---
library_name: transformers
tags:
  - smolvlm
  - vlm
  - dpo
  - hallucination-reduction
  - accessibility
  - qlora
  - rlaif
  - gguf
license: apache-2.0
language:
  - en
pipeline_tag: image-text-to-text
base_model: Cubex11/Solari
---

# Solari-GGUF

**GGUF quantized version** of [Solari](https://huggingface.co/Cubex11/Solari) — a 500M parameter vision-language model fine-tuned for reduced hallucination on real-world images.

> For full model details, training procedure, and benchmark analysis, see the [Solari model card](https://huggingface.co/Cubex11/Solari).

> [!WARNING]
> `Solari-f16.gguf` and `Solari_v2-f16.gguf` are **deprecated**. Please use **`Solari_v3-f16.gguf`** for the best results. Older versions may produce incorrect or degraded outputs.

## Model Details

- **Base Model:** [Cubex11/Solari](https://huggingface.co/Cubex11/Solari)
- **Original Base:** [SmolVLM2-500M-Video-Instruct](https://huggingface.co/HuggingFaceTB/SmolVLM2-500M-Video-Instruct)
- **Format:** GGUF (for use with llama.cpp, Ollama, LM Studio, etc.)
- **Fine-tuning Method:** QLoRA + DPO on [RLAIF-V](https://huggingface.co/datasets/HuggingFaceH4/rlaif-v_formatted) (72K preference pairs)
- **License:** Apache-2.0

## Benchmark Results

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** | 27.58 | **28.14** | **+0.56** |
| MME Perception | **1216** | 1119 | -97.7 |
			
> Note: Benchmarks were evaluated on the full-precision model. GGUF quantization may cause minor performance differences.

## Usage

### With llama.cpp

```bash
# Download the GGUF file
huggingface-cli download Cubex11/Solari-GGUF --local-dir ./solari-gguf

# Run inference
./llama-cli -m ./solari-gguf/Solari.gguf -p "Describe this image" --image your_image.jpg
```

### With Ollama

```bash
# Create a Modelfile
echo 'FROM ./Solari.gguf' > Modelfile
ollama create solari -f Modelfile
ollama run solari
```

## Links

- **Full-precision model:** [Cubex11/Solari](https://huggingface.co/Cubex11/Solari)
- **Training dataset:** [RLAIF-V](https://huggingface.co/datasets/HuggingFaceH4/rlaif-v_formatted)
- **Base model:** [SmolVLM2-500M-Video-Instruct](https://huggingface.co/HuggingFaceTB/SmolVLM2-500M-Video-Instruct)

## Citation

```bibtex
@misc{solari2026,
    title={Solari: Hallucination-Reduced Vision Language Model via QLoRA DPO on RLAIF-V},
    author={Cubex11},
    year={2026},
    url={https://huggingface.co/Cubex11/Solari}
}
```