← Back to Quantization

int4

Quantization
Used in
6 PRs
Best BPB
1.0785
Avg BPB
1.1380

Hyperparameters Across PRs

pr_numberbitsscope
3054MLP and attention weights
3754all
4774bigram logit table
4824bigram logit table
4854bigram logit table
17324MLP FC2 and residuals