",
|
|
"headers": {},
|
|
"body": {
|
|
"model": "meta-llama/Llama-3.2-1B-Instruct",
|
|
"prompt": "Hello, world!",
|
|
"stream": false,
|
|
"extra_body": {
|
|
"prompt_logprobs": 0
|
|
}
|
|
},
|
|
"endpoint": "/v1/completions",
|
|
"model": "meta-llama/Llama-3.2-1B-Instruct"
|
|
},
|
|
"response": {
|
|
"body": {
|
|
"__type__": "openai.types.completion.Completion",
|
|
"__data__": {
|
|
"id": "cmpl-eca3197888914854a6ed09e551908a70",
|
|
"choices": [
|
|
{
|
|
"finish_reason": "length",
|
|
"index": 0,
|
|
"logprobs": null,
|
|
"text": " I am a simple program written in Python. Here is my code:\n```\n",
|
|
"stop_reason": null,
|
|
"prompt_logprobs": [
|
|
null,
|
|
{
|
|
"9906": {
|
|
"logprob": -9.223112106323242,
|
|
"rank": 466,
|
|
"decoded_token": "Hello"
|
|
}
|
|
},
|
|
{
|
|
"11": {
|
|
"logprob": -1.4462913274765015,
|
|
"rank": 1,
|
|
"decoded_token": ","
|
|
}
|
|
},
|
|
{
|
|
"1917": {
|
|
"logprob": -5.506766319274902,
|
|
"rank": 10,
|
|
"decoded_token": " world"
|
|
}
|
|
},
|
|
{
|
|
"0": {
|
|
"logprob": -1.1048365831375122,
|
|
"rank": 2,
|
|
"decoded_token": "!"
|
|
}
|
|
}
|
|
]
|
|
}
|
|
],
|
|
"created": 1758035876,
|
|
"model": "meta-llama/Llama-3.2-1B-Instruct",
|
|
"object": "text_completion",
|
|
"system_fingerprint": null,
|
|
"usage": {
|
|
"completion_tokens": 16,
|
|
"prompt_tokens": 5,
|
|
"total_tokens": 21,
|
|
"completion_tokens_details": null,
|
|
"prompt_tokens_details": null
|
|
},
|
|
"kv_transfer_params": null
|
|
}
|
|
},
|
|
"is_streaming": false
|
|
}
|
|
}
|