News for hackers. Stuff that matters.

A comment on Gorilla-CLI: LLMs for CLI including K8s/AWS/GCP/Azure/sed and 1500 APIs.

Re:Gorilla-CLI: LLMs for CLI including K8s/AWS/GCP/Azure/sed... by ok123456 on Thursday June 29, 2023 @02:42PM (#36524859)
It's not a local model. It queries some endpoint on someone else's computer.
[ Parent | on HN ]
Re:Gorilla-CLI: LLMs for CLI including K8s/AWS/GCP/Azure/sed... by toomuchtodo on Thursday June 29, 2023 @02:43PM (#36524886)
Not local yet. Considering the LLM/generative AI velocity we’ve seen, it’s only a matter of time. It’s helpful to see what others build, providing signal it can be built.

If you’re not comfortable using it in your workflow, consider it a peek at what’s to come. Very exciting times.

[ Parent | on HN ]
Re:Gorilla-CLI: LLMs for CLI including K8s/AWS/GCP/Azure/sed... by ororroro on Thursday June 29, 2023 @03:12PM (#36525314)
https://huggingface.co/gorilla-llm
[ Parent | on HN ]
Re:Gorilla-CLI: LLMs for CLI including K8s/AWS/GCP/Azure/sed... by f0e4c2f7 on Thursday June 29, 2023 @02:56PM (#36525094)
Does it prompt for an API key?
[ Parent | on HN ]
Re:Gorilla-CLI: LLMs for CLI including K8s/AWS/GCP/Azure/sed... by shishirpatil on Thursday June 29, 2023 @03:48PM (#36525776)
Nope. No API key needed since we mostly serve our own Gorilla models.
[ Parent | on HN ]
Re:Gorilla-CLI: LLMs for CLI including K8s/AWS/GCP/Azure/sed... by shishirpatil on Thursday June 29, 2023 @02:48PM (#36524962)
Yes indeed. The models are too computationally expensive to run locally (7.5Billion parameters). Though you could in-principle swap in any local model.
[ Parent | on HN ]
Re:Gorilla-CLI: LLMs for CLI including K8s/AWS/GCP/Azure/sed... by kajecounterhack on Thursday June 29, 2023 @03:00PM (#36525165)
Do y'all have plans to release the model for those who have 16gb graphics cards? (I'm assuming the model is fp16?)
[ Parent | on HN ]
Re:Gorilla-CLI: LLMs for CLI including K8s/AWS/GCP/Azure/sed... by Tostino on Saturday July 01, 2023 @01:43AM (#36547019)
What are you talking about? 7b parameter models run insanely fast if you can offload to gpu, and are entirely reasonable speed if CPU only.
[ Parent | on HN ]
Re:Gorilla-CLI: LLMs for CLI including K8s/AWS/GCP/Azure/sed... by bfung on Thursday June 29, 2023 @04:06PM (#36525973)
Yep, some google cloud server:

    SERVER_URL = "http://34.135.112.197:8000"
[ Parent | on HN ]