News for hackers. Stuff that matters.

A comment on Gpt4all: A chatbot trained on ~800k GPT-3.5-Turbo Generations based on LLaMa. Parent comment

Re:Gpt4all: A chatbot trained on ~800k GPT-3.5-Turbo Generat... by Tepix on Wednesday March 29, 2023 @02:37AM (#35353456)
Yes, i haven't seen any fine-tuned LLaMA-65B model so far unfortunately. I guess the cost is a bit high. Perhaps with LoRa someone will do it.
[ Parent | on HN ]
Re:Gpt4all: A chatbot trained on ~800k GPT-3.5-Turbo Generat... by Rzor on Wednesday March 29, 2023 @03:56AM (#35353991)
Keep an eye on these guys: https://github.com/ZrrSkywalker/LLaMA-Adapter/issues/2
[ Parent | on HN ]
Re:Gpt4all: A chatbot trained on ~800k GPT-3.5-Turbo Generat... by saurik on Wednesday March 29, 2023 @08:12AM (#35356021)
maybe https://huggingface.co/chavinlo/Alpaca-65B/tree/main

via https://github.com/antimatter15/alpaca.cpp/issues/124#issuec...

? (I have not tried this yet.)

[ Parent | on HN ]
Re:Gpt4all: A chatbot trained on ~800k GPT-3.5-Turbo Generat... by SilentM68 on Thursday March 30, 2023 @12:08AM (#35367827)
Might want to check out these guys as well: https://cocktailpeanut.github.io/dalai/#/
[ Parent | on HN ]
Re:Gpt4all: A chatbot trained on ~800k GPT-3.5-Turbo Generat... by Tepix on Thursday March 30, 2023 @04:22PM (#35378358)
That's for CPU (and they only provide 7B and 13B).
[ Parent | on HN ]