Update README.md
Browse files
README.md
CHANGED
|
@@ -5,7 +5,9 @@ thanks to :https://github.com/HimariO/llama.cpp/tree/qwen2-vl
|
|
| 5 |
Follow steps:
|
| 6 |
|
| 7 |
1 Download `turingevo/Qwen2-VL-2B-Instruct-gguf`
|
|
|
|
| 8 |
2 `git clone https://github.com/HimariO/llama.cpp/tree/qwen2-vl` then build ,get target `llama-qwen2vl-cli`
|
|
|
|
| 9 |
3 Get pictures:
|
| 10 |
It's recommended to resize the image to a resolution below 640x640, so it won't take forever to run on CPU backend:
|
| 11 |
`ffmpeg -i input.jpeg -vf "scale=512:512" 1.png`
|
|
|
|
| 5 |
Follow steps:
|
| 6 |
|
| 7 |
1 Download `turingevo/Qwen2-VL-2B-Instruct-gguf`
|
| 8 |
+
|
| 9 |
2 `git clone https://github.com/HimariO/llama.cpp/tree/qwen2-vl` then build ,get target `llama-qwen2vl-cli`
|
| 10 |
+
|
| 11 |
3 Get pictures:
|
| 12 |
It's recommended to resize the image to a resolution below 640x640, so it won't take forever to run on CPU backend:
|
| 13 |
`ffmpeg -i input.jpeg -vf "scale=512:512" 1.png`
|