# Fine Tuning Falcon7B with QLora

**URL:** </static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffine-tuning-falcon7b-with-qlora%2F62238%3E%5C
**Category:** 🤗Transformers\
**Created:** [November 14, 2023, 4:46pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffine-tuning-falcon7b-with-qlora%2F62238 "2023-11-14T16:46:45Z")\
**Posts on this page:** 6\
**Page:** 1

<div class="post-metadata">

**Author:** ![MGDragon](https://avatars.discourse-cdn.com/v4/letter/m/65b543/32.png) [@MGDragon](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FMGDragon)%5C
**Post date:** [November 14, 2023, 4:46pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffine-tuning-falcon7b-with-qlora%2F62238%2F1 "2023-11-14T16:46:45Z")

</div>

Hello  
I am trying to fine tune Falcon7B with only little ressources.  
I found several notebooks and tutorials on how to do it with T4 Colab or only Kaggle.  
But I keep encountering the same error related to this crucial step:

model = prepare\_model\_for\_kbit\_training(model)

Error:

TypeError: FalconPreTrainedModel.\_set\_gradient\_checkpointing() got an unexpected keyword argument ‘enable’

Thank you for your help

---

<div class="post-metadata">

**Author:** ![boda](https://avatars.discourse-cdn.com/v4/letter/b/ecae2f/32.png) [@boda](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fboda)%5C
**Post date:** [November 15, 2023, 8:35am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffine-tuning-falcon7b-with-qlora%2F62238%2F2 "2023-11-15T08:35:17Z")

</div>

In the `TrainingArguments` set `gradient_checkpointing` to false

---

<div class="post-metadata">

**Author:** ![MGDragon](https://avatars.discourse-cdn.com/v4/letter/m/65b543/32.png) [@MGDragon](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FMGDragon)%5C
**Post date:** [November 15, 2023, 10:37am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffine-tuning-falcon7b-with-qlora%2F62238%2F3 "2023-11-15T10:37:41Z")

</div>

Since it’s an online Notebook, I cant modify the code source, do you have an idea of how I can modify it from the notebook itsefl ?

Here is the Notebook

> **[Google Colaboratory](https://colab.research.google.com/drive/1RbWr77vkmmMtTVq94DMYsF0kpm5jHbXO#scrollTo=O75HchDaIbxa&uniqifier=1)**

---

<div class="post-metadata">

**Author:** ![MGDragon](https://avatars.discourse-cdn.com/v4/letter/m/65b543/32.png) [@MGDragon](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FMGDragon)%5C
**Post date:** [November 15, 2023, 10:39am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffine-tuning-falcon7b-with-qlora%2F62238%2F4 "2023-11-15T10:39:07Z")

</div>

Hello,

Thank you for your answer.  
It seems that I can’t change the source code itself.  
here is the notebook [Google Colab](https://colab.research.google.com/drive/1RbWr77vkmmMtTVq94DMYsF0kpm5jHbXO#scrollTo=O75HchDaIbxa&uniqifier=1)  
Do you know what I should change on the notebook in order to make it work ?

---

<div class="post-metadata">

**Author:** ![dillip5](https://avatars.discourse-cdn.com/v4/letter/d/ebca7d/32.png) [@dillip5](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2Fdillip5)%5C
**Post date:** [November 20, 2023, 11:48pm UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffine-tuning-falcon7b-with-qlora%2F62238%2F5 "2023-11-20T23:48:21Z")

</div>

@MGDragon I am also having this issue, please let me know if you find solution for this error.

---

<div class="post-metadata">

**Author:** ![MGDragon](https://avatars.discourse-cdn.com/v4/letter/m/65b543/32.png) [@MGDragon](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Fu%2FMGDragon)%5C
**Post date:** [November 21, 2023, 9:01am UTC](/static-proxy?url=https%3A%2F%2Fdiscuss.huggingface.co%2Ft%2Ffine-tuning-falcon7b-with-qlora%2F62238%2F6 "2023-11-21T09:01:08Z")

</div>

I did:

model = prepare\_model\_for\_kbit\_training(model,use\_gradient\_checkpointing=False)

This should work, and also reduce the batch size afterwards!