docs: fix invalid json in api.md
This commit is contained in:
parent
1f78e409b4
commit
371d4e5df3
21
docs/api.md
21
docs/api.md
|
@ -62,27 +62,28 @@ A stream of JSON objects:
|
||||||
|
|
||||||
The final response in the stream also includes additional data about the generation:
|
The final response in the stream also includes additional data about the generation:
|
||||||
|
|
||||||
|
- `total_duration`: time spent generating the response
|
||||||
|
- `load_duration`: time spent in nanoseconds loading the model
|
||||||
|
- `sample_count`: number of samples generated
|
||||||
|
- `sample_duration`: time spent generating samples
|
||||||
|
- `prompt_eval_count`: number of tokens in the prompt
|
||||||
|
- `prompt_eval_duration`: time spent in nanoseconds evaluating the prompt
|
||||||
|
- `eval_count`: number of tokens the response
|
||||||
|
- `eval_duration`: time in nanoseconds spent generating the response
|
||||||
|
|
||||||
|
To calculate how fast the response is generated in tokens per second (token/s), divide `eval_count` / `eval_duration`.
|
||||||
|
|
||||||
```json
|
```json
|
||||||
{
|
{
|
||||||
"model": "llama2:7b",
|
"model": "llama2:7b",
|
||||||
"created_at": "2023-08-04T19:22:45.499127Z",
|
"created_at": "2023-08-04T19:22:45.499127Z",
|
||||||
"done": true,
|
"done": true,
|
||||||
|
|
||||||
// total time in nanoseconds spent generating the response
|
|
||||||
"total_duration": 5589157167,
|
"total_duration": 5589157167,
|
||||||
|
|
||||||
// time spent in nanoseconds loading the model
|
|
||||||
"load_duration": 3013701500,
|
"load_duration": 3013701500,
|
||||||
|
|
||||||
// Sample: how fast tokens were sampled
|
|
||||||
"sample_count": 114,
|
"sample_count": 114,
|
||||||
"sample_duration": 81442000,
|
"sample_duration": 81442000,
|
||||||
|
|
||||||
// Prompt stats: how fast the prompt was evaluated
|
|
||||||
"prompt_eval_count": 46,
|
"prompt_eval_count": 46,
|
||||||
"prompt_eval_duration": 1160282000,
|
"prompt_eval_duration": 1160282000,
|
||||||
|
|
||||||
// Eval stats: how fast tokens were generated by the model
|
|
||||||
"eval_count": 113,
|
"eval_count": 113,
|
||||||
"eval_duration": 1325948000
|
"eval_duration": 1325948000
|
||||||
}
|
}
|
||||||
|
|
Loading…
Reference in a new issue