Could you share the evaluation scripts for the bge-code-v1 model on the CoIR and CodeRAG benchmarks?

[kartikzheng]

I noticed that the official evaluation results of the bge-code-v1 model on the CoIR and CodeRAG benchmarks are relatively high. I'm curious about some of the test configurations and steps. Could you share the evaluation scripts for the bge-code-v1 model on the CoIR and CodeRAG benchmarks? Thank you very much.

https://modelscope.cn/models/BAAI/bge-code-v1/summary

[545999961]

You can evaluate the model using the following command: https://github.com/FlagOpen/FlagEmbedding/tree/master/research/BGE_Coder#evaluation-script

[kartikzheng]

Thank you very much. I tried it and was able to reproduce the results.