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

Spaces to 4 and other code style cleanup. Notes in README.

Browse source
This commit is contained in:
Randall Fitzgerald 2023-06-09 04:47:18 -04:00
parent ccd85e0a6b
commit a9c34779f6
2 changed files with 842 additions and 842 deletions
Download patch file Download diff file Expand all files Collapse all files

4
examples/server/README.md
View file

@ -23,6 +23,8 @@ Command line options:
## Quick Start
**Note:** The server is not built by default. Make sure to add `LLAMA_BUILD_SERVER=ON` to your CMake command.
To get started right away, run the following command, making sure to use the correct path for the model you have:
### Unix-based systems (Linux, macOS, etc.):
@ -99,7 +101,7 @@ node .
`top_p`: Limit the next token selection to a subset of tokens with a cumulative probability above a threshold P (default: 0.9).
`n_predict`: Set the number of tokens to predict when generating text (default: 128, -1 = infinity).
`n_predict`: Set the number of tokens to predict when generating text. **Note:** May exceed the the limit slightly if the last token is a partial multibyte character. (default: 128, -1 = infinity).
`n_keep`: Specify the number of tokens from the initial prompt to retain when the model resets its internal context.
By default, this value is set to 0 (meaning no tokens are kept). Use `-1` to retain all tokens from the initial prompt.

1680
examples/server/server.cpp
View file

File diff suppressed because it is too large Load diff