Instructions to use thomas-yanxin/Qwen2-VL-7B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use thomas-yanxin/Qwen2-VL-7B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="thomas-yanxin/Qwen2-VL-7B-GGUF",
	filename="Qwen2-VL-7B-Instruct-F16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use thomas-yanxin/Qwen2-VL-7B-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf thomas-yanxin/Qwen2-VL-7B-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf thomas-yanxin/Qwen2-VL-7B-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf thomas-yanxin/Qwen2-VL-7B-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf thomas-yanxin/Qwen2-VL-7B-GGUF:F16

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf thomas-yanxin/Qwen2-VL-7B-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf thomas-yanxin/Qwen2-VL-7B-GGUF:F16

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf thomas-yanxin/Qwen2-VL-7B-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf thomas-yanxin/Qwen2-VL-7B-GGUF:F16

Use Docker

docker model run hf.co/thomas-yanxin/Qwen2-VL-7B-GGUF:F16

LM Studio
Jan
Ollama
How to use thomas-yanxin/Qwen2-VL-7B-GGUF with Ollama:
```
ollama run hf.co/thomas-yanxin/Qwen2-VL-7B-GGUF:F16
```

Unsloth Studio

How to use thomas-yanxin/Qwen2-VL-7B-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for thomas-yanxin/Qwen2-VL-7B-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for thomas-yanxin/Qwen2-VL-7B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for thomas-yanxin/Qwen2-VL-7B-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use thomas-yanxin/Qwen2-VL-7B-GGUF with Docker Model Runner:
```
docker model run hf.co/thomas-yanxin/Qwen2-VL-7B-GGUF:F16
```

Lemonade

How to use thomas-yanxin/Qwen2-VL-7B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull thomas-yanxin/Qwen2-VL-7B-GGUF:F16

Run and chat with the model

lemonade run user.Qwen2-VL-7B-GGUF-F16

List all available models

lemonade list

How to use it

To get the Code:

git clone https://github.com/HimariO/llama.cpp.git
cd llama.cpp
git switch qwen2-vl

nano Makefile #(to add llama-qwen2vl-cli)

diff --git a/Makefile b/Makefile
index 8a903d7e..51403be2 100644
--- a/Makefile
+++ b/Makefile
@@ -1485,6 +1485,14 @@ libllava.a: examples/llava/llava.cpp \
     $(OBJ_ALL)
     $(CXX) $(CXXFLAGS) -static -fPIC -c $< -o $@ -Wno-cast-qual
 
+llama-qwen2vl-cli: examples/llava/qwen2vl-cli.cpp \
+	examples/llava/llava.cpp \
+	examples/llava/llava.h \
+	examples/llava/clip.cpp \
+	examples/llava/clip.h \
+	$(OBJ_ALL)
+	$(CXX) $(CXXFLAGS) $< $(filter-out %.h $<,$^) -o $@ $(LDFLAGS) -Wno-cast-qual
+
 llama-llava-cli: examples/llava/llava-cli.cpp \
     examples/llava/llava.cpp \
     examples/llava/llava.h \

Metal Build

cmake . -DGGML_CUDA=ON -DCMAKE_CUDA_COMPILER=$(which nvcc) -DTCNN_CUDA_ARCHITECTURES=61
make -j35

./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"