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

update help message

Browse source
This commit is contained in:
ngxson 2024-07-24 16:25:26 +02:00
parent cedacf0092
commit 3c965b4f58
2 changed files with 1 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

2
.devops/tools.sh
View file

@ -34,8 +34,6 @@ else
echo " ex: --outtype f16 \"/models/7B/\" "
echo " --quantize (-q): Optimize with quantization process ggml"
echo " ex: \"/models/7B/ggml-model-f16.bin\" \"/models/7B/ggml-model-q4_0.bin\" 2"
echo " --finetune (-f): Run finetune command to create a lora finetune of the model"
echo " See documentation for finetune for command-line parameters"
echo " --all-in-one (-a): Execute --convert & --quantize"
echo " ex: \"/models/\" 7B"
echo " --server (-s): Run a model on the server"

2
Makefile
View file

@ -1566,7 +1566,7 @@ llama-q8dot: pocs/vdot/q8dot.cpp ggml/src/ggml.o \
# Deprecated binaries that we want to keep around long enough for people to migrate to the new filenames, then these can be removed.
#
# Mark legacy binary targets as .PHONY so that they are always checked.
.PHONY: main quantize perplexity embedding server finetune
.PHONY: main quantize perplexity embedding server
# NOTE: We currently will always build the deprecation-warning `main` and `server` binaries to help users migrate.
# Eventually we will want to remove these target from building all the time.