Giters
magic-research
/
PLLaVA
Official repository for the paper PLLaVA
Geek Repo:
Geek Repo
Github PK Tool:
Github PK Tool
Stargazers:
348
Watchers:
10
Issues:
34
Forks:
20
magic-research/PLLaVA Issues
Bug in tasks/eval/eval_utils.py
Updated
2 days ago
Comments count
1
Hardware specs?
Updated
2 days ago
Comments count
4
Finetune my own's tasks based on pllava-7b, but got "image_to_overwrite.sum() != image_features.shape[:-1].numel()" assertion failure.
Updated
2 days ago
Can PLLaVA caption rectangular videos without cropping?
Updated
2 days ago
demo.sh issues in 34b model
Updated
2 days ago
Comments count
1
finetuning PLLaVA - IMAGEs for Video Analysis
Closed
2 days ago
Comments count
3
Dataset Resquest
Updated
3 days ago
Comments count
2
CLI inference
Updated
3 days ago
ValueError: The input provided to the model are wrong. The number of image tokens is 0 while the number of image given to the model is 1. This prevents correct indexing and breaks batch generation.
Updated
4 days ago
Comments count
4
Demo issues
Updated
7 days ago
Comments count
13
About vram and int-4 version
Updated
7 days ago
Error with Flash attention2 while testing the 34b demo
Closed
9 days ago
Comments count
5
34b can not use gpu
Closed
8 days ago
Encountered an error while running the demo: the data type (dtype) of the llm does not match the data type of the vision model.
Closed
8 days ago
Comments count
2
Missing LICENSE file
Updated
8 days ago
train_pllava_13b.sh运行时会报错
Updated
9 days ago
Comments count
3
No grid configuration in PLLaVA
Updated
9 days ago
Comments count
2
Cannot run demo.sh with pllava-34b
Updated
11 days ago
Comments count
1
Evaluation bug
Closed
12 days ago
Comments count
4
I would like to ask why I can't reproduce your results, the same sora's Tokyo woman video. My model is Pllava-7b.
Updated
12 days ago
Comments count
4
Why are the results in the SOTA table not consistent with ablation studies?
Updated
12 days ago
Comments count
3
Question about fine-tuning
Updated
12 days ago
Issue with multi-GPU inference
Updated
13 days ago
Comments count
1
How to eval using HF?
Updated
15 days ago
Comments count
2
Does it support batch inference
Closed
15 days ago
Comments count
1
Recaption bug.
Updated
16 days ago
Comments count
9
Important ablations and findings missing in your work?
Closed
17 days ago
Comments count
4
Problems encountered in fine-tuning models
Closed
18 days ago
Comments count
5
Errors in your paper
Closed
19 days ago
Comments count
1
Can you give some instructions on fine-tuning?
Closed
19 days ago
Comments count
5
Raw image data
Closed
19 days ago
Comments count
5
provide more demo
Updated
19 days ago
Comments count
2
figure name in paper
Closed
20 days ago
Comments count
1
why does the loss never change during finetune
Closed
20 days ago
Comments count
5