-
### Describe the issue
When attempting to run inference with my fine-tuned LLaVA model using LoRA, I encountered an error. Here's the code snippet I used:
```
from llava.model.builder import load_p…
-
So,This repo help me a lot I even read your blog and this part
* Get pretrained vision encoder from SigLIP or CLIP (both come in difference sizes). Freeze weights (i.e. don’t update during
bac…
-
-
[Grouped Query Attention](https://arxiv.org/abs/2305.13245) improves parameter-efficiency of attention KV projections and reduces IO at inference-time, making inference faster.
It can be implemente…
-
거의 scheming만 했던 논문 모아놓는 곳.
notion에 정리중이었으나 link를 걸기가 어려워서 옮김.
-
### A URL for this dataset
https://pro.europeana.eu/page/iiif#download
### Dataset description
This is a dataset of historic newspapers digitised by various national libraries and made available vi…
-
-
![image](https://user-images.githubusercontent.com/52986798/234012132-d7f660c1-ba5e-4c23-b4af-6187fd80dab1.png)
# Abstract
We mask random patches of the input image and reconstruct the missing pix…
-
## Environment
- Platform: Debian Linux
- GPU: A100
- Torch: '2.1.2+cu121'
- Transfomers: '4.37.2'
## Issue
I'm seeing random and sudden loss spikes during training, if there is a simpler wa…
-
Hi!
Thanks for the great work!
I encountered an issue during the pretraining stage.
I was fine-tuning the vision tower, the linear adapter, and the Large Language Model (LLM) in the pretraining sta…