Instructions to use yusufizzetmurat/fed-pulse-retrieval with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use yusufizzetmurat/fed-pulse-retrieval with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("yusufizzetmurat/fed-pulse-retrieval", dtype="auto") - Notebooks
- Google Colab
- Kaggle
yusufizzetmurat/fed-pulse-retrieval
Artefact for the fed-pulse FOMC text analytics project.
- Source code: https://github.com/yusufizzetmurat/fed-pulse
- Live demo: https://fedpulse.yusufizzetmurat.com
- License:
mit
Training corpus
Sentence-transformer retrieval bundle: embedding_index.parquet, embeddings.npy, and manifest.json. Trained via MultipleNegativesRankingLoss on same-meeting positive pairs.
Training command
python -m app.retrieval.train --train-end <fold-end>
Attribution
- FOMC text: scraped from the Board of Governors of the Federal Reserve System (US-government public domain), with supervised labels merged from gtfintechlab/fomc_communication.
- Encoder backbone:
yusufizzetmurat/fed-pulse-encoder(see that card for upstream BIS / gtfintechlab / FinBERT attribution).
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support