This repository has been archived by the owner on Jun 24, 2024. It is now read-only.
Add Falcon Support #313
Merged
Add Falcon Support #313
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
danforbes
reviewed
Jun 17, 2023
Co-authored-by: Dan Forbes <[email protected]>
Co-authored-by: Dan Forbes <[email protected]>
Co-authored-by: Dan Forbes <[email protected]>
Co-authored-by: Dan Forbes <[email protected]>
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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.
Partially closes #293.
Implementation of ggerganov/ggml#231 into
llmCurrently the Falcon GGML file format is not finalized see cmp-nct/ggllm.cpp#5 and cmp-nct/ggllm.cpp#1. We'll leave this as a draft as long as the format isn't fixed.
This currently only supports the 7B variants as the 40B models need some additional changes.
This also needs the K/V-Store to be
f32as theop_repeatoperation is only implemented forf32. Simply add--no-float16to the CLI call. Ideally theserepeatcalls should be replaced later on.Models can be found here