README.md

---
license: apache-2.0
---


![image](https://cdn-uploads.huggingface.co/production/uploads/66276727368ec2a0b933772c/q8ymYL8Wp7778j2TlQefi.png)


 [![Python](https://img.shields.io/badge/Python-3.10%2B-blue)](https://www.python.org/)  [![PyTorch](https://img.shields.io/badge/PyTorch-2.6.0-blue)](https://pytorch.org/) 

# FLAME: Flow Enhanced Legendre Memory Models for General Time Series Forecasting


This is the official repository of **FLAME**: Flow Enhanced Legendre Memory Models for General Time Series Forecasting. It has been accepted by **NeurIPS** 2026!



## Introduction
FLAME is a family of extremely **lightweight** and highly capable time series foundation models. Based on the normalization-based forecasting head, it can support both the **deterministic** and **probabilistic** forecasting.

To our best knowldege, FLAME is the first time series foundation model possessing both lightweight backbones and generative prediction capabilities!



![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

We release all three versions of FLAME in different branches:
```shell
FLAME Small (2M) -- branch main & FLAME_Small
FLAME Base (6M) -- branch FLAME_Base
FLAME Large (10M) -- branch FLAME_Large
```



You need to install the following packages:

```shell
# pip install transformers[torch]

# pip install mamba-ssm[causal-conv1d]

# pip install zuko
```

To make deterministic or probabilistic forecasts, just follow:

```python
from transformers import AutoModel, AutoConfig
import torch

model_path = "path/to/your/model"
config_path = "path/to/your/config"

config = AutoConfig.from_pretrained(config_path)

model = AutoModel.from_pretrained(model_path, config=config)
model.eval() 

 # The inputs need to be [batch_size, seq_len]. If multivariate, transform the inputs to [batch_size * n_vars, seq_len]
inputs = torch.randn(batch_size, seq_length)

# deterministic forecasting
with torch.no_grad():
    # output shape: [batch_size, 1, seq_len]
    outputs = model.generate(
        inputs=inputs,
        max_length=96,    
        revin=True,
        num_samples=1,
        inference_patch_len=48 # recommend to input the period length
    )


# probabilistic forecasting
with torch.no_grad():
    # output shape: [batch_size, 100, seq_len]
    outputs = model.generate(
        inputs=inputs,
        max_length=96,    
        revin=True,
        num_samples=100
    )

```