mmnga
/

QVQ-72B-Preview-gguf

Inference Endpoints

Model card Files Files and versions Community

mmnga commited on Dec 29, 2024

Commit

c5383d2

·

verified ·

1 Parent(s): dc8f976

Update README.md

Files changed (1) hide show

README.md +3 -2

README.md CHANGED Viewed

@@ -18,6 +18,7 @@ imatrixのデータは[TFMC/imatrix-dataset-for-japanese-llm](https://huggingfac
 ```
 git clone https://github.com/ggerganov/llama.cpp.git
 cd llama.cpp
-make -j
-build/bin/llama-qwen2vl-cli -m QVQ-72B-Preview-IQ4_NL.gguf --mmproj qvq-72b-preview-vision.gguf -p "どんな景色ですか？何が映ってます？"  --image test-image.png
 ```

 ```
 git clone https://github.com/ggerganov/llama.cpp.git
 cd llama.cpp
+cmake -B build -DGGML_CUDA=ON
+cmake --build build --config Release
+build/bin/llama-qwen2vl-cli -m QVQ-72B-Preview-IQ4_NL.gguf --mmproj qvq-72b-preview-vision.gguf -p "どんな景色ですか？何が映ってます？" --image test-image.png
 ```