vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

make : deprecate (#10514)

Browse source 
* make : deprecate

ggml-ci

* ci : disable Makefile builds

ggml-ci

* docs : remove make references [no ci]

* ci : disable swift build

ggml-ci

* docs : remove obsolete make references, scripts, examples

ggml-ci

* basic fix for compare-commits.sh

* update build.md

* more build.md updates

* more build.md updates

* more build.md updates

* Update Makefile

Co-authored-by: Diego Devesa <slarengh@gmail.com>

---------

Co-authored-by: slaren <slarengh@gmail.com>
This commit is contained in:
Georgi Gerganov 2024-12-02 21:22:53 +02:00 • committed by GitHub
parent 64ed2091b2
commit 8648c52101
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
11 changed files with 139 additions and 1011 deletions
Download patch file Download diff file Expand all files Collapse all files

61
examples/base-translate.sh
View file

@ -1,61 +0,0 @@
#!/bin/bash
#
# Few-shot translation example.
# Requires a base model (i.e. no fine-tuned or instruct models).
#
# Usage:
#
# cd llama.cpp
# make -j
#
# ./examples/base-translate.sh <model-base> "<text>" [extra-main-args]
#
if [ $# -lt 2 ]; then
echo "Usage: ./base-translate.sh <model-base> \"<text>\" [extra-main-args]"
exit 1
fi
eargs=""
if [ $# -gt 2 ]; then
eargs="${@:3}"
fi
ftmp="__llama.cpp_example_tmp__.txt"
trap "rm -f $ftmp" EXIT
echo "Translate from English to French:
===
sea otter, peppermint, plush girafe:
sea otter => loutre de mer
peppermint => menthe poivrée
plush girafe => girafe peluche
===
violin
violin => violon
===
phone, computer, mouse, keyboard:
phone => téléphone
computer => ordinateur
mouse => souris
keyboard => clavier
===
" > $ftmp
echo "$2
" >> $ftmp
model=$1
# generate the most likely continuation until the string "===" is found
./llama-cli -m $model -f $ftmp -n 64 --temp 0 --repeat-penalty 1.0 --no-penalize-nl -r "===" $eargs

5
examples/convert-llama2c-to-ggml/README.md
View file

@ -2,11 +2,8 @@
This example reads weights from project [llama2.c](https://github.com/karpathy/llama2.c) and saves them in ggml compatible format. The vocab that is available in `models/ggml-vocab.bin` is used by default.
To convert the model first download the models from the [llama2.c](https://github.com/karpathy/llama2.c) repository:
To convert the model first download the models from the [llama2.c](https://github.com/karpathy/llama2.c) repository.
`$ make -j`
After successful compilation, following usage options are available:
```
usage: ./llama-convert-llama2c-to-ggml [options]

2
examples/imatrix/README.md
View file

@ -25,8 +25,6 @@ For faster computation, make sure to use GPU offloading via the `-ngl` argument
## Example
```bash
GGML_CUDA=1 make -j
# generate importance matrix (imatrix.dat)
./llama-imatrix -m ggml-model-f16.gguf -f train-data.txt -ngl 99

15
examples/server/README.md
View file

@ -188,12 +188,6 @@ services:
`llama-server` is built alongside everything else from the root of the project
- Using `make`:
```bash
make llama-server
```
- Using `CMake`:
```bash
@ -207,15 +201,6 @@ services:
`llama-server` can also be built with SSL support using OpenSSL 3
- Using `make`:
```bash
# NOTE: For non-system openssl, use the following:
# CXXFLAGS="-I /path/to/openssl/include"
# LDFLAGS="-L /path/to/openssl/lib"
make LLAMA_SERVER_SSL=true llama-server
```
- Using `CMake`:
```bash