issues
search
X-PLUG
/
mPLUG-Owl
mPLUG-Owl: The Powerful Multi-modal Large Language Model Family
https://www.modelscope.cn/studios/damo/mPLUG-Owl
MIT License
2.25k
stars
171
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
对图像进行坐标检测,生成的bbox是resize成正方形之后的值吗?
#199
zhaop-l
opened
8 months ago
5
Is there model checkpoint for multi-language(mainly chinese) videos?
#198
abeldafa
opened
8 months ago
0
The code and detailed implementation of Figure 4 and Figure 5 in the paper mPLUG-Owl2
#197
Zlatan-Ibrahi
opened
9 months ago
1
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:2 and cuda:0! (when checking argument for argument weight in method wrapper_CUDA__cudnn_convolution)
#196
wanghanyang123
opened
9 months ago
0
The Quick Start Code cannot be executed in mPLUG-Owl2
#195
ppsmk388
opened
9 months ago
8
implementation of pre-training stage
#194
annopackage
opened
9 months ago
0
cur_input_embeds = torch.cat([cur_input_embeds_1, cur_image_features[0:0], cur_input_embeds_2], dim=0),其中cur_image_features[0:0]表示这是一个没有维度的向量,图像的特征并没有真正加进去
#193
hangzeli05
opened
9 months ago
1
Encountered flash_attn_2_cuda error while running finetune_lora.sh
#192
pradipto111
opened
10 months ago
1
unable to load model
#191
segalinc
opened
10 months ago
3
RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cpu)
#190
LianghuiGuo
opened
10 months ago
2
Can you release the pre-trained ckpt (without sft) for mplug-owl2?
#189
waltonfuture
opened
10 months ago
0
mPLUG-Owl2,finetune,训练卡住没有输出
#188
LianghuiGuo
opened
10 months ago
5
Thanks for the great work! I am wondering whether mPLUG-Owl2 have OCR ability?
#187
LianghuiGuo
opened
10 months ago
0
🩹 make load_pretrained_model accept kwargs
#186
l-salewski
closed
8 months ago
0
Evaluation Script For The Other Benchmarks
#185
chancharikmitra
opened
10 months ago
1
从modelscope下载的权重,用给的示例代码做Inference,有的权重好像没有加载上,这个有影响么
#184
LianghuiGuo
closed
10 months ago
2
NameError: name 'repeat_kv' is not defined
#183
nullnameno
opened
10 months ago
1
加载本地模型报错
#182
LianghuiGuo
closed
10 months ago
1
Does mPLUG-Owl2 support Chinese? Or are there plans to release a new multilingual version?
#181
BaoyanWang
closed
10 months ago
1
请问是否支持中文数据微调呀?May I finetune mPLUG-Owl with chinese image-text pair?
#180
LianghuiGuo
opened
10 months ago
2
Have you tuned the vision model in sft stage?
#179
xmy0916
closed
10 months ago
2
duplicate outputs when trying the readme snipped inference code
#178
segalinc
closed
10 months ago
0
Question about the weight decay
#177
YifanXu74
closed
10 months ago
1
how many tuning parameters?
#176
adda1221
closed
10 months ago
1
Mplug_owl 2 support video training?
#175
YuzhouPeng
closed
10 months ago
3
Dose mPLUG-Owl2 support Chinese?
#174
Little-Yeah
closed
10 months ago
1
OOM when finetune lora zero3 mPLUG-Owl2 on 4-A100-40g
#173
NamiKaze7
opened
10 months ago
1
When i run mPLUG-Owl 7B (Multilingual) web_demo RuntimeError: expected scalar type Float but found Half
#172
ShelterWFF
opened
10 months ago
0
RuntimeError: expected scalar type Float but found Half
#171
ShelterWFF
opened
10 months ago
0
The pretrained weight and Instruction tuning weight is same
#170
buaachen1993
closed
10 months ago
1
The video is not supported?
#169
Shame-fight
closed
10 months ago
1
tokenizers-lib does not compile on pip install
#168
FlatMapIO
opened
10 months ago
1
NameError: name 'Enum' is not defined
#167
ShelterWFF
opened
10 months ago
2
Fix loading with .from_pretrained() on transformers==4.34.1
#166
admk
closed
11 months ago
1
Does anyone have a successful deployment of local server?Too many questions!
#165
ShelterWFF
opened
11 months ago
0
Could not create share link. Please check your internet connection or our status page: https://status.gradio.app
#164
ShelterWFF
opened
11 months ago
0
Why can only CPU be used for video inference code in reademe? Is there any code that uses GPU for inference?
#163
Fly-hub
opened
11 months ago
1
Did you use the full LAION-400M and COYO-700M dataset for pre-training, or just sampled subsets. What's your total amount of image-text pairs for pre-training?
#162
linserSnow
closed
11 months ago
1
*** RuntimeError: "compute_columns3d" not implemented for 'Half'
#161
BinZhu-ece
opened
11 months ago
4
Error(s) in loading state_dict for MplugOwlForConditionalGeneration (video ):
#160
2023luckyboy
opened
11 months ago
2
Details of Lora's fine tuning
#159
AshOneN
closed
11 months ago
1
Thread worker: Error sending packet
#158
ceyxasm
opened
12 months ago
0
mplug video forward pass issue
#157
kcz358
opened
1 year ago
4
video checkpoint
#156
Xiuyuan-Chen
opened
1 year ago
0
[Feature Request] Support new-version transformers
#155
kennymckormick
opened
1 year ago
1
The loss value of stage2.
#154
Ivesfu
opened
1 year ago
0
what is the difference among the four task_types?
#153
BaoyanWang
opened
1 year ago
2
请问是否支持中文数据的微调
#152
yazheng0307
closed
11 months ago
1
Tuning multimodal pretrained model, using BloomTokenizerFast
#151
TonyAlbertWan
closed
1 year ago
1
fix typo in README.md
#150
LumenYoung
opened
1 year ago
0
Previous
Next