---
license: agpl-3.0
language:
- ja
base_model:
- google/gemma-2-2b-it
---


Gemma2 2b Japanese for Embedding generation. 

Base model is Gemma2B JPN-IT published by Google in October 2024.
Gemma2 2B JPN is the smallest Japanese LLM, 
so this is very useful for practical topics. 
(all other Japanese 7B LLM  cannot be used easily for embedding purposes due high inference cost).


This version has been lightly fine tuned on Japanese triplet dataset 
and with triplet loss and quantized into 4bit GGUF format:


Sample using llama-cpp


```
  class GemmaSentenceEmbeddingGGUF:
      def init(self, model_path="agguf/gemma-2-2b-jpn-it-embedding.gguf"):
          self.model = Llama(model_path=model_path, embedding=True)
  
      def encode(self, sentences: list[str], **kwargs) -> list[np.ndarray]:
          out = []
          for sentence in sentences:
              embedding_result = self.model.create_embedding([sentence])
              embedding = embedding_result['data'][0]['embedding'][-1]
              out.append(np.array(embedding))
  
          return out
  
  
  se = GemmaSentenceEmbeddingGGUF()
  se.encode(['こんにちは、ケビンです。よろしくおねがいします'])[0]
```

Access is public for research discussion purpose.

To access to the weight, 
please contact : kevin.noel @ uzabase.com