Add olmoe and granitemoe architecture to whitelist #3449
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
Those two model architectures are supported in llama.cpp and technically in GPT4All 3.8.0 as well, but they have to be whitelisted to make them accessible to users, so do it. Here are the models: - https://huggingface.co/allenai/OLMoE-1B-7B-0924-Instruct - https://huggingface.co/ibm-granite/granite-3.1-3b-a800m-instruct They are really small and not the brightest, but very fast. I am hoping to make use of them for sentence similarity search with the LocalDocs feature. There was also a user that wanted to have tiny LLMs for educational purposes in Africa, because of hardware constraints. Signed-off-by: ThiloteE <[email protected]>
ThiloteE
added
the
model-architecture
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Outdated suggestions cannot be applied.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.
Describe your changes
Those two model architectures are supported in llama.cpp and technically in GPT4All 3.8.0 as well, but they have to be whitelisted to make them accessible to users, so do it.
Here are the models:
They are really small and not the brightest, but very fast. I am hoping to make use of them for sentence similarity search with the LocalDocs feature. There was also a user that wanted to have tiny LLMs for educational purposes in Africa, because of hardware constraints.
Because they are so fast and tiny and not the brightest, not having them supported on the compute backend could be argued to be justified. They are compatible with the Cuda backend though, so that's good.
Checklist before requesting a review