Downloads · 30 days
4
3% of all-time downloads
forecastability-classifier-v1
noanabeshima/forecastability-classifier-v1
forecastability-classifier-v1 is a machine learning model from noanabeshima. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Classifier is fine-tuned from deberta-v3-base on this forecastability classification dataset to predict if Claude 3.7 Sonnet thinks a fineweb document is 'forecastable', i.e. is a useful seed for generating pastcastin…
All-time downloads
125
Public
Parameters
184M
738 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors735 MB · 99%
At a glance
- License
- apache-2.0
- Model type
- deberta-v2
- Access
- Public
- Created
- May 16, 2025
- Updated
- Aug 19, 2026
- SHA
- 505b48b5
Model card
From the Hugging Face model README
Classifier is fine-tuned from deberta-v3-base on this forecastability classification dataset to predict if Claude 3.7 Sonnet thinks a fineweb document is 'forecastable', i.e. is a useful seed for generating pastcasting questions.
Despite having a ROC AUC of .9625, only ~2% of fineweb documents are considered forecastable, so this classifier's precision/recall curves on random unseen fineweb documents look like this:
To load the model use
model = AutoModel.from_pretrained('noanabeshima/forecastability-classifier-v1')
tokenizer = AutoTokenizer.from_pretrained('noanabeshima/forecastability-classifier-v1')
- Type
- deberta-v2
- License
- apache-2.0
- Created
- May 16, 2025
- Updated
- Aug 19, 2026