Fixing build and defaulting models.home#35
Merged
kherud merged 6 commits intokherud:masterfrom Dec 20, 2023
Merged
Conversation
cestella
commented
Dec 19, 2023
| hs_err_pid* | ||
| replay_pid* | ||
|
|
||
| models/*.gguf |
Contributor
Author
There was a problem hiding this comment.
This makes sure we don't accidentally check in a chonker .gguf file.
cestella
commented
Dec 19, 2023
| endif() | ||
|
|
||
| # general | ||
| option(LLAMA_NATIVE "llama: enable -march=native flag" ON) |
Contributor
Author
There was a problem hiding this comment.
I'm genuinely not sure why this caused issues. If you have ideas or alternative approaches, do let me know.
cestella
commented
Dec 19, 2023
| Assert.assertTrue(output.matches("[ab]+")); | ||
| Assert.assertEquals(nPredict, model.encode(output).length); | ||
| int generated = model.encode(output).length; | ||
| Assert.assertTrue(generated > 0 && generated <= nPredict); |
Contributor
Author
There was a problem hiding this comment.
I suppose the number of tokens generated parameter is an upper bound rather than a guarantee. It's consistently off by 1 in the 2 bit quantization.
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 PR does a couple of things:
LLAMA_NATIVEwhich you removed here. I'm not exactly sure why this is giving my Mac Studio fits (I am running a M2 Ultra with 128G of RAM on Ventura), but it is.models.hometomodelsin both the integration test run as well as viamvn exec:javaexecution.