| --- |
| quantized_by: cjpais |
| base_model: vikhyatk/moondream2 |
| pipeline_tag: image-text-to-text |
| license: apache-2.0 |
| tags: |
| - llamafile |
| --- |
| |
| A [llamafile](https://github.com/Mozilla-Ocho/llamafile) generated for [moondream2](https://huggingface.co/vikhyatk/moondream2) |
|
|
| Big thanks to [@jartine](https://huggingface.co/jartine) and [@vikhyat](https://huggingface.co/vikhyatk/moondream2) for their respective works on llamafile and moondream |
|
|
| ## How to Run (on macos and linux) |
|
|
|
|
| 1. Download moondream2.llamafile |
| 2. `chmod +x moondream2.llamafile` - make it executable |
| 3. `./moondream2.llamafile` - run the llama.cpp server |
|
|
| ## Versions |
|
|
| 1. [Q5_M](https://huggingface.co/cjpais/moondream2-llamafile/resolve/main/moondream2-q5_k.llamafile?download=true) |
| 2. [Q8_0](https://huggingface.co/cjpais/moondream2-llamafile/resolve/main/moondream2-q8.llamafile?download=true) |
|
|
| From my short testing the Q8 is noticeably better. |
|
|
| # ORIGINAL MODEL CARD |
|
|
| moondream2 is a small vision language model designed to run efficiently on edge devices. Check out the [GitHub repository](https://github.com/vikhyat/moondream) for details, or try it out on the [Hugging Face Space](https://huggingface.co/spaces/vikhyatk/moondream2)! |
|
|
| **Benchmarks** |
|
|
| | Release | VQAv2 | GQA | TextVQA | TallyQA (simple) | TallyQA (full) | |
| | --- | --- | --- | --- | --- | --- | |
| | 2024-03-04 | 74.2 | 58.5 | 36.4 | - | - | |
| | 2024-03-06 | 75.4 | 59.8 | 43.1 | 79.5 | 73.2 | |
| | 2024-03-13 | 76.8 | 60.6 | 46.4 | 79.6 | 73.3 | |
| | **2024-04-02** (latest) | 77.7 | 61.7 | 49.7 | 80.1 | 74.2 | |
|
|
| **Usage** |
|
|
| ```bash |
| pip install transformers einops |
| ``` |
|
|
| ```python |
| from transformers import AutoModelForCausalLM, AutoTokenizer |
| from PIL import Image |
| |
| model_id = "vikhyatk/moondream2" |
| revision = "2024-04-02" |
| model = AutoModelForCausalLM.from_pretrained( |
| model_id, trust_remote_code=True, revision=revision |
| ) |
| tokenizer = AutoTokenizer.from_pretrained(model_id, revision=revision) |
| |
| image = Image.open('<IMAGE_PATH>') |
| enc_image = model.encode_image(image) |
| print(model.answer_question(enc_image, "Describe this image.", tokenizer)) |
| ``` |
|
|
| The model is updated regularly, so we recommend pinning the model version to a |
| specific release as shown above. |
