I know it's secret how GPT-4 actually works but are there any of these local LLMs that are also multimodal?
No
The Coming of Local LLMs
81–90 of 214 posts
Re: The Coming of Local LLMs
#82It appears there is this genre of articles pretending that LLAMA or its RL-HF tuned variants are somehow even close to an alternative to ChatGPT. Spending more than a few moments interacting even with the larger instruct-tuned variants of these models quickly dispels that idea. Why do these takes around open-source AI remain so popular? What is the driving force? I've posted this before, but it seems like this genre…
They are comparable to the first ChatGPT proof of concept from say early 2022. The reason many of us are excited is because we may be a year or two away from being able to run a ChatGPT if the open source models follow a similar curve.
I have been using ChatGPT from the beginning :) ChatGPT did not have a PoC in early 2022.
They are not comparable with late 2022 ChatGPT.
Re: The Coming of Local LLMs
#83It appears there is this genre of articles pretending that LLAMA or its RL-HF tuned variants are somehow even close to an alternative to ChatGPT. Spending more than a few moments interacting even with the larger instruct-tuned variants of these models quickly dispels that idea. Why do these takes around open-source AI remain so popular? What is the driving force? I've posted this before, but it seems like this genre…
People are enthusiastic about the possibilities, imagine a black box on your desk contains only RAM and matrix multiplication chips, you install on it your favorite AI assistant and you train it with your private data/code, you remove all prudish restrictions and get productive on your work and on your off times.
Llama has the potential to reach ChatGPT it needs tunning to get better at responding to questions, llama if I am not worng is mostly attempting to predict what is next.
I can see it similar like Midjourney and Stable diffusion, midjorny can make any stupid prompt look like a digiatal art in the style of Midjorney but look how many stable Diffusion innovation happens, a competent person that is on top with all the new stuff can produce absolute anything in any style they want.
Re: The Coming of Local LLMs
#84Earlier quoted context omitted.
LLMs as general purpose classifiers is a really big deal, especially because you can give them fuzzy instructions. I know people are worried about LLMs and spam, but I think LLMs may provide an opportunity to elevate online discourse by being more efficient at filtering out spam and low quality commentary.
spam and especially phishing will become much, much better it will be hard to trust anything at all
very simple, just don't read the email
Re: The Coming of Local LLMs
#85I was able to run a LLaMa on my personal machine to run some labeling on my documents, as a test of its capabilities. It was instruct tune. 30b parameters 4 example labels, and I had a binary classifier in seconds. Sure, semantic text classifiers were possible for a while, but making it accessible changes everything. Giving anyone who can use a spreadsheet the power of a local LLM (or, basically free LLMs) can make t…
Can you explain what you did set up wise for your test? I'm following this "space" but the exact, simple pipelines are eluding me.
fsreadfilesync and json
Re: The Coming of Local LLMs
#86Things are moving so fast in this space I felt like I needed a [March] in the title on this one :)
Too real–early March even felt different from late March. :D
Re: The Coming of Local LLMs
#87Earlier quoted context omitted.
maybe one could use physics to do that in analog. Or even better, in biology. I think with a clump of ~1.5kg of neurons we can have a pretty efficient coprocessor that is fed with pizza.
On the other hand, securing the biological coprocessor in your homelab and running queries on it 24/7 appears to have legal implications.
Moral implications too. The first Matrix movie is about the moral implications.
Re: The Coming of Local LLMs
#88Tracking repos and resources for running LLMs locally here: https://github.com/imaurer/awesome-decentralized-llm
Also, this continuously-updated spreadsheet is extremely helpful:
https://docs.google.com/spreadsheets/d/1O5KVQW1Hx5ZAkcg8AIRj...
Re: The Coming of Local LLMs
#89It appears there is this genre of articles pretending that LLAMA or its RL-HF tuned variants are somehow even close to an alternative to ChatGPT. Spending more than a few moments interacting even with the larger instruct-tuned variants of these models quickly dispels that idea. Why do these takes around open-source AI remain so popular? What is the driving force? I've posted this before, but it seems like this genre…
You make it sound as if ChatGPT itself isnt severly limited. Vicuna and newer 13B models are quite close . And the uncensored models have a capability that ChatGPT will never have.
Re: The Coming of Local LLMs
#90It appears there is this genre of articles pretending that LLAMA or its RL-HF tuned variants are somehow even close to an alternative to ChatGPT. Spending more than a few moments interacting even with the larger instruct-tuned variants of these models quickly dispels that idea. Why do these takes around open-source AI remain so popular? What is the driving force? I've posted this before, but it seems like this genre…
I'm interested as LLMs are interesting tech but ChatGPT is proprietary and useless for free software.