Instructions to use google/embeddinggemma-300m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use google/embeddinggemma-300m with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("google/embeddinggemma-300m") sentences = [ "That is a happy person", "That is a happy dog", "That is a very happy person", "Today is a sunny day" ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Inference
- Notebooks
- Google Colab
- Kaggle
MarCognity-AI for google/embeddinggemma-300m
EmbeddingGemma measures similarity.
MarCognity-AI asks: what makes two concepts “close”?
https://huggingface.co/elly99/MarCognity-AI
It’s a semantic cartographer:
– Journals conceptual distances
– Scores cognitive density
– Reflects on the geometry of thought
Not just embedding. Embedding with introspection.
Hi @elly99 ,
"Thank you for sharing the MarCognity-AI project! It’s exciting to see projects built on EmbeddingGemma that explore the deeper implications of semantic space.
The approach of journaling conceptual distances and reflecting on the 'geometry of thought' is highly relevant to current research. It's a great example of augmenting raw embeddings with higher-level analysis.
We appreciate you highlighting this interesting application. Please feel free to share any future developments or quantitative results on measuring conceptual closeness."
Thank you.