Update README.md
Browse files
README.md
CHANGED
@@ -21,10 +21,12 @@ tags:
|
|
21 |
|
22 |
Large time-series model introduced in this [paper](https://arxiv.org/abs/2402.02368) and enhanced with our [further work](https://arxiv.org/abs/2410.04803).
|
23 |
|
24 |
-
This version is pre-trained on **260B** time points with **84M** parameters, a lightweight generative Transformer for zero-shot point forecasting
|
25 |
|
26 |
We evaluate the model on the following benchmark: [TSLib Dataset](https://cdn-uploads.huggingface.co/production/uploads/64fbe24a2d20ced4e91de38a/VAfuvvqBALLvQUXYJPZJx.png).
|
27 |
|
|
|
|
|
28 |
# Quickstart
|
29 |
```
|
30 |
pip install transformers==4.40.1 # Use this version and Python 3.10 for stable compatibility
|
@@ -48,7 +50,7 @@ output = model.generate(seqs, max_new_tokens=prediction_length)
|
|
48 |
print(output.shape)
|
49 |
```
|
50 |
|
51 |
-
A notebook example is also provided [here](https://
|
52 |
|
53 |
## Specification
|
54 |
|
|
|
21 |
|
22 |
Large time-series model introduced in this [paper](https://arxiv.org/abs/2402.02368) and enhanced with our [further work](https://arxiv.org/abs/2410.04803).
|
23 |
|
24 |
+
This version is pre-trained on **260B** time points with **84M** parameters, a lightweight generative Transformer for zero-shot point forecasting.
|
25 |
|
26 |
We evaluate the model on the following benchmark: [TSLib Dataset](https://cdn-uploads.huggingface.co/production/uploads/64fbe24a2d20ced4e91de38a/VAfuvvqBALLvQUXYJPZJx.png).
|
27 |
|
28 |
+
For more information, please see the [Github Repo](https://github.com/thuml/Large-Time-Series-Model).
|
29 |
+
|
30 |
# Quickstart
|
31 |
```
|
32 |
pip install transformers==4.40.1 # Use this version and Python 3.10 for stable compatibility
|
|
|
50 |
print(output.shape)
|
51 |
```
|
52 |
|
53 |
+
A notebook example is also provided [here](https://github.com/thuml/Large-Time-Series-Model/blob/main/examples/quickstart_zero_shot.ipynb). Try it out!
|
54 |
|
55 |
## Specification
|
56 |
|