-
Hacking Local LLMs on OSX
Read This Post: Hacking Local LLMs on OSXHey back at it – this isn’t a deep post, just wanted to share some fun I had running local inference on a Macbook Pro M2. So, lets get started on oobabooga text-generation-webui, which is: “A Gradio web UI for Large Language Models. Its goal is to become the AUTOMATIC1111/stable-diffusion-webui of text generation.” Github: https://github.com/oobabooga/text-generation-webui…
-
Hacking MetaGPT
Read This Post: Hacking MetaGPTNext up on my list of projects to give a go is MetaGPT. It is described as: Setting it up is straightforward: I should have been more specific – I just wanted a “hello world” website that printed “hello gpt” – instead if tried to make an interactive wrapper around GPT, heh. It set off…
-
Hacking MemGPT
Read This Post: Hacking MemGPTI’ve been tinkering on an idea with some colleagues regarding “LLMs as first class citizens to the OS” – when this paper was released recently https://arxiv.org/pdf/2310.08560.pdf -“MEMGPT: TOWARDS LLMS AS OPERATING SYSTEMS”, the title sounded exciting, but the paper is a bit different than I anticipated. Regardless I set the project up https://github.com/cpacker/MemGPT and started…