FlagEmbedding For more details please refer to our Github: FlagEmbedding. BGE Code v1 is an LLM based code embedding model that supports code retrieval, text retrieval, and multilingual retrieval. It primarily demonstrates the following capabilities: Superior Code Retrieval Performance: The model demonstrates exceptional code retrieval capabilities, supporting natural language queries in both English and Chinese, as well as 20 programming languages. Robust Text Retrieval Capabilities: The model maintains strong text retrieval capabilities comparable to text embedding models of similar scale. Extensive Multilingual Support: BGE Code v1 offers comprehensive multilingual retrieval capabilities, excelling in languages such as English, Chinese, Japanese, French, and more. Usage Using FlagEmbedding By default, FlagLLMModel will use all available GPUs when encoding. Please set os.environ["CUDA VISIBLE DEVICES"] to select specific GPUs. You also can set os.environ["CUDA VISIBLE DEVICES"]="" to make all GPUs unavailable. Using Sentence Transformers Using HuggingFace Transformers Evaluation BGE Code v1 achieves state of the art performance on both the CoIR and CodeRAG benchmarks. CoIR CodeXE…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy