DeepScaleR-1.5B-Preview
Reward Function: Our reward function is simple but effective: - 1 for correct answers passing LaTeX/Sympy checks - 0 for incorrect or improperly formatted answers - Note: No partial rewards (such as PRMs) or intermediate feedback.
text → text · made by Agentica
Sold by
Nobody in the catalogue publishes a price for this yet.
About
DeepScaleR-1.5B-Preview — a text model from Agentica.
It takes text and returns text. It was published in January 2025. The catalogue files it under extract. Its weights are published under MIT, so you may run it on your own machine, or buy it from whoever serves it cheapest.
Every current figure
- Maker
- Agentica
- Register
- model
- Takes
- text
- Returns
- text
- Published
- January 2025
- Parameters
- 1.8 billion · read from its own weights
- Licence
- mit
Known as 1 name
agentica-org/DeepScaleR-1.5B-Preview