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/convert_compatible.py from MirrorNeuronLab/embeddinggemma-2-GGUF: direct link, hf CLI and curl.
- Browser
- Download file 1.82 kB
-
https://huggingface.co/MirrorNeuronLab/embeddinggemma-2-GGUF/resolve/main/reproduce/scripts/convert_compatible.py
- Command line
-
hf download hf://MirrorNeuronLab/embeddinggemma-2-GGUF/reproduce/scripts/convert_compatible.py
-
curl -L -o convert_compatible.py https://huggingface.co/MirrorNeuronLab/embeddinggemma-2-GGUF/resolve/main/reproduce/scripts/convert_compatible.py
1.82 kB
| #!/usr/bin/env python3 | |
| """Run upstream conversion with a lossless Transformers 5 -> 4 config adapter. | |
| The pinned upstream requirements use Transformers 4.57.6. Google's tokenizer | |
| configuration uses Transformers 5's list-valued extra_special_tokens and | |
| model_specific_special_tokens mapping. Supply the equivalent Transformers 4 | |
| arguments in memory; leave all checkpoint and upstream tool files untouched. | |
| """ | |
| import json | |
| import pathlib | |
| import runpy | |
| import sys | |
| from tokenizers import Tokenizer | |
| from transformers import AutoTokenizer | |
| root = pathlib.Path(__file__).resolve().parents[1] | |
| original_loader = AutoTokenizer.from_pretrained | |
| def load_compatible(model_path, *args, **kwargs): | |
| path = pathlib.Path(model_path) | |
| config = json.loads((path / "tokenizer_config.json").read_text()) | |
| extra = config.get("extra_special_tokens") | |
| if isinstance(extra, list): | |
| kwargs["extra_special_tokens"] = config["model_specific_special_tokens"] | |
| kwargs["additional_special_tokens"] = extra | |
| tokenizer = original_loader(model_path, *args, **kwargs) | |
| original = Tokenizer.from_file(str(path / "tokenizer.json")) | |
| assert tokenizer.get_vocab() == original.get_vocab(), "Tokenizer vocabulary or IDs changed" | |
| for name, token in config.get("model_specific_special_tokens", {}).items(): | |
| assert tokenizer.convert_tokens_to_ids(token) == original.token_to_id(token), name | |
| assert token in tokenizer.all_special_tokens, name | |
| print(f"Tokenizer compatibility audit: all {len(tokenizer)} token strings/IDs preserved; all model-specific special tokens preserved.", flush=True) | |
| return tokenizer | |
| AutoTokenizer.from_pretrained = staticmethod(load_compatible) | |
| sys.path.insert(0, str(root / "llama.cpp")) | |
| runpy.run_path(str(root / "llama.cpp/convert_hf_to_gguf.py"), run_name="__main__") | |