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

llama-run : include temperature option (#10899)

Browse source 
This commit updates the `examples/run/README.md` file to include a new
option for setting the temperature and updates the `run.cpp` file to
parse this option.

Signed-off-by: Eric Curtin <ecurtin@redhat.com>
This commit is contained in:
Eric Curtin 2024-12-23 00:21:40 +00:00 • committed by GitHub
parent 7024d59e6a
commit dab76c92cc
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 75 additions and 38 deletions
Download patch file Download diff file Expand all files Collapse all files

2
examples/run/README.md
View file

@ -19,6 +19,8 @@ Options:
Context size (default: 2048)
-n, --ngl <value>
Number of GPU layers (default: 0)
--temp <value>
Temperature (default: 0.8)
-v, --verbose, --log-verbose
Set verbosity level to infinity (i.e. log all messages, useful for debugging)
-h, --help