Feature Extraction
Transformers
Safetensors
sentence-transformers
multilingual
embedding_gemma2
embedding
multimodal-embedding
multimodal
vision
audio
video
image-feature-extraction
audio-feature-extraction
video-feature-extraction
sentence-similarity
unsloth
Instructions to use unsloth/embeddinggemma-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use unsloth/embeddinggemma-2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="unsloth/embeddinggemma-2")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("unsloth/embeddinggemma-2") model = AutoModel.from_pretrained("unsloth/embeddinggemma-2", device_map="auto") - sentence-transformers
How to use unsloth/embeddinggemma-2 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("unsloth/embeddinggemma-2") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
Download tokenizer.model from unsloth/embeddinggemma-2: direct link, hf CLI and curl.
- Browser
- Download file 4.69 MB
-
https://huggingface.co/unsloth/embeddinggemma-2/resolve/main/tokenizer.model
- Command line
-
hf download hf://unsloth/embeddinggemma-2/tokenizer.model
-
curl -L -o tokenizer.model https://huggingface.co/unsloth/embeddinggemma-2/resolve/main/tokenizer.model
4.69 MB
- Xet hash:
- 56f01b381b470fc31af7f5e4b1a429162cc4f80a465e14ad1dcadb282719bb7d
- Size of remote file:
- 4.69 MB
- SHA256:
- e594c8a90eb08d8bda498ff4747977dc827ae0c3c56b5c0d41a605a22d02ef03
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.