Downloads · 30 days
0
qlora-forecast
thijsdekker/qlora-forecast
qlora-forecast is a machine learning model from thijsdekker. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
A xlarge-scale implementation of the blip architecture, built for generation tasks.
Access
Public
Updated Aug 25, 2026
Repo size
—
Likes
0
Public
Repo makeup
Click a slice to open those files.
.py4.6 KB · 67%
At a glance
- License
- mit
- Access
- Public
- Created
- Aug 25, 2026
- Updated
- Aug 25, 2026
- SHA
- 462ab8e5
Model card
From the Hugging Face model README
main.py
Model Overview
A xlarge-scale implementation of the blip architecture, built for generation tasks.
Architecture
- Architecture: blip
- Scale: xlarge
- Attention: multi query
- Fusion strategy: low rank
- Task head: generation
- Activation: relu
- Normalization: layernorm
- Initialization: xavier
Training
- Optimizer: sgd
- LR scheduler: polynomial
Files
main.py— main artifact of this repository
License
See the license field above.
- License
- mit
- Created
- Aug 25, 2026
- Updated
- Aug 25, 2026