Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Update sft_lora_finetune_llm.mdx #765

Closed
wants to merge 1 commit into from
Closed

Update sft_lora_finetune_llm.mdx #765

wants to merge 1 commit into from

Conversation

rhisoni
Copy link

@rhisoni rhisoni commented Jan 22, 2025

  1. Added a line to install the right version of trl
  2. fix the output directory -- specified it to be dolly_llama
  3. Change the number of max cycles from a variable to 11.

@rhisoni
Update sft_lora_finetune_llm.mdx
0d212d8 
1. Added a line to install the right version of trl
2. fix the output directory -- specified it to be dolly_llama 
3. Change the number of max cycles from a variable to 11.
@dacorvo
Copy link
Collaborator

dacorvo commented Jan 30, 2025

Hi @rhisoni thank you for this pul-request. We are currently cleaning up the training tutorials, so I think your pull-request is partially obsolete: could you check if the changes on main introduced by #769 are addressing your issues ?

@dacorvo
Copy link
Collaborator

dacorvo commented Jan 30, 2025

cc @tengomucho

tengomucho
tengomucho reviewed Jan 30, 2025
View reviewed changes
Copy link
Collaborator

@tengomucho tengomucho left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thank you for your contributions! As commented by @dacorvo, this has just been updated in the master branch, so they are not needed anymore. Thanks anyway!

docs/source/training_tutorials/sft_lora_finetune_llm.mdx
@@ -50,6 +50,11 @@ huggingface-cli login --token YOUR_TOKEN
```bash
git clone https://github.com/huggingface/optimum-neuron.git
```
5. Install trl using:
```bash
pip install trl==0.11.4
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We now do this with the extra "training" see here:

optimum-neuron/docs/source/training_tutorials/sft_lora_finetune_llm.mdx

Line 61 in e84e0c6

python -m pip install .[training]

@tengomucho tengomucho closed this Jan 30, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@tengomucho tengomucho tengomucho left review comments

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@rhisoni @dacorvo @tengomucho