vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

update docs

Browse source
This commit is contained in:
Xuan Son Nguyen 2024-12-11 14:47:49 +01:00
parent 74dc729c0b
commit 7828013689
1 changed files with 32 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

39
examples/server/README.md
View file

@ -343,6 +343,10 @@ node index.js
### POST `/completion`: Given a `prompt`, it returns the predicted completion. ### POST `/completion`: Given a `prompt`, it returns the predicted completion.
> [!IMPORTANT]
>
> This endpoint is **not** OAI-compatible
*Options:* *Options:*
`prompt`: Provide the prompt for this completion as a string or as an array of strings or numbers representing tokens. Internally, if `cache_prompt` is `true`, the prompt is compared to the previous completion and only the "unseen" suffix is evaluated. A `BOS` token is inserted at the start, if all of the following conditions are true: `prompt`: Provide the prompt for this completion as a string or as an array of strings or numbers representing tokens. Internally, if `cache_prompt` is `true`, the prompt is compared to the previous completion and only the "unseen" suffix is evaluated. A `BOS` token is inserted at the start, if all of the following conditions are true:
@ -448,27 +452,48 @@ These words will not be included in the completion, so make sure to add them to
- Note: When using streaming mode (`stream`), only `content` and `stop` will be returned until end of completion. - Note: When using streaming mode (`stream`), only `content` and `stop` will be returned until end of completion.
- `completion_probabilities`: An array of token probabilities for each completion. The array's length is `n_predict`. Each item in the array has the following structure: - `completion_probabilities`: An array of token probabilities for each completion. The array's length is `n_predict`. Each item in the array has a nested array `top_logprobs`. It contains at **maximum** `n_probs` elements:
```json ```json
{ {
"content": "<the token selected by the model>", "content": "<the generated completion text>",
"probs": [ ...
"completion_probabilities": [
{ {
"id": <token id>,
"prob": float, "prob": float,
"tok_str": "<most likely token>" "token": "<most likely token>",
"bytes": [int, int, ...],
"top_logprobs": [
{
"id": <token id>,
"prob": float,
"token": "<token text>",
"bytes": [int, int, ...],
},
{
"id": <token id>,
"prob": float,
"token": "<token text>",
"bytes": [int, int, ...],
},
...
]
}, },
{ {
"id": <token id>,
"prob": float, "prob": float,
"tok_str": "<second most likely token>" "token": "<most likely token>",
"bytes": [int, int, ...],
"top_logprobs": [
...
]
}, },
... ...
] ]
}, },
``` ```
Notice that each `probs` is an array of length `n_probs`.
- `content`: Completion result as a string (excluding `stopping_word` if any). In case of streaming mode, will contain the next token as a string. - `content`: Completion result as a string (excluding `stopping_word` if any). In case of streaming mode, will contain the next token as a string.
- `stop`: Boolean for use with `stream` to check whether the generation has stopped (Note: This is not related to stopping words array `stop` from input options) - `stop`: Boolean for use with `stream` to check whether the generation has stopped (Note: This is not related to stopping words array `stop` from input options)
- `generation_settings`: The provided options above excluding `prompt` but including `n_ctx`, `model`. These options may differ from the original ones in some way (e.g. bad values filtered out, strings converted to tokens, etc.). - `generation_settings`: The provided options above excluding `prompt` but including `n_ctx`, `model`. These options may differ from the original ones in some way (e.g. bad values filtered out, strings converted to tokens, etc.).