We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
1 parent 6a7e6f3 commit ac45165Copy full SHA for ac45165
training/README.md
@@ -4,7 +4,7 @@ We trained our Bamba model with FSDP using our training repo [here](https://gith
4
Note that this training effort was started before FSDP2 and also long before we contributed
5
`Mamba2-Hybrid` to HF, so we were doing FSDP1 training with [official Mamba implementation](https://github.com/state-spaces/mamba).
6
For users trying to reproduce the training you now have much more options with our newly
7
-contributed [HF-version of Mamba2-Hybrid]() (will update this link soon!).
+contributed [HF-version of Mamba2-Hybrid](https://github.com/huggingface/transformers/tree/main/src/transformers/models/bamba).
8
9
Here are the setup details and command on how you can train the model:
10
0 commit comments