# How to merge LoRa weights with base model?

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-merge-lora-weights-with-base-model%2F38584%3E%5C
**Category:** 🤗Transformers\
**Created:** [May 3, 2023, 7:13pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-merge-lora-weights-with-base-model%2F38584 "2023-05-03T19:13:53Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Bastao](https://avatars.discourse-cdn.com/v4/letter/b/b487fb/32.png) [@Bastao](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FBastao)%5C
**Post date:** [May 3, 2023, 7:13pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Fhow-to-merge-lora-weights-with-base-model%2F38584%2F1 "2023-05-03T19:13:53Z")

</div>

Is it possible to merge LoRa adapter weights with a base model like Bloomz?
