[LLaVa] Some improvements #27895
Merged
[LLaVa] Some improvements #27895
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
NielsRogge
commented
Dec 7, 2023
NielsRogge
commented
Dec 8, 2023
| @@ -270,22 +270,22 @@ def resize_token_embeddings(self, new_num_tokens: Optional[int] = None, pad_to_m | |||
| def _merge_input_ids_with_image_features( | |||
| self, image_features, inputs_embeds, input_ids, attention_mask, position_ids | |||
| ): | |||
| nb_images, image_hidden_dim, embed_dim = image_features.shape | |||
| num_images, num_image_patches, embed_dim = image_features.shape | |||
There was a problem hiding this comment.
this is not really a "hidden dim" but rather the number of image patches. As below "num_image_tokens" is already used, this could be confusing with "num_image_patches". The former actually refers to the number of special image tokens, hence I've renamed that.
NielsRogge
commented
Dec 8, 2023
| This model was contributed by [ArthurZ](https://huggingface.co/ArthurZ) and [ybelkada](https://huggingface.co/ybelkada). | ||
| The original code can be found [here](https://github.com/haotian-liu/LLaVA/tree/main/llava). | ||
|
|
||
| ## Usage tips |
There was a problem hiding this comment.
cc @younesbelkada just an FYI, for new docs we always have a ## Usage tips section and a ## Resources section
I'm not sure the CookieCutter creates those sections by default
younesbelkada
approved these changes
Dec 8, 2023
|
They are failing on my setup: Could possibly also be the case on main, will check |
|
Yeah it still fails for me both on main and my branch even after #27909. So @ArthurZucker could you perhaps run the slow tests from my branch before merging? But I'm pretty sure it doesn't affect integration tests. |
younesbelkada
approved these changes
Dec 11, 2023
iantbutler01
pushed a commit
to BismuthCloud/transformers
that referenced
this pull request
Dec 16, 2023
* More improvements * Improve variable names * Update READMEs, improve docs
staghado
pushed a commit
to staghado/transformers
that referenced
this pull request
Jan 15, 2024
* More improvements * Improve variable names * Update READMEs, improve docs
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What does this PR do?
Some minor improvements when going over the LLaVa code.