Feature Extraction
GGUF
llama.cpp
embeddings
multimodal
vision
audio
image-feature-extraction
audio-feature-extraction
Instructions to use MirrorNeuronLab/embeddinggemma-2-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use MirrorNeuronLab/embeddinggemma-2-GGUF with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible embeddings server: llama serve -hf MirrorNeuronLab/embeddinggemma-2-GGUF:Q4_K_M --embeddings
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible embeddings server: llama serve -hf MirrorNeuronLab/embeddinggemma-2-GGUF:Q4_K_M --embeddings
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible embeddings server: ./build/bin/llama serve -hf MirrorNeuronLab/embeddinggemma-2-GGUF:Q4_K_M --embeddings
- Llama new
- LM Studio
- Jan
- Ollama
How to use MirrorNeuronLab/embeddinggemma-2-GGUF with Ollama:
ollama run hf.co/MirrorNeuronLab/embeddinggemma-2-GGUF:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use MirrorNeuronLab/embeddinggemma-2-GGUF with Docker Model Runner:
docker model run hf.co/MirrorNeuronLab/embeddinggemma-2-GGUF:Q4_K_M
- Lemonade
How to use MirrorNeuronLab/embeddinggemma-2-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull MirrorNeuronLab/embeddinggemma-2-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.embeddinggemma-2-GGUF-Q4_K_M
List all available models
lemonade list
- Atomic Chat
Download reproduce/scripts/download_source.py from MirrorNeuronLab/embeddinggemma-2-GGUF: direct link, hf CLI and curl.
- Browser
- Download file 2.16 kB
-
https://huggingface.co/MirrorNeuronLab/embeddinggemma-2-GGUF/resolve/main/reproduce/scripts/download_source.py
- Command line
-
hf download hf://MirrorNeuronLab/embeddinggemma-2-GGUF/reproduce/scripts/download_source.py
-
curl -L -o download_source.py https://huggingface.co/MirrorNeuronLab/embeddinggemma-2-GGUF/resolve/main/reproduce/scripts/download_source.py
2.16 kB
| #!/usr/bin/env python3 | |
| """Download the original public checkpoint at one immutable Hugging Face revision.""" | |
| import concurrent.futures | |
| import hashlib | |
| import json | |
| import pathlib | |
| import time | |
| import urllib.request | |
| ROOT = pathlib.Path(__file__).resolve().parents[1] | |
| REPO = "google/embeddinggemma-2" | |
| REVISION = "f9972ac22e696a105c482202646979e33e4b5a1e" | |
| url = f"https://huggingface.co/api/models/{REPO}/revision/{REVISION}?blobs=true" | |
| with urllib.request.urlopen(url, timeout=120) as response: | |
| metadata = json.load(response) | |
| assert metadata["sha"] == REVISION | |
| (ROOT / "logs/source-api.json").write_text(json.dumps(metadata, indent=2) + "\n") | |
| def fetch(entry): | |
| name = entry["rfilename"] | |
| path = ROOT / "source" / name | |
| path.parent.mkdir(parents=True, exist_ok=True) | |
| expected = entry.get("lfs", {}).get("sha256") | |
| for attempt in range(4): | |
| try: | |
| digest = hashlib.sha256() | |
| with urllib.request.urlopen(f"https://huggingface.co/{REPO}/resolve/{REVISION}/{name}", timeout=180) as response, path.with_suffix(path.suffix + ".part").open("wb") as target: | |
| while block := response.read(8 * 1024 * 1024): | |
| digest.update(block) | |
| target.write(block) | |
| sha = digest.hexdigest() | |
| if expected: | |
| assert sha == expected, (name, sha, expected) | |
| path.with_suffix(path.suffix + ".part").replace(path) | |
| print(f"{name}: {path.stat().st_size} bytes sha256={sha}", flush=True) | |
| return dict(path=name, size_bytes=path.stat().st_size, sha256=sha, | |
| upstream_lfs_sha256=expected) | |
| except Exception: | |
| if attempt == 3: | |
| raise | |
| time.sleep(2 ** attempt) | |
| with concurrent.futures.ThreadPoolExecutor(max_workers=4) as executor: | |
| files = sorted(executor.map(fetch, metadata["siblings"]), key=lambda item: item["path"]) | |
| (ROOT / "logs/source-manifest.json").write_text(json.dumps(dict(repo_id=REPO, revision=REVISION, files=files), indent=2) + "\n") | |
| (ROOT / "logs/source-SHA256SUMS").write_text("".join(f"{item['sha256']} {item['path']}\n" for item in files)) | |