Skip to content
This repository was archived by the owner on May 13, 2024. It is now read-only.

Add neuralbeagle as a new llm model #53

Merged
merged 5 commits into from
Feb 15, 2024
Merged

Add neuralbeagle as a new llm model #53

merged 5 commits into from
Feb 15, 2024

Conversation

MB-Finski
Copy link
Collaborator

@MB-Finski MB-Finski commented Feb 9, 2024

Adds support for the NeuralBeagle14 7B 8K context length model.

  • Model download tested as working

@marcelklehr
Copy link
Member

What's with the failing CI?

@MB-Finski
Copy link
Collaborator Author

MB-Finski commented Feb 14, 2024

What's with the failing CI?

Hmm.. I think it might be related to this: ggml-org/llama.cpp#3484

So we may need to update the falcon gguf model file.

EDIT: i.e. updating the deps caused this.

@MB-Finski
Copy link
Collaborator Author

Yup.. We will have to update the falcon model with this: https://gpt4all.io/models/gguf/gpt4all-falcon-newbpe-q4_0.gguf

@provokateurin
Copy link
Member

This will close #29

@MB-Finski MB-Finski merged commit 1a7972f into main Feb 15, 2024
27 checks passed
@delete-merged-branch delete-merged-branch bot deleted the add/neuralbeagle14 branch February 15, 2024 10:33
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants