arita37b/

gemma2-2B-JPN-Embedding

  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]