| license: apache-2.0 | |
| library_name: libreyolo | |
| base_model: google/gemma-4-E4B-it | |
| tags: | |
| - object-detection | |
| - image-text-to-text | |
| - libreyolo | |
| - vlm | |
| # LibreGemma4e4b | |
| Gemma 4 E4B instruct weights mirrored for LibreYOLO's LibreVLM tier. | |
| ## Source | |
| Mirrored from [google/gemma-4-E4B-it](https://huggingface.co/google/gemma-4-E4B-it) | |
| at commit `ee0ef6023621cff504d758262d4e04895a5af4a2`. | |
| Copyright (c) Google DeepMind. Licensed under the Apache License 2.0. | |
| ## Modifications | |
| No learned parameters were changed. This repository preserves the Hugging Face | |
| snapshot files needed by LibreYOLO's VLM wrapper and replaces the model card | |
| with LibreYOLO-specific loading notes. | |
| ## Usage | |
| ```python | |
| from libreyolo import LibreVLM | |
| model = LibreVLM("gemma-4") | |
| model.set_classes(["person", "helmet"]) | |
| results = model.predict("image.jpg") | |
| ``` | |
| ## License | |
| Apache License 2.0. See [`LICENSE`](./LICENSE) and [`NOTICE`](./NOTICE). | |