-
Hello Bernhard & all,
I have several questions about the querying mode of Channel List and Video List modules.
1) How is represented the boolean operator OR? I tried with comma and | and results…
-
Hello, have you ever run CEDR_KNRM on MSMARCO document ranking task?
I encountered some problems when I trained CEDR_KNRM initialized with the fine-tuned BERT (the performance almost no longer increa…
-
Hello,
I am trying to implement Transformers Interpret for sbert and not able to visualize the output to understand how sbert sentence similarity compares multiple sentences and the keywords which …
-
Hi~I am trying to reproduce the results of RepLLaMA. I have an a800 GPU. If I start training RepLLaMA from scratch with your code, it may take 80 hours? I want to know if this is normal? If possible, …
-
Hi,
While running the multi-GPU training with the below command:
`CUDA_VISIBLE_DEVICES="0,1" python -m torch.distributed.launch --nproc_per_node=2 -m colbert.train \
> --amp --doc_maxlen 18…
-
请问作者，bge-reranker-large 和 bge-reranker-base 的区别 是什么？（以下是我的几个猜想。）
- 训练数据更大？
- 支持更多语言？
- 提供更多选择，根据自己资源配置选 large or base？
我看到了作者在Reranking的模型排名，large相比base在平均得分上高出1%左右
我也看到了其他博主的测评，large相比base看上去对…
-
I notice that when TFrecord is generated, two documents are assigned different segment ids(1, 2). However, the type_vocab_size is 2 according to bert_config.json provided.
So I wonder the actual segm…
-
Hi there,
Is there any way or approach to use the T5 model as a retrieval model in BeIR?
-
Right now, it's possible to train DPR in a single command, via the `tevatron.driver.train` module. However, to evaluate, a more complex series of command (involving lower-level for loops) is needed, e…
-
我使用的环境是
pytorch 1.4.0
transformers 2.8.0
参照着文档https://github.com/thunlp/OpenMatch/blob/master/docs/experiments-msmarco.md 中的训练命令
```
CUDA_VISIBLE_DEVICES=0 \
python train.py\
-task r…