Instructions to use Cubex11/Solari-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Cubex11/Solari-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="Cubex11/Solari-GGUF")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Cubex11/Solari-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Cubex11/Solari-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 Cubex11/Solari-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf Cubex11/Solari-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Cubex11/Solari-GGUF:F16
# Run inference directly in the terminal:
llama cli -hf Cubex11/Solari-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 Cubex11/Solari-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf Cubex11/Solari-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 Cubex11/Solari-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Cubex11/Solari-GGUF:F16

Use Docker

docker model run hf.co/Cubex11/Solari-GGUF:F16

LM Studio
Jan

vLLM

How to use Cubex11/Solari-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Cubex11/Solari-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Cubex11/Solari-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/Cubex11/Solari-GGUF:F16

SGLang

How to use Cubex11/Solari-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Cubex11/Solari-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Cubex11/Solari-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Cubex11/Solari-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Cubex11/Solari-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Ollama
How to use Cubex11/Solari-GGUF with Ollama:
```
ollama run hf.co/Cubex11/Solari-GGUF:F16
```

Unsloth Studio

How to use Cubex11/Solari-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 Cubex11/Solari-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 Cubex11/Solari-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Cubex11/Solari-GGUF to start chatting

Docker Model Runner
How to use Cubex11/Solari-GGUF with Docker Model Runner:
```
docker model run hf.co/Cubex11/Solari-GGUF:F16
```

Lemonade

How to use Cubex11/Solari-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Cubex11/Solari-GGUF:F16

Run and chat with the model

lemonade run user.Solari-GGUF-F16

List all available models

lemonade list

Atomic Chat

Cubex11 commited on Apr 20

Commit

4c9fd68

verified ·

1 Parent(s): 8bf6043

Update README.md

Browse files

Files changed (1) hide show

README.md +9 -9

README.md CHANGED Viewed

@@ -36,15 +36,15 @@ Solari improves on **7 out of 8 benchmarks** vs the base model:
 | Benchmark | Base | **Solari** | Change |
 |-----------|------|------------|--------|
-| **POPE Overall** | 82.67 | **85.08** | **+2.41** ✅ |
-| **POPE Recall** | 76.73 | **85.33** | **+8.60** ✅ |
-| **AMBER Avg** | 79.38 | **79.77** | **+0.39** ✅ |
-| **A-OKVQA** | 68.12 | **69.00** | **+0.88** ✅ |
-| **MMStar** | 38.33 | **39.60** | **+1.27** ✅ |
-| **MMBench** | 53.14 | **53.42** | **+0.28** ✅ |
-| **RealWorldQA** | 49.80 | **50.59** | **+0.78** ✅ |
-| **HallusionBench fAcc** | 18.21 | **19.36** | **+1.16** ✅ |
-| MME Perception | **1216** | 1119 | -97.7 ❌ |
 > Note: Benchmarks were evaluated on the full-precision model. GGUF quantization may cause minor performance differences.

 | Benchmark | Base | **Solari** | Change |
 |-----------|------|------------|--------|
+| **POPE Overall** | 82.67 | **85.08** | **+2.41** |
+| **POPE Recall** | 76.73 | **85.33** | **+8.60** |
+| **AMBER Avg** | 79.38 | **79.77** | **+0.39** |
+| **A-OKVQA** | 68.12 | **69.00** | **+0.88** |
+| **MMStar** | 38.33 | **39.60** | **+1.27** |
+| **MMBench** | 53.14 | **53.42** | **+0.28** |
+| **RealWorldQA** | 49.80 | **50.59** | **+0.78** |
+| **HallusionBench fAcc** | 18.21 | **19.36** | **+1.16** |
+| MME Perception | **1216** | 1119 | -97.7 |
 > Note: Benchmarks were evaluated on the full-precision model. GGUF quantization may cause minor performance differences.