# Pegasus Questions

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fpegasus-questions%2F838%3E%5C
**Category:** 🤗Transformers\
**Created:** [August 24, 2020, 2:56pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fpegasus-questions%2F838 "2020-08-24T14:56:22Z")\
**Posts on this page:** 1\
**Showing post:** 29

<div class="post-metadata">

**Author:** ![silvia-casola](https://avatars.discourse-cdn.com/v4/letter/s/ee7513/32.png) [@silvia-casola](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fsilvia-casola)%5C
**Post date:** [June 15, 2021, 12:20pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fpegasus-questions%2F838%2F29 "2021-06-15T12:20:09Z")

</div>

I’m trying to exactly understand the differences among the pre-trained Pegasus models.

As far as I understood:

- models like google/pegasus-\* (e.g google/pegasus-xsum) are base models
- all base models are fine-tuned on a dataset (e.g. xsum in the previous example)
- google/pegasus-large is only pretrained (on C4 and Newsroom?)
- sshleifer/distill-pegasus-\* and sshleifer/student\_pegasus-\* are distilled models
- google/bigbird-pegasus-large-\* use the bigbird attention mechanism.

My questions are the following:

1. Is my understanding correct?
2. Is there any way to get a base Pegasus which is not fine-tuned on a downstream dataset?
3. Is google/pegasus-multi\_news multilingual?
4. As for the distilled models, what is the difference between a distill-\* and a student-\* model? And what do the two numbers represent (e.g. in sshleifer/distill-pegasus-cnn-16-4)?

Thank you very much and thanks for all the work.

---

_[View the full topic](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fpegasus-questions%2F838)._