Update README.md
Browse files
README.md
CHANGED
@@ -2,13 +2,14 @@
|
|
2 |
license: cdla-permissive-2.0
|
3 |
---
|
4 |
|
5 |
-
# Model Card
|
6 |
|
7 |
TTM, also known as TinyTimeMixer, are compact pre-trained models for Time-Series Forecasting, open-sourced by IBM Research.
|
8 |
**With less than 1 Million parameters, TTM introduces the notion of the first-ever “tiny” pre-trained models for Time-Series Forecasting.**
|
9 |
|
10 |
TTM outperforms several popular benchmarks demanding billions of parameters in zero-shot and few-shot forecasting. TTM is pre-trained on diverse public time-series datasets which
|
11 |
-
can be easily fine-tuned for your target data. Refer to our [paper](https://arxiv.org/pdf/2401.03955.pdf) for more details.
|
|
|
12 |
|
13 |
**Note that zeroshot, fine-tuning and inference tasks using TTM can easily be executed in 1 GPU machine or in laptops too!!**
|
14 |
|
|
|
2 |
license: cdla-permissive-2.0
|
3 |
---
|
4 |
|
5 |
+
# TTM Model Card
|
6 |
|
7 |
TTM, also known as TinyTimeMixer, are compact pre-trained models for Time-Series Forecasting, open-sourced by IBM Research.
|
8 |
**With less than 1 Million parameters, TTM introduces the notion of the first-ever “tiny” pre-trained models for Time-Series Forecasting.**
|
9 |
|
10 |
TTM outperforms several popular benchmarks demanding billions of parameters in zero-shot and few-shot forecasting. TTM is pre-trained on diverse public time-series datasets which
|
11 |
+
can be easily fine-tuned for your target data. Refer to our [paper](https://arxiv.org/pdf/2401.03955.pdf) for more details. The current open-source
|
12 |
+
version supports forecasting use-cases ranging from minutely to hourly resolutions (Ex. 10 min, 15 min, 1 hour, etc.)
|
13 |
|
14 |
**Note that zeroshot, fine-tuning and inference tasks using TTM can easily be executed in 1 GPU machine or in laptops too!!**
|
15 |
|