-
I tried to predict using pretrained model as follows:
’
python main.py --root_path data --video_path mit_videos/a064-0224C.mp4 --annotation_path actionlist.csv --result_path results --dataset mit …
-
Hi, the paper seems interesting as the way you have used zig-zag learning to mitigate the domain shift that can perturb the features of student network.
I was trying to reproduce the results for FL…
-
Can any colleague help with the example of interference with the Gemma model in CTranslate2? Unfortunately, there is no information about this model in the documentation.
Thx
-
### Is there an existing issue for this?
- [X] I have searched the existing issues
### Environment
```markdown
- Milvus version:master/2.4
- Deployment mode(standalone or cluster):
- MQ type(rock…
-
110510 26743
121019 26740
121017 26739
106401 26736
104307 26734
103010 26733
71300 26732
127445 26730
120839 26729
123188 26725
this is the features_input
i guess the first col is movie i…
-
Hi, I have searched this package on pypi. Unfortunately, I can't find this 0.7.2 version.
I tried to install other version(0.9.0), but there are some errors when 'from dgl.nn import GraphConv, AvgPoo…
-
[Nucleus sampling](https://arxiv.org/abs/1904.09751) (top-p sampling in HF) is a dynamic sampling strategy that "truncat[es] the unreliable tail of the probability distribution, sampling from the dyna…
-
### Describe the issue as clearly as possible:
When using JSON logits processor, the processor does not mask off the token `SPIECE_UNDERLINE * 2`.``
### Steps/code to reproduce the bug:
```python
i…
-
hi,dear
the nextvlad_final file can't be load ???
```
[INFO: predict.py: 185]: Namespace(batch_size=1, config='configs/attention_cluster.txt', filelist=None, infer_topk=20, log_interval=1, model_n…
-
seems fast-moe still cannot archive running multi experts in parallel with single gpu card?