Downloads · 30 days
0
LLAMIAFlux-13b-unprojector-pretrain-t2i-0_5
ssingh22/LLAMIAFlux-13b-unprojector-pretrain-t2i-0_5
LLAMIAFlux-13b-unprojector-pretrain-t2i-0_5 is a machine learning model from ssingh22. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This model was pretrained on the coyo-hd-11m-llavanext dataset to predict CLIP embeddings from text descriptions.
Access
Public
Updated Apr 21, 2025
Repo size
45.2 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt48.1 GB · 100%
At a glance
- Access
- Public
- Created
- Apr 18, 2025
- Updated
- Apr 21, 2025
- SHA
- 34283ce6
Model card
From the Hugging Face model README
LLAMIAFlux - Pretrained Model
This model was pretrained on the coyo-hd-11m-llavanext dataset to predict CLIP embeddings from text descriptions.
- Number of image generation heads: 4
- Training parameters:
- Batch size: 32
- Learning rate: 3e-05
- Weight decay: 0.01
- Epochs: 2
- Model base: ssingh22/LLAMIAFlux-13b-unprojector-inverted
- Trained on 9438926 image-caption pairs from coyo-hd-11m-llavanext
- Trained on 9438926 image-caption pairs from coyo-hd-11m-llavanext
- Created
- Apr 18, 2025
- Updated
- Apr 21, 2025