DecisionIntelligence
/

FLAME

Model card Files Files and versions

Ccloud0525 commited on 2 days ago

Commit

4eb886b

·

verified ·

1 Parent(s): 080689e

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -22,14 +22,14 @@ To our best knowldege, FLAME is the first time series foundation model possessin
-![image/png](https://cdn-uploads.huggingface.co/production/uploads/66276727368ec2a0b933772c/OHKXxjrwYR3n3LO6UeVRS.png)
 ## Architecture
 FLAME adopts the Channel-Independent pretraining paradigm, and each variable is preprocessed through Instance Normalization to mitigate the value discrepancy. FLAME utilizes the Re-Norm to further mitigate the statistical differences between inputs and forecasts, and its backbone mainly consists of three modules: 1) Encoding, including Time Series Tokenization, **Local-Perception**, and MSA-Encoder, which tokenize the time series and enhance them through fusing the local environmental information with LegT; 2) Decoding, including **LegS based SSD-Decoder** and MCA-Enhancer, which utilize the SSD layers and MCA layers to make long-term inference ; 3) **Flow-based Head**, which leverages the Normalization Flow to support generative probabilistic forecasting, with both efficiency and accuracy.
-![image/png](https://cdn-uploads.huggingface.co/production/uploads/66276727368ec2a0b933772c/LchwMIvetMu10EjWjcW5N.png)
 ## Quickstart

+![image](https://cdn-uploads.huggingface.co/production/uploads/66276727368ec2a0b933772c/gViEr9T9f9Lts8AgfZvDJ.png)
 ## Architecture
 FLAME adopts the Channel-Independent pretraining paradigm, and each variable is preprocessed through Instance Normalization to mitigate the value discrepancy. FLAME utilizes the Re-Norm to further mitigate the statistical differences between inputs and forecasts, and its backbone mainly consists of three modules: 1) Encoding, including Time Series Tokenization, **Local-Perception**, and MSA-Encoder, which tokenize the time series and enhance them through fusing the local environmental information with LegT; 2) Decoding, including **LegS based SSD-Decoder** and MCA-Enhancer, which utilize the SSD layers and MCA layers to make long-term inference ; 3) **Flow-based Head**, which leverages the Normalization Flow to support generative probabilistic forecasting, with both efficiency and accuracy.
+![image](https://cdn-uploads.huggingface.co/production/uploads/66276727368ec2a0b933772c/Fmq7kerdj2xqSxfl2mn4o.png)
 ## Quickstart