mistralai
/

Devstral-Small-2-24B-Instruct-2512

Model card Files Files and versions

patrickvonplaten commited on 16 days ago

Commit

8d27a0d

·

verified ·

1 Parent(s): 9592b53

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -235,7 +235,7 @@ And run the following code snippet:
 > While the checkpoint is serialized in FP8 format, there is currently a problem
 > with "true" FP8 inference. Hence the weights are automatically dequantized to BFloat16
 > as per [this config setting](https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512/blob/main/config.json#L13).
-> Once the bug is fixed, we will by default run the model in "true" FP8.
 ```python
 import torch

 > While the checkpoint is serialized in FP8 format, there is currently a problem
 > with "true" FP8 inference. Hence the weights are automatically dequantized to BFloat16
 > as per [this config setting](https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512/blob/main/config.json#L13).
+> Once the bug is fixed, we will by default run the model in "true" FP8. Stay tuned by following [this issue](https://github.com/huggingface/transformers/issues/42746).
 ```python
 import torch