Downloads · 30 days
4.3K
6% of all-time downloads
llava-1.6-gguf
cmp-nct/llava-1.6-gguf
llava-1.6-gguf is a image-text-to-text model from cmp-nct. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
Update: PR is merged, llama.cpp now natively supports these models Important: Verify that processing a simple question with any image at least uses 1200 tokens of prompt processing, that shows that the new PR is in us…
All-time downloads
71.2K
Public
Repo size
78.1 GB
Likes
75
Public
Repo makeup
Click a slice to open those files.
.gguf78.1 GB · 100%
At a glance
- Task
- Image-Text-to-Text
- Library
- transformers
- License
- apache-2.0
- Access
- Public
- Created
- Feb 2, 2024
- Updated
- Feb 21, 2024
- SHA
- f2c82bed
Try a prompt
Model card
From the Hugging Face model README
Update: PR is merged, llama.cpp now natively supports these models
Important: Verify that processing a simple question with any image at least uses 1200 tokens of prompt processing, that shows that the new PR is in use.
If your prompt is just 576 + a few tokens, you are using llava-1.5 code (or projector) and this is incompatible with llava-1.6
note Keep in mind the different fine tunes as described in the llama.cpp llava readme, it's essential to use the non defaults for non vicuna models
The mmproj files are the embedded ViT's that came with llava-1.6, I've not compared them but given the previous releases from the team I'd be surprised if the ViT has not been fine tuned this time.
If that's the case, using another ViT can cause issues.
You need to use the mmproj of the right model but you can mix quantizations.
Original models: https://github.com/haotian-liu/LLaVA
- Task
- Image-Text-to-Text
- Library
- transformers
- License
- apache-2.0
- Created
- Feb 2, 2024
- Updated
- Feb 21, 2024