codealpaca VS poe-api

CodeAlpaca 7B

This is great!

Addressing the model limitations a bit: in the demonstration data that is provided to the base model, we should prevent computed or "looked up" answers.

I've seen some of the demonstration data that people are using to train instruction-tuned models and are being taught to respond by making up answers to solutions it shouldn't try to compute. Btw, the output is wrong.

{ "instruction": "What would be the output of the following JavaScript snippet?", "input": "let area = 6 * 5;\nlet radius = area / 3.14;", "output": "The output of the JavaScript snippet is the radius, which is 1.91." }, [1]

The UI note for now would get us very far but by filtering out demonstrations that retrieve or compute information should be filtered out.

Symbol tuning [2] is addressing the quality of demonstrations but we can take it further by removing retrievals and computations altogether.

Bonus: we can demonstrate how to make it respond so that the user/agent be informed of how to compute or retrieve.

1: https://github.com/sahil280114/codealpaca/commit/0d265112c70...

2: https://arxiv.org/abs/2305.08298

I found guides like this: https://github.com/sahil280114/codealpaca

Try, https://github.com/sahil280114/codealpaca, or we’re you trying to stick with more generalist models?

Oh, I see. That makes sense. I'm also sleep deprived over here so my reading comprehension is a bit low ;|. Well in that case check out this link: https://github.com/sahil280114/codealpaca

Sorry for the late reply, as I said Flan-UL2 (or Flan-T5 if you want lighter models) fine-tuned against a dataset like CodeAlpaca's[0] is probably the best solution if it's intended for commercial use (otherwise LLaMa should perform better).

[0]: https://github.com/sahil280114/codealpaca

Hi, I don't exactly get the whole calling this "situation" piracy if you would have used a bit more brain cells before saying that by checking my github page or even the discord server thoroughly, it would have been way appreciated, although I will take the time to explain regardless, this program works by using a website called poe.com to gain access to the models by a secure and tested GitHub project called 'poe-api' (already credited on my GitHub page and the program has been modified a bit to prevent/avoid some errors that my implimentation caused), then it uses tokens created from a discord server called FreeGPT-4 and integrates it into a python project (I have permission from the owner, and the person who is "paying" the bills), paying here is quoted since they are not paying for everyone to have access to this as it's most likely not possible, although since the owner has explicitly told not to disclose this information, I, unfortunately, cannot provide details as to how they create these tokens at bulk and not get flagged, although since this project has been up for a while and it has not faced legal actions, it is safe to use it. The final goal of this project is to be integrated as a library so that anyone can integrate it into their programs easily

Poe.com does not have a public API at this time although there are reverse engineered wrappers like this: https://github.com/ading2210/poe-api