mozilla-ai/llamafile

How do I add the ChatML prompt template to the .args file when creating a llamafile?

Open

#227 opened on Jan 24, 2024

View on GitHub
 (3 comments) (1 reaction) (0 assignees)C++ (24,439 stars) (1,358 forks)batch import
enhancementhelp wanted

Description

Simply something like this:

-template "<|im_start|>system {system_message}<|im_end|> <|im_start|>user {prompt}<|im_end|> <|im_start|>assistant"

or something else entirely?

Contributor guide

Tech stack
cpp
Domain
cli
Issue type
documentation
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
2
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
under 1 hour
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
needs maintainer response
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
clear
Prerequisites
Familiarity with llamafileUnderstanding of .args files
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
80
Research direction
This issue is a user question about adding a ChatML prompt template to the .args file when creating a llamafile. The maintainers should provide instructions or update documentation on how to customize prompt templates. Relevant files include the .args configuration file and any documentation on prompt formatting.