You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: src/UserGuide/Master/Table/AI-capability/TimeSeries-Large-Model.md
+6-6Lines changed: 6 additions & 6 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -37,7 +37,7 @@ The team's related technologies of time series large models have been published
37
37
38
38
## Timer Model
39
39
40
-
The Timer<sup><ahref="#appendix1"id="ref1"style="text-decoration: none;">[1]</a></sup> model not only demonstrates excellent few-shot generalization and multi-task adaptation capabilities but also gains a rich knowledge base through pre-training, endowing it with the universal capability to handle a variety of downstream tasks, featuring the following:
40
+
The Timer<sup><ahref="#appendix1"id="ref1"style="text-decoration: none;">[1]</a></sup> model(not built-in) not only demonstrates excellent few-shot generalization and multi-task adaptation capabilities but also gains a rich knowledge base through pre-training, endowing it with the universal capability to handle a variety of downstream tasks, featuring the following:
41
41
42
42
-**Generalization**: The model can be fine-tuned using a small number of samples to achieve leading predictive performance in the industry.
43
43
-**Versatility**: The model is designed flexibly to adapt to various task requirements and supports variable input and output lengths, enabling it to play a role in various application scenarios.
@@ -47,7 +47,7 @@ The Timer<sup><a href="#appendix1" id="ref1" style="text-decoration: none;">[1]<
47
47
48
48
## Timer-XL Model
49
49
50
-
Timer-XL<sup><ahref="#appendix2"id="ref2"style="text-decoration: none;">[2]</a></sup> is an upgraded version of Timer that further extends the network structure and achieves comprehensive breakthroughs in multiple dimensions:
50
+
Timer-XL<sup><ahref="#appendix2"id="ref2"style="text-decoration: none;">[2]</a></sup> is an upgraded version of Timer that further extends the network structure and achieves comprehensive breakthroughs in multiple dimensions(available since V2.0.5.1):
51
51
52
52
-**Ultra-long Context Support**: This model breaks through the limitations of traditional time series forecasting models, supporting inputs of thousands of Tokens (equivalent to tens of thousands of time points), effectively solving the context length bottleneck problem.
53
53
-**Multi-variable Prediction Scenarios Coverage**: Supports various forecasting scenarios, including non-stationary time series forecasting, multi-variable forecasting tasks, and forecasting with covariates, meeting diverse business needs.
Timer-Sundial<sup><ahref="#appendix3"id="ref3"style="text-decoration: none;">[3]</a></sup> is a series of generative foundational models focused on time series forecasting. The basic version has 128 million parameters and has undergone large-scale pre-training on 1 trillion time points. Its core features include:
60
+
Timer-Sundial<sup><ahref="#appendix3"id="ref3"style="text-decoration: none;">[3]</a></sup> is a series of generative foundational models focused on time series forecasting(available since V2.0.5.1). The basic version has 128 million parameters and has undergone large-scale pre-training on 1 trillion time points. Its core features include:
61
61
62
62
-**Powerful Generalization Performance**: Possesses zero-shot forecasting capabilities, supporting both point forecasting and probabilistic forecasting simultaneously.
63
63
-**Flexible Forecasting Distribution Analysis**: Can not only forecast mean values or quantiles but also evaluate any statistical characteristics of the forecasting distribution through the original samples generated by the model.
Copy file name to clipboardExpand all lines: src/UserGuide/Master/Tree/AI-capability/TimeSeries-Large-Model.md
+6-6Lines changed: 6 additions & 6 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -37,7 +37,7 @@ The team's related technologies of time series large models have been published
37
37
38
38
## Timer Model
39
39
40
-
The Timer<sup><ahref="#appendix1"id="ref1"style="text-decoration: none;">[1]</a></sup> model not only demonstrates excellent few-shot generalization and multi-task adaptation capabilities but also gains a rich knowledge base through pre-training, endowing it with the universal capability to handle a variety of downstream tasks, featuring the following:
40
+
The Timer<sup><ahref="#appendix1"id="ref1"style="text-decoration: none;">[1]</a></sup> model(not built-in) not only demonstrates excellent few-shot generalization and multi-task adaptation capabilities but also gains a rich knowledge base through pre-training, endowing it with the universal capability to handle a variety of downstream tasks, featuring the following:
41
41
42
42
-**Generalization**: The model can be fine-tuned using a small number of samples to achieve leading predictive performance in the industry.
43
43
-**Versatility**: The model is designed flexibly to adapt to various task requirements and supports variable input and output lengths, enabling it to play a role in various application scenarios.
@@ -47,7 +47,7 @@ The Timer<sup><a href="#appendix1" id="ref1" style="text-decoration: none;">[1]<
47
47
48
48
## Timer-XL Model
49
49
50
-
Timer-XL<sup><ahref="#appendix2"id="ref2"style="text-decoration: none;">[2]</a></sup> is an upgraded version of Timer that further extends the network structure and achieves comprehensive breakthroughs in multiple dimensions:
50
+
Timer-XL<sup><ahref="#appendix2"id="ref2"style="text-decoration: none;">[2]</a></sup> is an upgraded version of Timer that further extends the network structure and achieves comprehensive breakthroughs in multiple dimensions(available since V2.0.5.1):
51
51
52
52
-**Ultra-long Context Support**: This model breaks through the limitations of traditional time series forecasting models, supporting inputs of thousands of Tokens (equivalent to tens of thousands of time points), effectively solving the context length bottleneck problem.
53
53
-**Multi-variable Prediction Scenarios Coverage**: Supports various forecasting scenarios, including non-stationary time series forecasting, multi-variable forecasting tasks, and forecasting with covariates, meeting diverse business needs.
Timer-Sundial<sup><ahref="#appendix3"id="ref3"style="text-decoration: none;">[3]</a></sup> is a series of generative foundational models focused on time series forecasting. The basic version has 128 million parameters and has undergone large-scale pre-training on 1 trillion time points. Its core features include:
60
+
Timer-Sundial<sup><ahref="#appendix3"id="ref3"style="text-decoration: none;">[3]</a></sup> is a series of generative foundational models focused on time series forecasting(available since V2.0.5.1). The basic version has 128 million parameters and has undergone large-scale pre-training on 1 trillion time points. Its core features include:
61
61
62
62
-**Powerful Generalization Performance**: Possesses zero-shot forecasting capabilities, supporting both point forecasting and probabilistic forecasting simultaneously.
63
63
-**Flexible Forecasting Distribution Analysis**: Can not only forecast mean values or quantiles but also evaluate any statistical characteristics of the forecasting distribution through the original samples generated by the model.
Copy file name to clipboardExpand all lines: src/UserGuide/latest-Table/AI-capability/TimeSeries-Large-Model.md
+6-6Lines changed: 6 additions & 6 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -37,7 +37,7 @@ The team's related technologies of time series large models have been published
37
37
38
38
## Timer Model
39
39
40
-
The Timer<sup><ahref="#appendix1"id="ref1"style="text-decoration: none;">[1]</a></sup> model not only demonstrates excellent few-shot generalization and multi-task adaptation capabilities but also gains a rich knowledge base through pre-training, endowing it with the universal capability to handle a variety of downstream tasks, featuring the following:
40
+
The Timer<sup><ahref="#appendix1"id="ref1"style="text-decoration: none;">[1]</a></sup> model(not built-in) not only demonstrates excellent few-shot generalization and multi-task adaptation capabilities but also gains a rich knowledge base through pre-training, endowing it with the universal capability to handle a variety of downstream tasks, featuring the following:
41
41
42
42
-**Generalization**: The model can be fine-tuned using a small number of samples to achieve leading predictive performance in the industry.
43
43
-**Versatility**: The model is designed flexibly to adapt to various task requirements and supports variable input and output lengths, enabling it to play a role in various application scenarios.
@@ -47,7 +47,7 @@ The Timer<sup><a href="#appendix1" id="ref1" style="text-decoration: none;">[1]<
47
47
48
48
## Timer-XL Model
49
49
50
-
Timer-XL<sup><ahref="#appendix2"id="ref2"style="text-decoration: none;">[2]</a></sup> is an upgraded version of Timer that further extends the network structure and achieves comprehensive breakthroughs in multiple dimensions:
50
+
Timer-XL<sup><ahref="#appendix2"id="ref2"style="text-decoration: none;">[2]</a></sup> is an upgraded version of Timer that further extends the network structure and achieves comprehensive breakthroughs in multiple dimensions(available since V2.0.5.1):
51
51
52
52
-**Ultra-long Context Support**: This model breaks through the limitations of traditional time series forecasting models, supporting inputs of thousands of Tokens (equivalent to tens of thousands of time points), effectively solving the context length bottleneck problem.
53
53
-**Multi-variable Prediction Scenarios Coverage**: Supports various forecasting scenarios, including non-stationary time series forecasting, multi-variable forecasting tasks, and forecasting with covariates, meeting diverse business needs.
Timer-Sundial<sup><ahref="#appendix3"id="ref3"style="text-decoration: none;">[3]</a></sup> is a series of generative foundational models focused on time series forecasting. The basic version has 128 million parameters and has undergone large-scale pre-training on 1 trillion time points. Its core features include:
60
+
Timer-Sundial<sup><ahref="#appendix3"id="ref3"style="text-decoration: none;">[3]</a></sup> is a series of generative foundational models focused on time series forecasting(available since V2.0.5.1). The basic version has 128 million parameters and has undergone large-scale pre-training on 1 trillion time points. Its core features include:
61
61
62
62
-**Powerful Generalization Performance**: Possesses zero-shot forecasting capabilities, supporting both point forecasting and probabilistic forecasting simultaneously.
63
63
-**Flexible Forecasting Distribution Analysis**: Can not only forecast mean values or quantiles but also evaluate any statistical characteristics of the forecasting distribution through the original samples generated by the model.
Copy file name to clipboardExpand all lines: src/UserGuide/latest/AI-capability/TimeSeries-Large-Model.md
+6-6Lines changed: 6 additions & 6 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -37,7 +37,7 @@ The team's related technologies of time series large models have been published
37
37
38
38
## Timer Model
39
39
40
-
The Timer<sup><ahref="#appendix1"id="ref1"style="text-decoration: none;">[1]</a></sup> model not only demonstrates excellent few-shot generalization and multi-task adaptation capabilities but also gains a rich knowledge base through pre-training, endowing it with the universal capability to handle a variety of downstream tasks, featuring the following:
40
+
The Timer<sup><ahref="#appendix1"id="ref1"style="text-decoration: none;">[1]</a></sup> model(not built-in) not only demonstrates excellent few-shot generalization and multi-task adaptation capabilities but also gains a rich knowledge base through pre-training, endowing it with the universal capability to handle a variety of downstream tasks, featuring the following:
41
41
42
42
-**Generalization**: The model can be fine-tuned using a small number of samples to achieve leading predictive performance in the industry.
43
43
-**Versatility**: The model is designed flexibly to adapt to various task requirements and supports variable input and output lengths, enabling it to play a role in various application scenarios.
@@ -47,7 +47,7 @@ The Timer<sup><a href="#appendix1" id="ref1" style="text-decoration: none;">[1]<
47
47
48
48
## Timer-XL Model
49
49
50
-
Timer-XL<sup><ahref="#appendix2"id="ref2"style="text-decoration: none;">[2]</a></sup> is an upgraded version of Timer that further extends the network structure and achieves comprehensive breakthroughs in multiple dimensions:
50
+
Timer-XL<sup><ahref="#appendix2"id="ref2"style="text-decoration: none;">[2]</a></sup> is an upgraded version of Timer that further extends the network structure and achieves comprehensive breakthroughs in multiple dimensions(available since V2.0.5.1):
51
51
52
52
-**Ultra-long Context Support**: This model breaks through the limitations of traditional time series forecasting models, supporting inputs of thousands of Tokens (equivalent to tens of thousands of time points), effectively solving the context length bottleneck problem.
53
53
-**Multi-variable Prediction Scenarios Coverage**: Supports various forecasting scenarios, including non-stationary time series forecasting, multi-variable forecasting tasks, and forecasting with covariates, meeting diverse business needs.
Timer-Sundial<sup><ahref="#appendix3"id="ref3"style="text-decoration: none;">[3]</a></sup> is a series of generative foundational models focused on time series forecasting. The basic version has 128 million parameters and has undergone large-scale pre-training on 1 trillion time points. Its core features include:
60
+
Timer-Sundial<sup><ahref="#appendix3"id="ref3"style="text-decoration: none;">[3]</a></sup> is a series of generative foundational models focused on time series forecasting(available since V2.0.5.1). The basic version has 128 million parameters and has undergone large-scale pre-training on 1 trillion time points. Its core features include:
61
61
62
62
-**Powerful Generalization Performance**: Possesses zero-shot forecasting capabilities, supporting both point forecasting and probabilistic forecasting simultaneously.
63
63
-**Flexible Forecasting Distribution Analysis**: Can not only forecast mean values or quantiles but also evaluate any statistical characteristics of the forecasting distribution through the original samples generated by the model.
0 commit comments