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.

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

Feat(inference): Swap to GenerationConfig #119

Merged
merged 2 commits into from
May 31, 2023

Conversation

NanoCode012
Copy link
Collaborator

@NanoCode012 NanoCode012 commented May 31, 2023

Closes #70

Fixes: #66

@NanoCode012 NanoCode012 changed the title Feat: Swap to GenerationConfig Feat(inference): Swap to GenerationConfig May 31, 2023
scripts/finetune.py Outdated Show resolved Hide resolved
Co-authored-by: Wing Lian <wing.lian@gmail.com>
@NanoCode012
Copy link
Collaborator Author

@winglian , as a future PR, I just realized that we can "load" this config from huggingface. This will allow us to select certain configs and keep using it.

generation_config.save_pretrained("my_account/my_model", push_to_hub=True)

model = AutoModelForCausalLM.from_pretrained("my_account/my_model")
model.generation_config

@NanoCode012 NanoCode012 merged commit fac4600 into axolotl-ai-cloud:main May 31, 2023
@NanoCode012 NanoCode012 deleted the feat/update-inference branch May 31, 2023 05:09
mkeoliya pushed a commit to mkeoliya/axolotl that referenced this pull request Dec 15, 2023
…inference

Feat(inference): Swap to GenerationConfig
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

[Question] Should inference instruction have stripped last new line?
2 participants