# Quantize and Optimize summarization model (Seq2SeqLM)

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fquantize-and-optimize-summarization-model-seq2seqlm%2F21549%3E%5C
**Category:** Beginners\
**Created:** [August 12, 2022, 3:44am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fquantize-and-optimize-summarization-model-seq2seqlm%2F21549 "2022-08-12T03:44:55Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Z3K3](https://avatars.discourse-cdn.com/v4/letter/z/a3d4f5/32.png) [@Z3K3](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FZ3K3)%5C
**Post date:** [August 12, 2022, 3:44am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fquantize-and-optimize-summarization-model-seq2seqlm%2F21549%2F1 "2022-08-12T03:44:55Z")

</div>

I want to Quantize and Optimize the [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn), so i can get faster summarization results while reducing the size of the model, i have looked at [Optimum with Huggingface](https://huggingface.co/blog/optimum-inference), but they dont support summarization, and when you try to use it with seq2seq models it actually makes the model larger. I want to know if there any other ways i could optimize or quantize the [facebook/bart-large-cnn](https://huggingface.co/facebook/bart-large-cnn), for better speeds, while still getting similar accuracy