Model Card for LLaVa-Phi-2-3B-GGUF
Model Details
Model Description
Quantized version of llava-phi-2-3b. Quantization was done using llama.cpp
- Developed by: LAION, SkunkworksAI & Ontocord
- Model type: LLaVA is an open-source chatbot trained by fine-tuning Phi-2 on GPT-generated multimodal instruction-following data. It is an auto-regressive language model, based on the transformer architecture
- Finetuned from model: Phi-2
- License: MIT
Model Sources
Usage
make & ./llava-cli -m ../ggml-model-f16.gguf --mmproj ../mmproj-model-f16.gguf --image /path/to/image.jpg
Evaluation
Benchmarks
| Model | Parameters | SQA | GQA | TextVQA | POPE |
|---|---|---|---|---|---|
| LLaVA-1.5 | 7.3B | 68.0 | 62.0 | 58.3 | 85.3 |
| MC-LLaVA-3B | 3B | - | 49.6 | 38.59 | - |
| LLaVA-Phi | 3B | 68.4 | - | 48.6 | 85.0 |
| moondream1 | 1.6B | - | 56.3 | 39.8 | - |
| llava-phi-2-3b | 3B | 69.0 | 51.2 | 47.0 | 86.0 |
Image Captioning (MS COCO)
| Model | BLEU_1 | BLEU_2 | BLEU_3 | BLEU_4 | METEOR | ROUGE_L | CIDEr | SPICE |
|---|---|---|---|---|---|---|---|---|
| llava-1.5-7b | 75.8 | 59.8 | 45 | 33.3 | 29.4 | 57.7 | 108.8 | 23.5 |
| llava-phi-2-3b | 67.7 | 50.5 | 35.7 | 24.2 | 27.0 | 52.4 | 85.0 | 20.7 |
- Downloads last month
- 1,064
Unable to determine this model’s pipeline type. Check the
docs
.