Xiaotian Han
Xiaotian Han
Sorry, I do not have and not use the matlab code for HR and NDCG. I use the python code instead. Thank you.
Thanks for your interest in our paper. The UI.data contians the user and item interaction history and each line of this file mean a user click history. For example ,...
I think that the the shape of UI(189621x2 ) is wrong. the shape should be (the amount of user ) x (the amount of item). In your dataset, I think...
I have updated the code and you can try the new code, thanks!
Since in this repo I do not upload more Aspect information(for example, T, V information in amazon datatset), and if you want more information, you should compute the similarity matrix...
Sorry for the late reply. I will organize the data set and upload it. Thanks for your interest.
Glad to see that our method works well with Gemma!! Our python implementation is here https://github.com/datamllab/LongLM/blob/master/gemma_self_extend_patch.py and the llama.cpp implementation is here https://github.com/ggerganov/llama.cpp/blob/cb49e0f8c906e5da49e9f6d64a57742a9a241c6a/examples/main/main.cpp#L569 We are glad to help!!!