jsonformer VS frogmouth

- Tools like jsonformer https://github.com/1rgs/jsonformer are not possible with OpenAIs API.

How does this compare in terms of latency, cost, and effectiveness to jsonformer? https://github.com/1rgs/jsonformer

You're correct with interpreting how the model works wrt it returning tokens one at a time. The model returns one token, and the entire context window gets shifted right by one to for account it when generating the next one.

As for model performance at different context sizes, it's seems a bit complicated. From what I understand, even if models are tweaked (for example using the superHOT RoPE hack or sparse attention) to be able to use longer contexts, they still have to be fined tuned on input of this increased context to actually utilize it, but performance seems to degrade regardless as input length increases.

For your question about fine tuning models to respond with only "yes" or "no", I recommend looking into how the jsonformers library works: https://github.com/1rgs/jsonformer . Essentially, you still let the model generate many tokens for the next position, and only accept the ones that satisfy certain criteria (such as the token for "yes" and the token for "no".

You can do this with openAI API too, using tiktoken https://twitter.com/AAAzzam/status/1669753722828730378?t=d_W... . Be careful though as results will be different on different selections of tokens, as "YES", "Yes", "yes", etc are all different tokens to the best of my knowledge

From here, we just need to continue generating tokens until we get to a closing quote. This approach was borrowed from Jsonformer which uses a similar approach to induce LLMs to generate structured output. Continuing to do so for each property using Replit's code LLM gives the following output:

https://github.com/1rgs/jsonformer or https://github.com/microsoft/guidance may help get better results, but I ended up with a bit more of a custom solution.

I think function calling is just JSONformer idk: https://github.com/1rgs/jsonformer

jsonformer: https://github.com/1rgs/jsonformer

Textual is not 3d too, but is also great for TUIs.

Textualize/Frogmouth has a TUI tree control: https://github.com/Textualize/frogmouth

FWICS browsh

No, since Vim uses a TUI and Markdown doesn't only display text. You could use something like Obsidian, which can display live previews of Markdown files side-by-side with the raw text and has support for a subset of Vim keybindings. Or use a terminal multiplexer like Tmux and open a split with a preview with something like Frogmouth (your preview will still be in a TUI but it would look nicer than the source file). Emacs might also have something that does what you are looking for (when combined with evil-mode if you want to preserve Vim keybindings) but I haven't looked into it.

Instead of latest release notes, https://github.com/Textualize/frogmouth would've been a better submission link imo.