Skip to content

[Doc] Update PaliGemma note to a warning #14565

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Mar 10, 2025
Merged

[Doc] Update PaliGemma note to a warning #14565

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 7 additions & 5 deletions docs/source/models/supported_models.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -847,7 +847,7 @@ See [this page](#generative-models) for more information on how to use generativ
* ✅︎
* ✅︎
- * `PaliGemmaForConditionalGeneration`
* PaliGemma (see note), PaliGemma 2 (see note)
* PaliGemma ⚠️, PaliGemma 2 ⚠️
* T + I<sup>E</sup>
* `google/paligemma-3b-pt-224`, `google/paligemma-3b-mix-224`, `google/paligemma2-3b-ft-docci-448`, etc.
*
Expand Down Expand Up @@ -917,6 +917,12 @@ See [this page](#generative-models) for more information on how to use generativ
<sup>E</sup> Pre-computed embeddings can be inputted for this modality.
<sup>+</sup> Multiple items can be inputted per text prompt for this modality.

:::{warning}
vLLM does not currently support PrefixLM attention mask, so our PaliGemma implementation uses regular causal attention, which causes the model output to be unstable.

We may deprecate this model series in a future release.
:::

:::{note}
`h2oai/h2ovl-mississippi-2b` will be available in V1 once we support backends other than FlashAttention.
:::
Expand All @@ -930,10 +936,6 @@ The official `openbmb/MiniCPM-V-2` doesn't work yet, so we need to use a fork (`
For more details, please see: <gh-pr:4087#issuecomment-2250397630>
:::

:::{note}
Currently the PaliGemma model series is implemented without PrefixLM attention mask. This model series may be deprecated in a future release.
:::

:::{note}
To use Qwen2.5-VL series models, you have to install Hugging Face Transformers library from source via `pip install git+https://github.com/huggingface/transformers`.
:::
Expand Down