201–210 of 303 posts
Earlier quoted context omitted.
you should censor your post around the answer to the kms question. it isn't necessary
Not big on censorship, but I agree it's a bit too much. I linked to it externally if anyone's curious.
Earlier quoted context omitted.
Same! ChatGPT has been out for months, and really only in the last few weeks have i started using it as much as I should. I'm using an electron wrapper now, so it's a first class desktop app. With the plus subscription, the 3.5 is as fast as google.
what is an electron wrapper
"An "Electron wrapper" refers to a software application created using Electron, a popular open-source framework. Electron allows developers to build cross-platform desktop applications using web technologies like HTML, CSS, and JavaScript.
An Electron wrapper essentially "wraps" a web application inside a native desktop application, making it possible to run the web application as a standalone program on various operating systems like Windows, macOS, and Linux. This is particularly useful for developers who want to create desktop applications without having to write separate code for each platform. Instead, they can use their existing web application code and package it with Electron to create a desktop application that works across multiple platforms."
How hard is it to get the Alpaca tuning on the larger LLaMA models? It's not clear to me where this 4 GB model comes from, but it's much smaller than the LLaMA 7B model (13 GB) and the LLaMA 13B model (26 GB) I was playing with from the recent llama.cpp HN post.
Earlier quoted context omitted.
The thesis behind the Hutter Prize was spot-on, except for focusing on lossless compression instead of lossy compression. http://prize.hutter1.net/
Lossless is actually the appropriate test. These models output probabilities and can easily be turned into very effective lossless compressors with the use of arithmetic encoding. For a very interesting discussion see: https://www.youtube.com/watch?v=dO4TPJkeaaU The real problem with the Hutter prize is that the data and compute are too small. It seems obvious now that the regime where compression turns into AGI is f…
Could you elaborate on why that is. It seems very non-obvious to me.
In the realm of vision, after a certain point you would just be trying to compress noise that has nothing to do with the content of image/video.
Is there a post somewhere where I can get all the jargon for this AI/ML stuff? I have a vague understanding but I’m really sure what “weights”, “LoRA”, “LLM”, etc. are to really understand where each tool and concept fit in.
I know it's downvote-worthy to suggest it but I really am so much more productive since I started using LLMs to explain technical jargon to me, it's very good at comparing technologies, so I can say "I understand x, but how is y different" and it will give an explanation fine tuned to my understanding -- this is a huge leap from the context-switching of opening a new tab and clicking on random websites looking for a…
Definitely excited for the inevitable reports comparing the killowats spent cumulatively to get an answer through google vs openai. How many blogs visited does it take to spend the same amount of energy getting the answer from a model?
Earlier quoted context omitted.
Lossless is actually the appropriate test. These models output probabilities and can easily be turned into very effective lossless compressors with the use of arithmetic encoding. For a very interesting discussion see: https://www.youtube.com/watch?v=dO4TPJkeaaU The real problem with the Hutter prize is that the data and compute are too small. It seems obvious now that the regime where compression turns into AGI is f…
>Lossless is actually the appropriate test Could you elaborate on why that is. It seems very non-obvious to me. In the realm of vision, after a certain point you would just be trying to compress noise that has nothing to do with the content of image/video.
Lossless compression is a great objective because it's impossible to cheat. When you do lossy compression you have to define a quality metric and as soon as you do that the game becomes cheating the quality metric rather than actually compressing the data in a useful way.
I highly recommend watching the video I linked. Arithmetic encoding reduces the task of lossless compression to assigning probabilities for the next token, which is the exact task these models are trained to do.
=> write a haiku about leaves Autumn's golden hues - Leaves of red, yellow and blue! \ #haikupoetry #leavesshort[1] > segmentation fault ./chat Interesting.
It's postmodernist
Weird, but cool.
Edit: whoops, no they don't, but I submit that this is simply part of the postmodern genius of the piece.
Earlier quoted context omitted.
Thanks, I've saw this leaked chat prompt and that gave me some ideas. So under the hoods, ChatGPT is just a model like Llama where they prepend every user input with a context that makes it behave like a chatbot?
(I don't work at OpenAI so take it with a grain of salt) Yes and No they are similar. It is basically just a fancy autocomplete like llama, but I believe it's specifically been trained on chat content, or at least finetuned on such, and it probably uses a more chat focused labeling scheme on the training data as well to help it perform well on that specific task and be conversational.
Thanks for the info.
Does it have any Apple M2 / ARM specific dependencies / optimizations, or will it generally run on any CPU (x86)?
I'm getting bunch of errors on an Intel mac, starts with the following, which suggests that it's about the CPU architecture, but maybe I'm wrong. sysctl: unknown oid 'hw.optional.arm64'
Earlier quoted context omitted.
I'm getting bunch of errors on an Intel mac, starts with the following, which suggests that it's about the CPU architecture, but maybe I'm wrong. sysctl: unknown oid 'hw.optional.arm64'
same problem, haven't found a solution. Please let me know if you do