From cc3026d695f1a57f5ec54879ab24f57d5dc309ed Mon Sep 17 00:00:00 2001 From: melodyliu1986 Date: Thu, 8 Aug 2024 19:50:11 +0800 Subject: [PATCH] Update run.sh From the https://github.com/ggerganov/llama.cpp/blob/master/Makefile, it said "The 'quantize' binary is deprecated. Please use 'llama-quantize' instead." The command works after my testing using llama-quantize. --- convert_models/run.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/convert_models/run.sh b/convert_models/run.sh index 4961ed1e..2118904b 100644 --- a/convert_models/run.sh +++ b/convert_models/run.sh @@ -20,7 +20,7 @@ python download_huggingface.py --model $hf_model_url --token $hf_token python llama.cpp/examples/convert_legacy_llama.py /opt/app-root/src/converter/converted_models/$hf_model_url python llama.cpp/convert_hf_to_gguf.py /opt/app-root/src/converter/converted_models/$hf_model_url mkdir -p /opt/app-root/src/converter/converted_models/gguf/ -llama.cpp/examples/quantize /opt/app-root/src/converter/converted_models/$hf_model_url/ggml-model-f16.gguf /opt/app-root/src/converter/converted_models/gguf/$model_org-$model_name-${QUANTIZATION}.gguf ${QUANTIZATION} +llama.cpp/llama-quantize /opt/app-root/src/converter/converted_models/$hf_model_url/ggml-model-f16.gguf /opt/app-root/src/converter/converted_models/gguf/$model_org-$model_name-${QUANTIZATION}.gguf ${QUANTIZATION} rm -rf /opt/app-root/src/converter/converted_models/$model_org if [ $keep_orgi = "False" ]; then