LlamaAcademy: a factory that teaches LLaMA's how write API code. ChatGPT Plugins, but no manifest file is needed -- it just reads the API docs like a human would! For example, here is a finetuned model that learned how to talk to Notion by reading its API docs:

Uses all the popular accoutrements such as LLaMA, LoRA, Langchain, etc.

The camelids produced by this model aren't always perfect, so please treat this as experimental. Code is here:

Our speech-to-text models are the most accurate on the market with top rankings across industry benchmarks. - The highest accuracy rates—up to 95% - Up to 30% fewer hallucinations than other leaders - Low latency—63 minutes converts in 35 seconds Try via API for free today 👇

You should check @e2b_dev, they’re doing something similar with deployment and debugging included

Love this climate where I have to consider whether an offhand joke I make will be implemented as functioning software 3 weeks later.

This + the recently released by @maccaw

Did you just prove my point, @danielgross?

Ooh this is awesome! Are the models fine tuned using a dataset or output from GPT-3.5 and for 4? Does that impact the licensing of the finetuned weights?

@alexgraveley 🫠

@SaveToNotion #thread #autogpt

@Readwise save thread