dfurman
/

Mixtral-8x7B-Instruct-v0.1

Text Generation

Model card Files Files and versions Community

dfurman commited on Dec 14, 2023

Commit

8908d58

•

1 Parent(s): ddb2812

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -149,7 +149,7 @@ Garnish with a lime wedge and a cherry.
 | runtime / 50 tokens (sec) | GPU  | dtype | VRAM (GB) |
 |:-----------------------------:|:---------------------:|:-------------:|:-----------------------:|
-| 3.21                          | 1x A100 (40 GB SXM)                | torch.bfloat16    | 16                    |
 ## Training

 | runtime / 50 tokens (sec) | GPU  | dtype | VRAM (GB) |
 |:-----------------------------:|:---------------------:|:-------------:|:-----------------------:|
+| 8.25                        | 1x A100 (40 GB SXM)                | nf4    | 28                    |
 ## Training