happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

model-conversion : use CONVERTED_EMBEDDING_MODEL for embedding_verify_logits (#18079) 

This commit updates the embedding model verification script to use the
CONVERTED_EMBEDDING_MODEL environment variable instead of using the
EMBEDDING_MODEL_PATH (the original embedding model path) as the basis
for the converted model file name.

The motivation for this that currently if the converted embedding model
file name differs from the original embedding model directory/name the
verification script will look for the wrong .bin files that were
generating when running the models.
This commit is contained in:
Daniel Bevenius 2025-12-16 11:17:20 +01:00 committed by GitHub
parent c05aa69f32
commit db81d5ec4b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
examples/model-conversion/scripts/embedding/compare-embeddings-logits.sh
View File

@ -34,8 +34,11 @@ done
MODEL_PATH="${MODEL_PATH:-"$EMBEDDING_MODEL_PATH"}" MODEL_PATH="${MODEL_PATH:-"$EMBEDDING_MODEL_PATH"}"
MODEL_NAME="${MODEL_NAME:-$(basename "$MODEL_PATH")}" MODEL_NAME="${MODEL_NAME:-$(basename "$MODEL_PATH")}"
CONVERTED_MODEL_PATH="${CONVERTED_EMBEDDING_PATH:-"$CONVERTED_EMBEDDING_MODEL"}"
CONVERTED_MODEL_NAME="${CONVERTED_MODEL_NAME:-$(basename "$CONVERTED_MODEL_PATH" .gguf)}"
if [ -t 0 ]; then if [ -t 0 ]; then
CPP_EMBEDDINGS="data/llamacpp-${MODEL_NAME}-embeddings.bin" CPP_EMBEDDINGS="data/llamacpp-${CONVERTED_MODEL_NAME}-embeddings.bin"
else else
# Process piped JSON data and convert to binary (matching logits.cpp format) # Process piped JSON data and convert to binary (matching logits.cpp format)
TEMP_FILE=$(mktemp /tmp/tmp.XXXXXX.binn) TEMP_FILE=$(mktemp /tmp/tmp.XXXXXX.binn)