Update README.md
Browse files
README.md
CHANGED
@@ -60,7 +60,7 @@ getting started [notebook](https://github.com/IBM/tsfm/blob/main/notebooks/hfdem
|
|
60 |
|
61 |
- **512-96-r2**: Given the last 512 time-points (i.e. context length), this model can forecast up to next 96 time-points (i.e. forecast length)
|
62 |
in future. This model is pre-trained with a larger pretraining dataset for improved accuracy. Recommended for hourly and minutely
|
63 |
-
resolutions (Ex. 10 min, 15 min, 1 hour, etc). (branch name:
|
64 |
|
65 |
- **1024-96-r2**: Given the last 1024 time-points (i.e. context length), this model can forecast up to next 96 time-points (i.e. forecast length)
|
66 |
in future. This model is pre-trained with a larger pretraining dataset for improved accuracy. Recommended for hourly and minutely
|
|
|
60 |
|
61 |
- **512-96-r2**: Given the last 512 time-points (i.e. context length), this model can forecast up to next 96 time-points (i.e. forecast length)
|
62 |
in future. This model is pre-trained with a larger pretraining dataset for improved accuracy. Recommended for hourly and minutely
|
63 |
+
resolutions (Ex. 10 min, 15 min, 1 hour, etc). (branch name: main) [[Benchmarks]](https://github.com/ibm-granite/granite-tsfm/blob/main/notebooks/hfdemo/tinytimemixer/ttm-r2_benchmarking_512_96.ipynb)
|
64 |
|
65 |
- **1024-96-r2**: Given the last 1024 time-points (i.e. context length), this model can forecast up to next 96 time-points (i.e. forecast length)
|
66 |
in future. This model is pre-trained with a larger pretraining dataset for improved accuracy. Recommended for hourly and minutely
|