Vaibhav Adlakha

> In my experiments, the results are _attn_implementation dependent... I am not sure what you mean by this. Can you elaborate? We do not evaluate MNTP task separately as it...

Feel free to re-open if you have any more questions about this issue.

Yes, definitely. Our [scripts](https://github.com/McGill-NLP/llm2vec/tree/main/experiments) provide an example of how to use LORA finetuning for masked next token prediction (MNTP) and supervised contrastive learning. You can similarly use LORA finetuning for...

It is generally recommended to keep the instructions in similar style as used in training. You can check Table 10 in our [paper](https://arxiv.org/pdf/2404.05961) to see the instructions we have used...

Feel free to re-open if you have any more questions regarding this issue.

Which version of llm2vec are you using? The latest version of llm2vec is compatible with transformers 4.40.1. Can you share the exact command that resulted in the error?

Closing as it is stale. Feel free to re-open if you have any more questions regarding this issue.

I changed the code slightly on my end as I did not have access to `data2vec`. ```python import time import matplotlib.pyplot as plt import random import numpy as np import...

For CPU, I got this plot 

Can you try encoding with different batch sizes using any [sentence-transformer models](https://huggingface.co/models?library=sentence-transformers&sort=trending)? Similar to LLM2Vec, you have to call `encode` function with list of sentences. This will help us determine...