HengranZhang

Reproducing repllama on passage retrieval.

4

Hello, thanks for sharing the great work! I download the checkpoint of repllama from huggiface. I encode the query and passages with this checkpoint and find the result I got...

load the model erro

2

Hi, i meet a problem when load the model using the "tevatron/retriever/driver/encode.py". "lora_name_or_path" is trained with "tevatron/retriever/driver/train.py". I am confused by this problem. Traceback (most recent call last): File "/usr/lib/python3.8/runpy.py",...

Reproducing repllama on document retrieval

3

Hi, @MXueguang~ I am currently reproducing repllama on document retrieval of MSMARCO. In order to reproduce successfully, I need a training set that is consistent with the paper. I would...