InternLM / InternLM/InternLM-XComposer
Is the image token always necessary or not for InternLM-XComposer2.5?
Open
- Dominant language
- Python
- Stars
- 2.9k
- Forks
- 175
- PR merge metrics
- No merged PRs in 30d
Description
Hi, simple question about your fantastic model! I see that your multi-image demo uses image tokens while your single high-resolution image demo does not. Is the usage of image tokens only necessary for multiple images? And does not using the image token somehow implicitly indicate high-resolution image inputs or no?
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.