mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-11-04 09:32:00 +00:00
40a751ea9a
* model-conversion : remove hardcoded /bin/bash shebangs [no ci] This commit updates the bash scripts to use env instead of using hardcoded /bin/bash in the shebang line. The motivation for this is that some systems may have bash installed in a different location, and using /usr/bin/env bash ensures that the script will use the first bash interpreter found in the user's PATH, making the scripts more portable across different environments. * model-conversion : rename script to .py [no ci] This commit renames run-casual-gen-embeddings-org.sh to run-casual-gen-embeddings-org.py to reflect its Python nature.
49 lines
1.3 KiB
Bash
Executable File
49 lines
1.3 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
|
|
set -e
|
|
|
|
CONVERTED_MODEL="${1:-"$CONVERTED_MODEL"}"
|
|
QUANTIZED_TYPE="${2:-"$QUANTIZED_TYPE"}"
|
|
TOKEN_EMBD_TYPE="${3:-"${TOKEN_EMBD_TYPE}"}"
|
|
OUTPUT_TYPE="${4:-"${OUTPUT_TYPE}"}"
|
|
QUANTIZED_MODEL=$CONVERTED_MODEL
|
|
|
|
# Final check if we have a model path
|
|
if [ -z "$CONVERTED_MODEL" ]; then
|
|
echo "Error: Model path must be provided either as:" >&2
|
|
echo " 1. Command line argument" >&2
|
|
echo " 2. CONVERTED_MODEL environment variable" >&2
|
|
exit 1
|
|
fi
|
|
|
|
if [ -z "$QUANTIZED_TYPE" ]; then
|
|
echo "Error: QUANTIZED_TYPE is required" >&2
|
|
exit 1
|
|
fi
|
|
|
|
echo $CONVERTED_MODEL
|
|
|
|
# Process the quantized model filename
|
|
if [[ "$QUANTIZED_MODEL" == *.gguf ]]; then
|
|
# Remove .gguf suffix, add quantized type, then add .gguf back
|
|
BASE_NAME="${QUANTIZED_MODEL%.gguf}"
|
|
QUANTIZED_MODEL="${BASE_NAME}-${QUANTIZED_TYPE}.gguf"
|
|
else
|
|
echo "Error: QUANTIZED_MODEL must end with .gguf extension" >&2
|
|
exit 1
|
|
fi
|
|
|
|
cmake --build ../../build --target llama-quantize -j8
|
|
|
|
echo $TOKEN_EMBD_TYPE
|
|
echo $OUTPUT_TYPE
|
|
|
|
CMD_ARGS=("../../build/bin/llama-quantize")
|
|
[[ -n "$TOKEN_EMBD_TYPE" ]] && CMD_ARGS+=("--token-embedding-type" "$TOKEN_EMBD_TYPE")
|
|
[[ -n "$OUTPUT_TYPE" ]] && CMD_ARGS+=("--output-tensor-type" "$OUTPUT_TYPE")
|
|
CMD_ARGS+=("$CONVERTED_MODEL" "$QUANTIZED_MODEL" "$QUANTIZED_TYPE")
|
|
|
|
"${CMD_ARGS[@]}"
|
|
|
|
echo "Quantized model saved to: $QUANTIZED_MODEL"
|