PatrickHaller
/

hgrn2_pile_100m_distill_babylm

Text Generation

Model card Files Files and versions Community

Our model for the 2024 BabyLM challenge 100M words track.

To download and use this model the fla package has to be installed:

pip install -U git+https://github.com/sustcsonglin/flash-linear-attention

Downloads last month: 6,365

Inference Providers NEW

Text Generation

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Dataset used to train PatrickHaller/hgrn2_pile_100m_distill_babylm

Collection including PatrickHaller/hgrn2_pile_100m_distill_babylm

BabyLM Submissions

Collection contains relevant models for the BabyLM 2024 submission. The 100m model is for the strict and the 10m is for the strict-small track • 2 items • Updated Sep 17, 2024