deep learning/NLP/RL
deep learning/NLP/RL
啥叫演示代码？
![Uploading 1.png…]()
> 首先，基于bge-large-zh-1.5，难负例微调，微调一个embedding模型 再基于这个微调后的embedding模型，难负例挖掘，微调reranker模型 第二步的neg是80（记得很清楚，因为当时大部分的参数都不行），第一步当时没做多参数的对比测试，用的默认数量，15 BGE 模型分为三步：1. pretrain 2. fineturn 3.rerank 请问你的微调一个embedding模型是指pretrain 和fineturn 之后，对吗？
> How to run the code? Thank you. 同是pku的校友发来疑问
求解决方案，同报错 [2023-12-15 14:01:57,786] torch.distributed.elastic.multiprocessing.api: [ERROR] failed (exitcode: 1) local_rank: 0 (pid: 66887) of binary: /nfs/volume-151-1/gaozhiqiang/miniconda3/envs/case_platform_hdbscan/bin/python Traceback (most recent call last): File "/nfs/volume-151-1/gaozhiqiang/miniconda3/envs/case_platform_hdbscan/bin/torchrun", line 8, in sys.exit(main()) File "/nfs/volume-151-1/gaozhiqiang/miniconda3/envs/case_platform_hdbscan/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 346,...
can you tell me where to find cnn=pickle.load(open('neuralsum/cnn/all.pkl')) dailymail=pickle.load(open('/neuralsum/dailymail/all.pkl')) please!!!!!!!
can you tell me where to find cnn=pickle.load(open('neuralsum/cnn/all.pkl')) dailymail=pickle.load(open('/neuralsum/dailymail/all.pkl')) please