Update README.md
Browse files
README.md
CHANGED
|
@@ -7,7 +7,7 @@ base_model:
|
|
| 7 |
|
| 8 |
## How to use it
|
| 9 |
|
| 10 |
-
1.
|
| 11 |
```
|
| 12 |
git clone https://github.com/HimariO/llama.cpp.git
|
| 13 |
cd llama.cpp
|
|
@@ -36,16 +36,15 @@ index 8a903d7e..51403be2 100644
|
|
| 36 |
examples/llava/llava.cpp \
|
| 37 |
examples/llava/llava.h \
|
| 38 |
|
| 39 |
-
|
| 40 |
```
|
| 41 |
|
| 42 |
-
3.
|
| 43 |
```
|
| 44 |
cmake . -DGGML_CUDA=ON -DCMAKE_CUDA_COMPILER=$(which nvcc) -DTCNN_CUDA_ARCHITECTURES=61
|
| 45 |
make -j35
|
| 46 |
```
|
| 47 |
|
| 48 |
-
4.
|
| 49 |
```
|
| 50 |
./bin/llama-qwen2vl-cli -m ./thomas-yanxin/Qwen2-VL-7B-GGUF/Qwen2-VL-7B-GGUF-Q4_K_M.gguf --mmproj ./thomas-yanxin/Qwen2-VL-7B-GGUF/qwen2vl-vision.gguf -p "Describe the image" --image "./thomas-yanxin/Qwen2-VL-7B-GGUF/1.png"
|
| 51 |
```
|
|
|
|
| 7 |
|
| 8 |
## How to use it
|
| 9 |
|
| 10 |
+
1. To get the Code:
|
| 11 |
```
|
| 12 |
git clone https://github.com/HimariO/llama.cpp.git
|
| 13 |
cd llama.cpp
|
|
|
|
| 36 |
examples/llava/llava.cpp \
|
| 37 |
examples/llava/llava.h \
|
| 38 |
|
|
|
|
| 39 |
```
|
| 40 |
|
| 41 |
+
3. Metal Build
|
| 42 |
```
|
| 43 |
cmake . -DGGML_CUDA=ON -DCMAKE_CUDA_COMPILER=$(which nvcc) -DTCNN_CUDA_ARCHITECTURES=61
|
| 44 |
make -j35
|
| 45 |
```
|
| 46 |
|
| 47 |
+
4. RUN
|
| 48 |
```
|
| 49 |
./bin/llama-qwen2vl-cli -m ./thomas-yanxin/Qwen2-VL-7B-GGUF/Qwen2-VL-7B-GGUF-Q4_K_M.gguf --mmproj ./thomas-yanxin/Qwen2-VL-7B-GGUF/qwen2vl-vision.gguf -p "Describe the image" --image "./thomas-yanxin/Qwen2-VL-7B-GGUF/1.png"
|
| 50 |
```
|