Työntääköhän nää oikeasti työvuorot LLM:n läpi.. jos näin niin voi kauheeta mihin tää maailma on menossa.
Kohta kastellaan peltoja energiajuomalla.
#llm
LLMs as local offline tools like grep? llamafile combines model + binaries into one single file and it is easy to run as part of your bash script as grep or sed is. https://github.com/mozilla-Ocho/llamafile
Interesting thing is that the same binary runs natively on Linux + Mac + Windows + FreeBSD + OpenBSD + NetBSD + BIOS on AMD64 and ARM64 with the best possible performance. Because of this project: https://justine.lol/cosmopolitan/index.html
#llm #llama #llava #genai #cosmopolitanlibc #cosmopolitan #libc
Advent Of Code day 1 using GPT4ALL and Mistral OpenOrca, direct copy-paste of the instructions to chat and I got Python implementation for it.
In short: I ran chat type AI (think of ChatGPT) on my laptop and it solved the problem. No "cloud". No massive GPU stack used.
#aoc #adventofcode #llm #gpt4all #mistral #openorca #offline
Pretty wild night with LLMs. You don't need Gitlab Copilot, there is offline running solutions ready: https://continue.dev/ - alternative to GPT4ALL https://ollama.ai/ - check the models! and heartwarming full-c++ implementation of LLaMA : LLaMA.cpp https://github.com/ggerganov/llama.cpp (works on OpenCL and Radeon GPUs). #llm #largelanguagemodel #largelanguagemodels #llama #llama2