issues
search
YiyangZhou
/
POVID
[Arxiv] Aligning Modalities in Vision Large Language Models via Preference Fine-tuning
Apache License 2.0
71
stars
3
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
TRL version
#14
refine-counting
opened
2 days ago
0
Loading adapter weights from /root/autodl-tmp/POVID/checkpoint/output/POVID_stage_one_LoRa_bs2 led to unexpected keys not found in the model:
#13
phkhub
opened
1 month ago
0
ERR! AssertionError: The parameter 447 has already been reduced.
#12
shipengai
closed
2 months ago
4
您实现的dpo和原始dpo不一样。
#11
shipengai
closed
2 months ago
1
Ref model is not used!
#10
shipengai
closed
2 months ago
0
About Chair evaluation
#9
itsqyh
opened
3 months ago
0
Failed to reproduce the score [POPE, ScienceQA]
#8
Wang-Xiaodong1899
opened
3 months ago
0
About the evaluation code
#7
takomc
opened
5 months ago
2
AssertionError: The parameter 447 has already been reduced. Gradient computed twice for this partition. Multiple gradient reduction is currently not supported
#6
zkysss11235
opened
6 months ago
4
About CHAIR evaluation
#5
Kizna1ver
opened
6 months ago
2
Visualize Attention Map
#4
franciscoliu
closed
6 months ago
3
the first loss is not exactly DPO loss
#3
elmiraloo
closed
7 months ago
1
Result for Pope not reproduced [Issue]
#2
rohan598
closed
6 months ago
1
dependencies in `pyproject.toml`
#1
elmiraloo
closed
7 months ago
4