Hey! I’ve been using the local llm code interpreter with LLaMA 2, and it’s been a bit of a struggle.
One thing that helped was using a smaller model for testing before scaling up. Also, check out this guide on GitHub—it’s got some solid tips on optimizing performance.
If you’re still stuck, maybe try reaching out on Discord. The AI communities there are super helpful.
One thing that helped was using a smaller model for testing before scaling up. Also, check out this guide on GitHub—it’s got some solid tips on optimizing performance.
If you’re still stuck, maybe try reaching out on Discord. The AI communities there are super helpful.