← Back to Quantization
mixed int6/int7
QuantizationUsed in
8 PRs
Best BPB
1.0135
Avg BPB
1.0569
Submissions
Hyperparameters Across PRs
| pr_number | bits | scope |
|---|---|---|
| 1707 | — | all |
| 1934 | — | embeddings |
| 1953 | — | weights + embeddings |
| 1958 | — | model weights |
| 1992 | 6 | attention/MLP matrices |
| 1992 | 7 | token embeddings |
| 1995 | — | matrix weights + embeddings |
| 2067 | 6 | weights and embeddings |