add support for moondream vision language model #6899
Merged
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
This required making the following changes to the CLIP model: 1. Support for patch embedding bias. 2. Make class embedding and pre-layernorm optional. 3. Add support for post-layernorm.
ggerganov
approved these changes
Apr 25, 2024
|
Would this be a general support for all SigLIP based encoders or just for moondream2? |
Closed
9 tasks
nopperl
pushed a commit
to nopperl/llama.cpp
that referenced
this pull request
May 5, 2024
* add support for moondream vision language model This required making the following changes to the CLIP model: 1. Support for patch embedding bias. 2. Make class embedding and pre-layernorm optional. 3. Add support for post-layernorm. * Update examples/llava/clip.cpp --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
jart
added a commit
to Mozilla-Ocho/llamafile
that referenced
this pull request
May 7, 2024
This broke the server's LLaVA support in a non-obvious way. See ggerganov/llama.cpp#6899 See ggerganov/llama.cpp#7060
abetlen
added a commit
to abetlen/llama.cpp
that referenced
this pull request
May 9, 2024
…el (ggerganov#6899)"" This reverts commit 9da243b.
Merged
ggerganov
pushed a commit
that referenced
this pull request
May 10, 2024
|
Unfortunately, I can't convert the model to GGUF with gguf-my-repo; would it be better to build the source myself (with make) for a higher chance of success? |
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Outdated suggestions cannot be applied.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.
This required making the following changes to the CLIP model:
I verified that the LLaVA model still works as expected after this change.