Skip to content

Changes for orcacode experiment#3612

Merged
shahules786 merged 7 commits into
mainfrom
prepare_orcacode
Jul 29, 2023
Merged

Changes for orcacode experiment#3612
shahules786 merged 7 commits into
mainfrom
prepare_orcacode

Conversation

@andreaskoepf

Copy link
Copy Markdown
Collaborator

No description provided.

@shahules786

Copy link
Copy Markdown
Collaborator

Besides this I think there is a bug in this line. Config cannot be updated. I removed it from my version. Can you check that too with this PR? @andreaskoepf

name = "dophin-mix"

def __init__(self, cache_dir, num_samples=100000, max_char_len=8000, seed=42):
def __init__(self, cache_dir, num_samples: Optional[int] = None, max_char_len: int = 8000, seed: int = 42):

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

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

Isn't it better to add data_files as an argument with the default value "flan-5m..."? In this way, we can change to gpt-4 version using config if required.
`

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

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

Can you remove the update_config function definition too since it's not used?

@shahules786

Copy link
Copy Markdown
Collaborator

Nice, thanks.

@shahules786
shahules786 merged commit c2c1318 into main Jul 29, 2023
@shahules786
shahules786 deleted the prepare_orcacode branch July 29, 2023 09:16
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.

3 participants