donghyunli/Meta-Llama-3-8B-KronQ-HG download history

donghyunli/Meta-Llama-3-8B-KronQ-HG is a text generation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 757 times (83 in the last 7 days), and 3,932 times in total. It ranks #23,971 among datasets by monthly downloads.

Meta-Llama-3-8B — KronQ H_G (output-side gradient covariance) Paper: arXiv:2607.07964 · Code: GitHub Pre-computed H_G for Meta-Llama-3-8B, the output-side curvature factor used by KronQ under the K-FAC factorization H ≈ H_X ⊗ H_G. H_G is the per-sublayer empirical-Fisher gradient cova

Open donghyunli/Meta-Llama-3-8B-KronQ-HG on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.