forked from ggerganov/llama.cpp
-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
simple-vision : add initial README.md
- Loading branch information
Showing
1 changed file
with
26 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,26 @@ | ||
### Simple Vision Example | ||
This example demonstrates how to use the vision-api. | ||
|
||
_The Vision API is currently in development_ | ||
|
||
### Building | ||
This can be build with cmake using the following commands: | ||
```console | ||
$ cmake -S . -B build -DGGML_CUDA=On | ||
$ cmake --build build --target llama-simple-vision -- -j 8 | ||
``` | ||
And with make using the following commands: | ||
```console | ||
$ make -j8 GGML_CUDA=1 LLAMA_DEBUG=1 llama-simple-vision | ||
``` | ||
|
||
### Running the example: | ||
The binaries for cmake and make are located in different directories, cmake | ||
are located in the `build/bin` directory and the make binaries are located in | ||
project root directory so use the binary for the build system you used above. | ||
|
||
The example requires that a model is passed in which should be a CLIP model, and | ||
an image to be processed: | ||
```console | ||
$ ./llama-simple-vision -m models/llava-1.5.7b-hf.gguf -c 1024 -v -ngl 20 --image models/eiffel-tower-3349075_1280.jpg | ||
``` |