Added resizing note
Browse files
README.md
CHANGED
|
@@ -33,6 +33,7 @@ cmake --build build --config Release
|
|
| 33 |
```
|
| 34 |
./path/to/llama-qwen2vl-cli -m path/to/Qwen2-VL-2B-Instruct-F16.gguf --mmproj path/to/qwen2-vl-2b-instruct-vision.gguf -p "Describe this image." --image path/to/image.png
|
| 35 |
```
|
|
|
|
| 36 |
|
| 37 |
|
| 38 |
**Credit to the original model**: https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct
|
|
|
|
| 33 |
```
|
| 34 |
./path/to/llama-qwen2vl-cli -m path/to/Qwen2-VL-2B-Instruct-F16.gguf --mmproj path/to/qwen2-vl-2b-instruct-vision.gguf -p "Describe this image." --image path/to/image.png
|
| 35 |
```
|
| 36 |
+
Note: According to llama.cpp contributors, "it's recommended to resize the image to a resolution below 640x640, so it won't take forever to run on CPU backend"
|
| 37 |
|
| 38 |
|
| 39 |
**Credit to the original model**: https://huggingface.co/Qwen/Qwen2-VL-2B-Instruct
|