---
library_name: transformers
datasets:
- monology/pile-uncopyrighted
base_model:
- state-spaces/mamba-2.8b-hf
pipeline_tag: text-generation
---

# MambaConstrict TD

MambaConstrict Model trained using a temporal difference regularization with $\lambda = 0.0001$.

For inquiring, please contact teilers@student.ethz.ch