issues
search
Yuliang-Liu
/
Monkey
【CVPR 2024 Highlight】Monkey (LMM): Image Resolution and Text Label Are Important Things for Large Multi-modal Models
MIT License
1.82k
stars
128
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
What is the difference between monkey and monkey-chat?
#102
w-qhai
closed
4 months ago
1
Token sampler代码与论文的差异
#101
jfma-USTC
closed
4 months ago
2
RunTimeError: Numpy is not available
#100
ShashankKrishnaV
closed
4 months ago
0
demo_textmonkey.py 模型加载问题
#99
hzy459176895
closed
4 months ago
2
eval/eval_doc.sh中运行是的哪个py脚本呢？
#98
hzy459176895
closed
4 months ago
2
What is the various task-specific augmentations to different dataset mentioned in TextMonkey Sec3.5 ?
#97
double-fire-0
closed
4 months ago
2
模型加载问题
#96
Tzx11
closed
2 months ago
8
demo doesn't give OCR with grounding
#95
jeong-tae
closed
5 months ago
3
Textmonkey有推理代码吗，为什么web demo运行起来不回答
#94
zhangxilin1
closed
5 months ago
1
How to set gpu card for the demo project running
#93
Mararesliu
closed
5 months ago
5
Get the embeddings of the image.
#92
xinyanghuang7
closed
5 months ago
1
vizwiz的准确率仅有37.62？表中的结果为61.2?QwenVL是35.2，请问是数据填写错误吗？
#91
Leavelk
closed
5 months ago
8
How to finetune certain params via from HF's transformers, a
#90
JasonLeeFdu
closed
2 months ago
1
How to finetune only one subnetwork using Deepspeed + Transformers
#89
JasonLeeFdu
closed
2 months ago
1
Will Rico data be released?
#88
YFCYFC
closed
5 months ago
4
textmonkey支持多图输入吗
#87
sky-fly97
closed
6 months ago
1
为什么文档理解的输入不是pdf或者doc文档，而是图片？
#86
Xiaolong-RRL
closed
6 months ago
1
TextMonkey RuntimeError
#85
jweihe
closed
6 months ago
9
Data Access
#84
daniel-z-kaplan
closed
6 months ago
2
A100 40G可以跑通训练吗？全参数SFT和LoRA我在A100 40G报OOM，我debug看到是self.visual.encode(images)就报OOM了
#83
zws-2019
closed
2 months ago
16
TextMonkey问题
#82
songyanbei
closed
6 months ago
2
textMonkey data release
#81
BingranHu
closed
6 months ago
3
Pretrained weight for text monkey
#80
MartinYYYYan
closed
6 months ago
3
Online Demo
#79
jiawei-liu1103
closed
6 months ago
2
Training data
#78
luohao123
closed
6 months ago
1
Does the TextMoney vit has pretrain model?
#77
luohao123
closed
6 months ago
9
run demo.py error
#76
cqray1990
closed
6 months ago
1
TextMonkey
#75
MelosY
closed
6 months ago
0
update dev
#74
MelosY
closed
6 months ago
0
Inconsistency in Performance: Inference Code Yields Poor Results Compared to Online Demo
#73
ashu0013
closed
6 months ago
3
looking forward to TextMonkey model weight and sample code
#72
truebit
closed
6 months ago
2
蹲TextMonkey代码
#71
lyb18758
closed
6 months ago
4
同一幅图，问题变得复杂一些，容易出现不停重复停不下来的情况
#70
charliedream1
closed
7 months ago
1
AttributeError: 'QWenTokenizer' object has no attribute 'IMAGE_ST'
#69
charliedream1
closed
7 months ago
2
性能比在线demo差很多，本地版输出都很简单且短
#68
charliedream1
closed
7 months ago
4
有没有运行demo最低推荐配置呢?
#67
hbh112233abc
closed
7 months ago
1
冻结LLM：需要在finetune_multitask.py中冻结除LoRA和Resampler模块的其他模块
#66
jweihe
closed
7 months ago
5
TextMonkey 在线demo
#65
hsl20130659
closed
6 months ago
11
OOM Issue on 8x40G A100 GPUs Despite Adjustments and Use of modeling_qwen_nvidia3090.py
#64
jweihe
closed
6 months ago
3
Issue with Fine-tuning using LoRA on V100 GPUs
#63
jweihe
closed
7 months ago
1
About the training dataset in Multi-task Training of Monkey
#62
DLUT-LYZ
closed
7 months ago
1
AttributeError: 'Linear' object has no attribute 'bias' during LoRA Training
#61
jweihe
closed
7 months ago
3
Issue with Image Path not Being Correctly Replaced in Training Script
#60
jweihe
closed
7 months ago
2
Questions about train data of TextMonkey†
#59
jpWang
closed
7 months ago
1
使用生成中文描述之外的提示词，结果出现各种错乱
#58
TAOSHss
closed
6 months ago
3
Can we use model weight for commercial purpose?
#57
phuchm
closed
6 months ago
1
demo error
#56
coder4nlp
closed
6 months ago
0
TextMonkey的在线demo使用提示错误
#55
HelloSZS
closed
7 months ago
1
Question about using other LLM models as pre-training models
#54
Sanster
closed
6 months ago
3
modeling_qwen_nvdia3090.py
#53
Ryoo72
closed
7 months ago
1
Previous
Next