SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Added time-series blogs to the models (#23857)

Browse Source 
* added blogs to docs

* removed new-line
This commit is contained in:
Eli Simhayev
2023-06-02 22:02:34 +05:30
committed by GitHub
parent 167a0d8f87
commit bacaab1629
2 changed files with 3 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/source/en/model_doc/informer.mdx
View File

@@ -25,6 +25,8 @@ The abstract from the paper is the following:
This model was contributed by [elisim](https://huggingface.co/elisim) and [kashif](https://huggingface.co/kashif). This model was contributed by [elisim](https://huggingface.co/elisim) and [kashif](https://huggingface.co/kashif).
The original code can be found [here](https://github.com/zhouhaoyi/Informer2020). The original code can be found [here](https://github.com/zhouhaoyi/Informer2020).
Tips:
- Check out the Informer blog-post in HuggingFace blog: [Multivariate Probabilistic Time Series Forecasting with Informer](https://huggingface.co/blog/informer)
## InformerConfig ## InformerConfig

1
docs/source/en/model_doc/time_series_transformer.mdx
View File

@@ -25,6 +25,7 @@ The Time Series Transformer model is a vanilla encoder-decoder Transformer for t
Tips: Tips:
- Check out the Time Series Transformer blog-post in HuggingFace blog: [Probabilistic Time Series Forecasting with 🤗 Transformers](https://huggingface.co/blog/time-series-transformers)
- Similar to other models in the library, [`TimeSeriesTransformerModel`] is the raw Transformer without any head on top, and [`TimeSeriesTransformerForPrediction`] - Similar to other models in the library, [`TimeSeriesTransformerModel`] is the raw Transformer without any head on top, and [`TimeSeriesTransformerForPrediction`]
adds a distribution head on top of the former, which can be used for time-series forecasting. Note that this is a so-called probabilistic forecasting model, not a adds a distribution head on top of the former, which can be used for time-series forecasting. Note that this is a so-called probabilistic forecasting model, not a
point forecasting model. This means that the model learns a distribution, from which one can sample. The model doesn't directly output values. point forecasting model. This means that the model learns a distribution, from which one can sample. The model doesn't directly output values.