issues
search
Yxxxb
/
VoCo-LLaMA
VoCo-LLaMA: This repo is the official implementation of "VoCo-LLaMA: Towards Vision Compression with Large Language Models".
https://yxxxb.github.io/VoCo-LLaMA-page/
Apache License 2.0
84
stars
4
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
number of token to store visual information
#17
betterze
closed
1 week ago
1
Checkpoints
#16
chriszhenghaochen
closed
1 week ago
1
About training
#15
KaKa-101
closed
2 months ago
0
Could you please provide the code for ablation study with LLaMA-VID
#14
YuchenLiu98
closed
1 week ago
1
implementation of voco token
#13
Cydia2018
closed
3 months ago
1
Find core files
#12
kawhiiiileo
closed
3 months ago
1
Weird loss curve
#11
Andrew-Zhang
closed
4 months ago
2
Evaluation on Video-MME & Temporal Understanding benchmarks
#10
TobiasLee
closed
4 months ago
1
Flash attention and attention mask modification. Does the model support flash attention?
#9
denadai2
closed
5 months ago
1
How to compare the inference time?
#8
Gumpest
closed
5 months ago
4
checkpoint and more benchmark results
#7
Nastu-Ho
closed
5 months ago
1
VoCo-LLaMA checkpoints
#6
pastapeter
closed
5 months ago
1
Hyperparameters for different number of voco tokens
#5
Andrew-Zhang
closed
5 months ago
2
Training Objective
#4
gordonhu608
closed
5 months ago
1
Missing setup.py or pyproject.toml
#3
Andrew-Zhang
closed
5 months ago
2
Final Weights
#2
Andrew-Zhang
closed
5 months ago
2
Congrats
#1
orrzohar
closed
5 months ago
1