Spaces:
Running on Zero
Running on Zero
|
Download README.md from jrhode666/embeddinggemma-2-explorer: direct link, hf CLI and curl.
- Browser
- Download file 1.05 kB
-
https://huggingface.co/spaces/jrhode666/embeddinggemma-2-explorer/resolve/main/README.md
- Command line
-
hf download hf://spaces/jrhode666/embeddinggemma-2-explorer/README.md
-
curl -L -o README.md https://huggingface.co/spaces/jrhode666/embeddinggemma-2-explorer/resolve/main/README.md
1.05 kB
| title: EmbeddingGemma 2 Explorer | |
| emoji: 🧭 | |
| colorFrom: indigo | |
| colorTo: purple | |
| sdk: gradio | |
| sdk_version: 6.30.0 | |
| app_file: app.py | |
| short_description: Any-to-any search with EmbeddingGemma 2 | |
| python_version: "3.12" | |
| startup_duration_timeout: 30m | |
| license: apache-2.0 | |
| models: | |
| - google/embeddinggemma-2 | |
| tags: | |
| - embeddings | |
| - multimodal | |
| - mcp-server | |
| # EmbeddingGemma 2 Explorer | |
| Interactive demo for [google/embeddinggemma-2](https://huggingface.co/google/embeddinggemma-2) — one 768-d vector space for text, images, audio and video. | |
| - **Any-to-any search** — query with text, an image, audio or a video and rank a mixed corpus of text, images and audio. | |
| - **Text retrieval & Matryoshka** — task-prefixed search (web search, QA, fact checking, code) with ranks shown at 768 / 512 / 256 / 128 dims. | |
| - **Similarity matrix** — cross-lingual pairwise similarity heatmap. | |
| - **Embed** — raw vectors, also exposed through the API and as an MCP server. | |
| Runs in bfloat16 on ZeroGPU. Sample media comes from Hugging Face documentation datasets. | |