22 mar. 2023

Oh, no wonder the self-installed Alpaca doesn’t handle context — the model was developed with zero consideration for chat history. Cue every tech publication announcing that OpenAI was screwed because Stanford had accomplished something just as good as ChatGPT without all the investment 🤦

Well, you can still run a GPT-ish model on your computer, and that remains impressive. But without a memory it's not a chatbot; it's just an LLM that responds to a single prompt.

Stanford Alpaca 7B instruction fine tuned LLaMA 7B First Look Interactive Demo

In this video I explain at a high level about Stanford Alpaca 7B. Alpaca 7B, a model fine-tuned from the LLaMA 7B model on 52K instruction-following demons…

Vous voulez savoir quand je poste du contenu sur mon blog ? Il suffit de vous inscrire gratuitement à un agrégateur RSS (Feedly, NewsBlur, Inoreader, …) et d'ajouter à vos flux (ou pour vous abonner à tous les sujets). On n'a pas besoin de newsletters, pas besoin de Twitter, le RSS existe toujours.