Update README.md
Browse files
README.md
CHANGED
@@ -75,22 +75,6 @@ getting started [notebook](https://github.com/IBM/tsfm/blob/main/notebooks/hfdem
|
|
75 |
but can provide any forecast lengths up to 720 in get_model() to get the required model.
|
76 |
|
77 |
|
78 |
-
## Model Capabilities with example scripts
|
79 |
-
|
80 |
-
The below model scripts can be used for any of the above TTM models. Please update the HF model URL and branch name in the `from_pretrained` call appropriately to pick the model of your choice.
|
81 |
-
|
82 |
-
**Since these models use frequency prefix tuning, ensure your dataset yaml (as mentioned in the below notebooks) have frequency information and set `enable_prefix_tuning` to True in load_dataset.**
|
83 |
-
- Getting Started [[colab]](https://colab.research.google.com/github/ibm-granite/granite-tsfm/blob/main/notebooks/hfdemo/ttm_getting_started.ipynb)
|
84 |
-
- Zeroshot Multivariate Forecasting [[Example]](https://github.com/ibm-granite/granite-tsfm/blob/main/notebooks/hfdemo/ttm_getting_started.ipynb)
|
85 |
-
- Finetuned Multivariate Forecasting:
|
86 |
-
- Channel-Independent Finetuning [[Example 1]](https://github.com/ibm-granite/granite-tsfm/blob/main/notebooks/hfdemo/ttm_getting_started.ipynb) [[Example 2]](https://github.com/ibm-granite/granite-tsfm/blob/main/notebooks/hfdemo/tinytimemixer/ttm_m4_hourly.ipynb)
|
87 |
-
- Channel-Mix Finetuning [[Example]](https://github.com/ibm-granite/granite-tsfm/blob/main/notebooks/tutorial/ttm_channel_mix_finetuning.ipynb)
|
88 |
-
- **New Releases (extended features released on October 2024)**
|
89 |
-
- Finetuning and Forecasting with Exogenous/Control Variables [[Example]](https://github.com/ibm-granite/granite-tsfm/blob/main/notebooks/tutorial/ttm_with_exog_tutorial.ipynb)
|
90 |
-
- Finetuning and Forecasting with static categorical features [Example: To be added soon]
|
91 |
-
- Rolling Forecasts - Extend forecast lengths via rolling capability. Rolling beyond 2*forecast_length is not recommended. [[Example]](https://github.com/ibm-granite/granite-tsfm/blob/main/notebooks/hfdemo/ttm_rolling_prediction_getting_started.ipynb)
|
92 |
-
- Helper scripts for optimal Learning Rate suggestions for Finetuning [[Example]](https://github.com/ibm-granite/granite-tsfm/blob/main/notebooks/tutorial/ttm_with_exog_tutorial.ipynb)
|
93 |
-
|
94 |
## Benchmarks
|
95 |
|
96 |
<p align="center" width="100%">
|
|
|
75 |
but can provide any forecast lengths up to 720 in get_model() to get the required model.
|
76 |
|
77 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
78 |
## Benchmarks
|
79 |
|
80 |
<p align="center" width="100%">
|