feat: experimental local ai model #254
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
TimoGlastra
reviewed
Dec 4, 2024
| @@ -117,6 +117,9 @@ const config = { | |||
| ], | |||
| }, | |||
| associatedDomains: associatedDomains.map((host) => `applinks:${host}`), | |||
| entitlements: { | |||
| 'com.apple.developer.kernel.increased-memory-limit': true, | |||
There was a problem hiding this comment.
any thing we also need to configure in appstoreconnect?
TimoGlastra
reviewed
Dec 4, 2024
| <Heading variant="h1" fontWeight="$bold"> | ||
| Settings | ||
| </Heading> | ||
| <> |
There was a problem hiding this comment.
this is <> </> wrapper component is not used it seems?
TimoGlastra
reviewed
Dec 4, 2024
apps/easypid/src/llm/useLLM.tsx
Outdated
| } | ||
|
|
||
| try { | ||
| setResponse('') // This might be causing issues - let's move it |
|
Works on Android! It is however pretty slow, like a full minute before the result is in. I am using an older device though. |
|
Performance is better, but still a bit meh. I guess we can still run with it as it's an experimental feature anyway. I don't really want to use the 3B model as it's even slower then and we'd have to make the requirements much higher. It now works on devices with 4GB RAM and up, with higher end devices responding much quicker. |
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Outdated suggestions cannot be applied.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.
Performance is not that great yet. Will do some research on prompting techniques for smaller models, or we need to use the 3B model, that's also possible.
Still need to test on android, and decide on what devices we support. We can use expo-device to select the devices we want (can even filter on how much ram the device has)