README.md

---
license: gemma
---

GGUFs of Google's Paligemma 3b 224 mix model. Currently in development so you'll need to use it with https://github.com/ggerganov/llama.cpp/pull/7553 or https://github.com/abetlen/llama-cpp-python/pull/1777

# Installation

```bash
pip install git+https://github.com/abetlen/llama-cpp-python.git@add-paligemma-support
```

# Usage

```python
from llama_cpp import Llama
from llama_cpp.llama_chat_format import PaliGemmaChatHandler

chat_handler = PaliGemmaChatHandler.from_pretrained(
  repo_id="abetlen/paligemma-3b-mix-224-gguf",
  filename="*mmproj*",
)

llm = Llama.from_pretrained(
  repo_id="abetlen/paligemma-3b-mix-224-gguf",
  filename="*text-model-q4_k_m.gguf",
  chat_handler=chat_handler,
  n_gpu_layers=-1,
  n_ctx=2048, # n_ctx should be increased to accommodate the image embedding
  n_ubatch=512, # must be large enough to fit image embeddings and text input in a single batch
  n_batch=512
)

response = llm.create_chat_completion(
    messages = [
        {
            "role": "user",
            "content": [
                {"type" : "text", "text": "What's in this image?"},
                {"type": "image_url", "image_url": {"url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg" } }

            ]
        }
    ]
)
```