Pinned issues
Issues
- 2
- 0
Question for mplug-owl v1 model code
#223 opened by bellos1203 - 0
mPLUG-owl2: RuntimeError: probability tensor contains either `inf`, `nan` or element < 0
#222 opened by liuxuannan - 0
Question about Abstractor's FFN and Attention
#219 opened by jp1924 - 0
The attention mask and pad token id were not set.
#221 opened by Evanwu1125 - 1
- 2
Owl2中使用的Vit-H-16是从哪个版本初始化的?
#218 opened by OpenJarvisAI - 0
ms-swift对于mPLUG-Owl2和mPLUG-Owl2.1微调(finetune)的支持
#217 opened by Jintao-Huang - 0
mplug-owl2-llama2-7b initialization error
#216 opened by lihong2303 - 0
mPLUG-Owl2.1输出全是英文
#215 opened by Cloopen-ReLiNK - 0
- 0
- 0
Please can you split the model into 4GB chunks rather than 1 x 16GB. SafeTensors would be a nice addition also.
#211 opened by doreilly257 - 3
- 1
The code and detailed implementation of Figure 4 and Figure 5 in the paper mPLUG-Owl2
#197 opened by Zlatan-Ibrahi - 0
- 0
Zero3 train: Invalidate trace cache @ step 391: expected module 25, but got module 5
#208 opened by Zhiyuan-Fan - 3
cls_token problem with image.
#207 opened by evertonipx - 8
- 0
Issue with gradio webui
#206 opened by vamsikrishyvk - 0
Cannot run inference
#205 opened by findalexli - 4
- 1
other downstream tasks available? Like Visual Reasoning, requires the model to predict whether a sentence describes a pair of images
#204 opened by fansticOne - 1
The updated owl2 based on qwen14b?
#203 opened by luohao123 - 5
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 opened by zhaop-l - 1
file configuration_qwen.py not found
#201 opened by vd001 - 1
No module named 'mplug_owl2.model.multiway
#202 opened by YHWmz - 0
- 3
unable to load model
#191 opened by segalinc - 1
- 0
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 opened by wanghanyang123 - 1
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 opened by hangzeli05 - 1
NameError: name 'repeat_kv' is not defined
#183 opened by nullnameno - 5
mPLUG-Owl2,finetune,训练卡住没有输出
#188 opened by LianghuiGuo - 2
RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cpu)
#190 opened by LianghuiGuo - 0
implementation of pre-training stage
#194 opened by annopackage - 0
- 2
- 0
Thanks for the great work! I am wondering whether mPLUG-Owl2 have OCR ability?
#187 opened by LianghuiGuo - 2
- 1
Evaluation Script For The Other Benchmarks
#185 opened by chancharikmitra - 1
加载本地模型报错
#182 opened by LianghuiGuo - 1
Does mPLUG-Owl2 support Chinese? Or are there plans to release a new multilingual version?
#181 opened by BaoyanWang - 2
Have you tuned the vision model in sft stage?
#179 opened by xmy0916 - 1
Question about the weight decay
#177 opened by YifanXu74 - 1
how many tuning parameters?
#176 opened by adda1221 - 0
- 3
Mplug_owl 2 support video training?
#175 opened by YuzhouPeng - 1
Dose mPLUG-Owl2 support Chinese?
#174 opened by Little-Yeah - 0