Duo Wang

RuntimeError: offset output dims: (160, 160) - computed output dims: (80, 80)

7

### 🐛 Describe the bug I run source build pytorch(torch==1.10.0) and torchvision(torchvision==0.12.0). train code snippet: ``` from torchvision.ops import DeformConv2d as ModulatedDeformConv conv_op = ModulatedDeformConv offset_channels = 27 self.conv2_offset =...

Can gpl be used on Chinese models?

6

Great job! Can I use gpl on Chinese models please? Which query generator model should I use? Which base models should be used? Which retrieval model should be used? Looking...

Pretrained models

8

@valencebond Hello, where can I find demo.py and the pre-trained model?

FileNotFoundError: [Errno 2] No such file or directory: '/opt/conda/lib/python3.7/site-packages/megatron_util/fused_kernels/build/lock'

1

When i train 'damo/nlp_gpt3_text-generation_2.7B', the error as title. Could you help me? @huangshenno1 When i train 'damo/nlp_gpt3_text-generation_chinese-base', the error is: AssertionError: intra_layer_model parallel group is not initialized I use 2...

convert_dont_stop_corpus.py file not found

2

很novel的思想！很受启发！点赞 在readme中， convert_dont_stop_corpus.py 好像找不到了 After downloading, please convert them to *.tsv files referring to the script [convert_dont_stop_corpus.py](https://github.com/shizhediao/Black-Box-Prompt-Learning/blob/main/data/convert_dont_stop_corpus.py). 请问您能提供此文件的内容吗？非常感谢