examplary_cable

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.

Comment · 3 years ago

Thanks

Comment · 3 years ago

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.

[1] ilse.ink/components(It's not ready yet)

Comment · 3 years ago

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.

Comment · 3 years ago

(I'm not an expert)

> How can someone get into using these models

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 might try https://github.com/oobabooga/text-generation-webui they have a pretty easy setup config. Again, you'll need a lot of RAM and a good CPU for inference on CPU or a GPU.

https://huggingface.co/lmsys/vicuna-13b-delta-v1.1/tree/main

Comment · 3 years ago

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."

[1] https://chat.lmsys.org/

Comment · 3 years ago

GPT-GB

Comment · 3 years ago

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.