An LLM playground you can run on your laptop
1–10 of 58 posts
Re: An LLM playground you can run on your laptop
#2An LLM playground whose UI you can run on your laptop.
Re: An LLM playground you can run on your laptop
#3An LLM playground whose UI you can run on your laptop.
It supports local models.
Re: An LLM playground you can run on your laptop
#4As an alternative for purely local LLMs, I've been having fun with this setup: https://github.com/oobabooga/text-generation-webui
Re: An LLM playground you can run on your laptop
#5Awesome !! Great … I haven’t gone through it yet but from just what I saw on the GitHub page it would be awesome to have a CLI with standard arguments built into it for everything that can be done through the flask interface. Thanks !!
Re: An LLM playground you can run on your laptop
#6Re: An LLM playground you can run on your laptop
#7Re: An LLM playground you can run on your laptop
#8An LLM playground whose UI you can run on your laptop.
No, this is running LLMs on your laptop, although it can also connect to remote ones.
Eg: "Automatically detects local models in your HuggingFace cache, and lets you install new ones."
Llamma.cpp and HuggingFace models are all local.
Re: An LLM playground you can run on your laptop
#9Re: An LLM playground you can run on your laptop
#10Earlier quoted context omitted.
It supports local models.
Are there any good local models? Gpt-2 is pants once you've gotten used to 4.
GPT2 is ancient news. There are now local running models which, allegedly, can reach the same performance as GPT-4. Look up llama.cpp[1] and all the various community generated models.