Multimodal Model #6

Open
opened 2024-12-17 23:46:28 +00:00 by james · 2 comments
Owner

Specifically, I want to try unsloth/Llama-3.2-11B-Vision-Instruct-bnb-4bit.

Specifically, I want to try `unsloth/Llama-3.2-11B-Vision-Instruct-bnb-4bit`.
james added the
enhancement
label 2024-12-17 23:46:28 +00:00
Author
Owner

figure out if second model entirely is needed for vision, or if it’s possible to train vision models on datasets without images

figure out if second model entirely is needed for vision, or if it’s possible to train vision models on datasets without images
Author
Owner

when a message is sent to miku with an image, we can just have it infer an image description and offer it as context in the longer langchain instruct prompt; #9

when a message is sent to miku with an image, we can just have it infer an image description and offer it as context in the longer langchain instruct prompt; #9
Sign in to join this conversation.
No Milestone
No project
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: james/MikuAI#6
No description provided.