← Back to Quantization

mixed int6/int7

Quantization
Used in
8 PRs
Best BPB
1.0135
Avg BPB
1.0569

Hyperparameters Across PRs

pr_numberbitsscope
1707all
1934embeddings
1953weights + embeddings
1958model weights
19926attention/MLP matrices
19927token embeddings
1995matrix weights + embeddings
20676weights and embeddings