From 154e0d75fccf1784fe9ff6fd76a630b66563da3d Mon Sep 17 00:00:00 2001 From: Kawrakow <48489457+ikawrakow@users.noreply.github.com> Date: Sat, 27 Jul 2024 07:55:01 +0200 Subject: Merge mainline llama.cpp (#3) * Merging mainline - WIP * Merging mainline - WIP AVX2 and CUDA appear to work. CUDA performance seems slightly (~1-2%) lower as it is so often the case with llama.cpp/ggml after some "improvements" have been made. * Merging mainline - fix Metal * Remove check --------- Co-authored-by: Iwan Kawrakow --- scripts/convert-gg.sh | 26 -------------------------- 1 file changed, 26 deletions(-) delete mode 100755 scripts/convert-gg.sh (limited to 'scripts/convert-gg.sh') diff --git a/scripts/convert-gg.sh b/scripts/convert-gg.sh deleted file mode 100755 index 8a016843..00000000 --- a/scripts/convert-gg.sh +++ /dev/null @@ -1,26 +0,0 @@ -#!/bin/bash - -set -e - -# LLaMA v1 -python3 examples/convert-legacy-llama.py ../llama1/7B --outfile models/llama-7b/ggml-model-f16.gguf --outtype f16 -python3 examples/convert-legacy-llama.py ../llama1/13B --outfile models/llama-13b/ggml-model-f16.gguf --outtype f16 -python3 examples/convert-legacy-llama.py ../llama1/30B --outfile models/llama-30b/ggml-model-f16.gguf --outtype f16 -python3 examples/convert-legacy-llama.py ../llama1/65B --outfile models/llama-65b/ggml-model-f16.gguf --outtype f16 - -# LLaMA v2 -python3 examples/convert-legacy-llama.py ../llama2/llama-2-7b --outfile models/llama-7b-v2/ggml-model-f16.gguf --outtype f16 -python3 examples/convert-legacy-llama.py ../llama2/llama-2-13b --outfile models/llama-13b-v2/ggml-model-f16.gguf --outtype f16 -python3 examples/convert-legacy-llama.py ../llama2/llama-2-70b --outfile models/llama-70b-v2/ggml-model-f16.gguf --outtype f16 - -# Code Llama -python3 examples/convert-legacy-llama.py ../codellama/CodeLlama-7b/ --outfile models/codellama-7b/ggml-model-f16.gguf --outtype f16 -python3 examples/convert-legacy-llama.py ../codellama/CodeLlama-13b/ --outfile models/codellama-13b/ggml-model-f16.gguf --outtype f16 -python3 examples/convert-legacy-llama.py ../codellama/CodeLlama-34b/ --outfile models/codellama-34b/ggml-model-f16.gguf --outtype f16 - -# Falcon -python3 convert-falcon-hf-to-gguf.py ../falcon/falcon-7b 1 -mv -v ../falcon/falcon-7b/ggml-model-f16.gguf models/falcon-7b/ggml-model-f16.gguf - -python3 convert-falcon-hf-to-gguf.py ../falcon/falcon-40b 1 -mv -v ../falcon/falcon-40b/ggml-model-f16.gguf models/falcon-40b/ggml-model-f16.gguf -- cgit v1.2.3