-
# Add special tokens to request (or not) metadata generation
## Feature details
We would like to add an argument to `MetadataConfig` that would control whether the model should generate one type o…
-
Executing the example:
```python
import torch
from h_transformer_1d import HTransformer1D
model = HTransformer1D(
num_tokens = 256, # number of tokens
dim = 512, …
-
```r
> data_tm1
# A tibble: 1,151,978 x 15
index BidOpen BidHigh BidLow BidClose AskOpen AskHigh AskLow AskClose year week
1 2014-12…
-
Found that for the causal attention setup the model still has an issue when not using maximum seq length input:
```python
import torch
from h_transformer_1d import HTransformer1D
model = HTran…
-
First of all, using the framework has been very useful already!
I am having two kinds of errors and don't know why. I use GPT2 architecture (in repository example notebook) successfully trained and…
-
- News
- CVPR 2021: 뭔가 운영이.. 영... 요약기사: http://www.aitimes.com/news/articleView.html?idxno=139176
- SIGIR 2021: 7월 11일 부터
- MWC 2021: https://news.naver.com/main/read.nhn?mode=LSD&mid=sec&sid…
-
- AI News
- ICCV notification out: accept letter 받으신 모든 분들 축하드립니다!
- IBM Watson 의 현주소
- NYT: https://www.nytimes.com/2021/07/16/technology/what-happened-ibm-watson.html
- 국내: https://…
-
Hi, I want to repre-train CodeGPT and CodeGPT-adapted models for code generation. How are these models pretrained? Do you plan to share the pre-train code?
-
## 🐛 Bug
### To Reproduce
Steps to reproduce the behavior (**always include the command you ran**):
I got this error when I try to evaluate a trained non-autoregressive MT model.
```ba…
-
**Description**
Librosa typically operates on one-dimensional, one-channel signals whose shape is `(n_samples,)`. In some cases, stereo signals are accepted in "time-major" format, e.g. of shape `(2…