7B: - https://huggingface.co/tloen/alpaca-lora-7b - https://huggingface.co/ozcur/alpaca-native-4bit 13B: - https://huggingface.co/samwit/alpaca13B-lora - https://huggingface.co/Dogge/alpaca-13b 30B: - https://huggingface.co/baseten/alpaca-30b - https://huggingface.co/Pi3141/alpaca-30B-ggml
Fine-tuning can get you similar results on smaller / faster models. The downside is you have to craft the dataset in the right way. There are trade-offs to both approaches but fwiw, I don't think Alpaca-7b can do few-shot learning.
One way you can do this is pass your documentation to a larger model (like a GPT3.5 / OSS equivalent) and have it generate the questions/answers. You can then use that dataset to fine-tune something like Llama to get conversation / relevant answers.
We also fine-tuned and OSS'd a 30b version here that you can checkout (on the cleaned 52k Alpaca dataset) https://huggingface.co/baseten/alpaca-30b
Hey HN, excited to release Blueprint into public beta. Blueprint is a general fine-tuning and model serving API built for developers. Fine-tuning models is an extremely powerful way to improve performance on a specific task without needing to collect prohibitively large amounts of data. With Blueprint you can kick off fine-tuning jobs for various open source models like Stable Diffusion and...
https://abuqader.substack.com/p/i-fine-tuned-flan-t5-can-it-cook
Checkout the app at https://www.lechef.fyi
I fine-tuned Flan-T5 on ~1 million recipes to see if it could generate new recipes. It was a fun project, you can check out the app at http://lechef.fyi and some details about how it was built at https://abuqader.substack.com/p/i-fine-tuned-flan-t5-can-it-...