char-fork/llama.cpp

git clone https://git.t4t.associates/char-fork/llama.cpp

Fathi Boudracommon: migrate the deprecated --mmap/--no-mmap to --load-mode (#26934)0177dcc73

char/aliceai-t5-moe
brancheschar/aliceai-t5-moeall refs →
481 B11 linesraw
1::  MIT license
2::  Copyright (C) 2024 Intel Corporation
3::  SPDX-License-Identifier: MIT
4
5set INPUT2="Building a website can be done in 10 simple steps:\nStep 1:"
6@call "C:\Program Files (x86)\Intel\oneAPI\setvars.bat" intel64 --force
7
8:: support malloc device memory more than 4GB.
9set UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS=1
10set LOAD_MODE="--load-mode auto"
11.\build\bin\llama-completion.exe -m models\llama-2-7b.Q4_0.gguf -no-cnv -p %INPUT2% -n 400 -e -ngl 99 -s 0 %LOAD_MODE%