Update README.md
Browse files
README.md
CHANGED
@@ -21,7 +21,7 @@ TinyTimeMixers (TTMs) are compact pre-trained models for Multivariate Time-Serie
|
|
21 |
|
22 |
|
23 |
TTM-R1 comprises TTM variants pre-trained on 250M public training samples. We have another set of TTM models released under TTM-R2 trained on a much larger pretraining
|
24 |
-
dataset (~700M samples) which can be accessed from [here](https://huggingface.co/ibm-granite/granite-timeseries-ttm-r2) In general, TTM-R2 models perform better than
|
25 |
TTM-R1 models as they are trained on larger pretraining dataset. However, the choice of R1 vs R2 depends on your target data distribution. Hence requesting users to
|
26 |
try both R1 and R2 variants and pick the best for your data.
|
27 |
|
|
|
21 |
|
22 |
|
23 |
TTM-R1 comprises TTM variants pre-trained on 250M public training samples. We have another set of TTM models released under TTM-R2 trained on a much larger pretraining
|
24 |
+
dataset (~700M samples) which can be accessed from [here](https://huggingface.co/ibm-granite/granite-timeseries-ttm-r2). In general, TTM-R2 models perform better than
|
25 |
TTM-R1 models as they are trained on larger pretraining dataset. However, the choice of R1 vs R2 depends on your target data distribution. Hence requesting users to
|
26 |
try both R1 and R2 variants and pick the best for your data.
|
27 |
|