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

Add SailorLLM template #5185

Merged
merged 2 commits into from
Aug 19, 2024
Merged

Conversation

chenhuiyu
Copy link
Contributor

@chenhuiyu chenhuiyu commented Aug 15, 2024

What does this PR do?

This PR adds a new template for SailorLLM to the repository, which enhances the system's ability to format user and system inputs according to the SailorLLM format. This template uses the following structure:

  • User Format: <|im_start|>question\n{{content}}<|im_end|>\n<|im_start|>answer\n
  • System Format: <|im_start|>system\n{{content}}<|im_end|>\n
  • Separator: \n
  • Stop Words: ["<|im_end|>"]
  • Replace EOS: True

This addition is based on the SailorLLM's formatting style, as referenced from the SailorLLM repository.

SailorLLM is a suite of Open Language Models for South-East Asia (SEA), focusing on languages like Indonesian, Thai, Vietnamese, Malay, and Lao. Built on Qwen 1.5, Sailor models range from 0.5B to 14B parameters and are fine-tuned for SEA language tasks. Sailor models on Hugging Face. This template supports Sailor models of sizes 0.5B/1.8B/4B/7B/14B.
Fixes # (issue)

No specific issue is linked to this PR.

Before submitting

@hiyouga hiyouga self-requested a review August 19, 2024 15:35
Copy link
Owner

@hiyouga hiyouga left a comment

Choose a reason for hiding this comment

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

LGTM!

@hiyouga hiyouga merged commit f59c9be into hiyouga:main Aug 19, 2024
1 check passed
@hiyouga hiyouga added the solved This problem has been already solved label Aug 19, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
solved This problem has been already solved
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants