-
Is it possible to train Albert from scratch in another language using a TPU v3 (128Gb)?
Could you give an estimated training time? Days, weeks, months?
What is a reasonable corpus size? 1B words…
-
**Describe the bug**
Followed code examples from the documentation to train Llama2 for sentence classification. I have a T4, so I used (as recommended) `lora` adapter and `4-bit` quantization. I even…
-
After the contribution of many people we built a gold standard as reference to indicate if a reimbursement is a generalization or not.
Example of generalization:
[5635048.pdf](http://www.camara.gov.…
-
Hi, thanks for putting this library together. I will put a feature request together in a similar format to the dgl repo:
## 🚀 Feature
Negative sampling with type constraints in `dgl.contrib.sampli…
-
With the benchmark from [here](https://github.com/KindXiaoming/pykan/issues/92) I wrote some optimizations to your cuda kernels to improve the backward while maintaining numerical accuracy with a tole…
-
RuntimeError: expand(torch.FloatTensor{[2, 1025, 475]}, size=[2, 1025]): the number of sizes provided (2) must be greater or equal to the number of dimensions in the tensor (3)
这个怎么处理?
然后我修正了参数 再…
-
Hi,
I wonder if there is a way to compare the performance of causal models that use different set of covariates.
I understand that you developed methods for comparing algorithms (score of second s…
-
It might be nice to have a keyword argument to disable the sorting of classes for `label_binarize`. Sometimes classes have a natural ordering other than lexicographical that I want to preserve in the …
-
Hey @boreshkinai,
I actually read your paper on Hybrik Transformer. I had 1-2 query which I hope gets answered.
For training Hybrik, we require the 3d keypoints, right? what other things woul…
-
Thanks very much for the work!
I am trying something interesting, MTCNN for cat heads!
Unfortunately, I could only have 10,000 labeled cat head example, which is much less than human face datasets. …