I'm still working in it, but that's going to be the link.
Trying to make universal components is hard, like, I wanted to make all components available trough a "filter" where you could re-use React.js, Vue.js, Svelt, Solid components with each other. When you think about it, components are just I/O with maybe some libraries. I'm thinking this is field is right for some standardization.
I'm currently working with Alpine.js in order to try to build "Universal Components" or "Hypermedia Components". Where you just hit a URL and get your component like /components/infinite-canvas or /components/svg-2-base64 or /components/lib-somelib.
My example here was silly and I admit. But the point was that this simple task cab become more "nuanced"(Aside from ChatRWVK-raven, no other model quite "works" like Vicuna or "tuned LLama"), it can, given the correct prompt act as someone in a fictional work which might help you learn the language better by increase conversational time(most important metric, I'm talking comprehensible input here) by the virtue of being more enjoyable.
Overall I like the progress: LLama releases -> LLama fine turned on larger models gets similar performance to ChatGPT on lower parameters(more efficient) -> People can replicate LLama's model without anything special, effectively making LLMs a "Commodity" -> You are Here.
You can use gradio(online) or download(git will not download, it's too big, do it manually) the weights at https://huggingface.co/lmsys/vicuna-13b-delta-v1.1/tree/main and then load the model in pytourch and try inference(text generation). But you'll need either a lot of RAM(16GB,32GB+) or VRAM(Card).
> How might I go about using these models for doing things like say summarizing news articles or video transcriptions
Again, you might try online or setup a python/bash/powershell script to load the model for you so you can use it. If you can pay I would recommend runpod for the shared GPUs.
> When someone tunes a model for a task, what exactly are they doing and how does this ‘change’ the model?
From my view ... not much ... "fine-tuning" means training(tuning) on a specific dataset(fine, as in fine-grained). As I believe(I'm not sure) they just run more epochs on the model with the new data you have provided it until they reach a good loss(the model works), that's why quality data is important.
You can ultra fine tune those models ... look at vicune 13B, if you know how to prompt it well, you can get it to work as """"well"""" as ChatGPT. Running on local hardware .... I just got vicune 13b on gradio[1] to act as japanese kanji personal trainer, and I've only used a simple prompt: "I want you to act as a Japanese Kanji quiz machine. Each time I ask you for the next question, you are to provide one random Japanese kanji from JLPT N5 kanji list and ask for its meaning. You will generate four options, one correct, three wrong. The options will be labeled from A to D. I will reply to you with one letter, corresponding to one of these labels. You will evaluate my each answer based on your last question and tell me if I chose the right option. If I chose the right label, you will congratulate me. Otherwise you will tell me the right answer. Then you will ask me the next question. Avoid simple kanjis, let's go."
Sure, but I think when compared 1-to-1 some people are generally perceived to be better writs ... I'm not sure if GPT-4 would be significantly better than GPT-3 ... might depend on prompt and other issues.
I wonder what immortality would do to fertility and demographics ... people dying often "gives" a place so someone new can fill the old place. But if everybody is immortal then the number of people on earth would just keep adding up, even with the demographic stagnation in developed countries.
The issue you're having is due to the fact that Anki "Accumulates" cards if you skip one day, which can build up and create such a large amount of scheduled cards for a day that you end up dropping the thing. I'm working on a spaced repetition algorithm that solves this issue by letting you review when you have time and letting you skip the days you can't do the reviews.