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

gguf-split: add --no-tensor-first-split (#7072)

Browse source
This commit is contained in:
Xuan Son Nguyen 2024-05-04 18:56:22 +02:00 • committed by GitHub
parent cf768b7e71
commit 842500144e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 23 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

14
examples/gguf-split/tests.sh
View file

@ -55,15 +55,15 @@ $MAIN --model $WORK_PATH/ggml-model-merge.gguf --random-prompt --n-predict 32
echo PASS
echo
# 4. Split with no tensor in metadata
#$SPLIT --split-max-tensors 32 --no-tensor-in-metadata $WORK_PATH/ggml-model-merge.gguf $WORK_PATH/ggml-model-split-32-tensors
#echo PASS
#echo
# 4. Split with no tensors in the first split
$SPLIT --split-max-tensors 32 --no-tensor-first-split $WORK_PATH/ggml-model-merge.gguf $WORK_PATH/ggml-model-split-32-tensors
echo PASS
echo
# 4b. Test the sharded model is loading properly
#$MAIN --model $WORK_PATH/ggml-model-split-32-tensors-00001-of-00006.gguf --random-prompt --n-predict 32
#echo PASS
#echo
$MAIN --model $WORK_PATH/ggml-model-split-32-tensors-00001-of-00007.gguf --random-prompt --n-predict 32
echo PASS
echo
# 5. Merge
#$SPLIT --merge $WORK_PATH/ggml-model-split-32-tensors-00001-of-00006.gguf $WORK_PATH/ggml-model-merge-2.gguf