issues
search
deepglint
/
RWKV-CLIP
[EMNLP 2024] RWKV-CLIP: A Robust Vision-Language Representation Learner
MIT License
115
stars
8
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
RWKV-CLIP/model/Text_rwkv.py "wkv6_text_birectional" -> "wkv6_text_bidirectional"
#11
joon0425
closed
9 hours ago
1
Request for RWKV-CLIP-B/16 Model Weight
#10
byougert
closed
3 weeks ago
2
方便提供一个直接输入一张图像路径和一个文本字符串计算其相似度的代码吗？
#9
nianfd
closed
4 weeks ago
3
The dataset you uploaded in huggingface is in parquet format, what format did you convert it to during training, it doesn't seem to be reflected in the code.
#8
Pengxiang-zhao
closed
1 month ago
5
Thank you for your contribution. Please tell me how long it took you to train the model on 8 A100 GPUs?
#7
Pengxiang-zhao
closed
1 month ago
2
wkv6_cuda.cu and wkv6_op.cpp
#6
dmmSJTU
closed
1 month ago
1
flickr的json文件
#5
dmmSJTU
closed
2 months ago
1
一些疑问：关于中文，输入长度，搜索
#4
gg22mm
closed
3 months ago
1
Missing requirements.txt File
#3
imljn
closed
4 months ago
2
code
#2
anshkumar
closed
5 months ago
1
arxiv link?
#1
ZihaoZheng98
closed
5 months ago
1