AIが動く。未来が更新される。Vietnamese_Embedding_v2
Vietnamese_Embedding_v2 is an embedding model fine-tuned from the BGE-M3 model (https://huggingface.co/BAAI/bge-reranker-v2-m3) to enhance retrieval capabilities for Vietnamese. Although the score on the legal domain drops a bit on Vietnamese_Embedding (Phase 2), since this phase data is much larger, it is good for other domains. You can reproduce the evaluation result by running code python evaluation_model.py (data downloaded from Kaggle).
翻訳準備中のため原文を表示しています
Vietnamese_Embedding_v2 is an embedding model fine-tuned from the BGE-M3 model (https://huggingface.co/BAAI/bge-reranker-v2-m3) to enhance retrieval capabilities for Vietnamese. Although the score on the legal domain drops a bit on Vietnamese_Embedding (Phase 2), since this phase data is much larger, it is good for other domains. You can reproduce the evaluation result by running code python evaluation_model.py (data downloaded from Kaggle).