How to use FinText/TimesFM_20M_2000_Global with Transformers:
# Load model directly from transformers import AutoTokenizer, TimesFMForHF tokenizer = AutoTokenizer.from_pretrained("FinText/TimesFM_20M_2000_Global") model = TimesFMForHF.from_pretrained("FinText/TimesFM_20M_2000_Global")
This is the Time Series Foundation Model (TSFM), pre-trained on global financial time series data up to the year 2000 using the TimesFM architecture (20M). The dataset spans from 1990–2000 and includes all global excess return data.
🔗 Related Links
Files info
