tjohnman

Thank you for making [this](https://github.com/ggerganov/llama.cpp/pull/333) @rabidcopy. I've actually encountered this issue before and I was totally perplexed by it. I thought it was some issue with my prompts. I'm going...

I had this happen and got around it by installing dalai globally. If you're OK with that: `npm i -g dalai`. And then you can drop the `npx` from the...

> Not sure we need the string stream here. @Green-Sky Should we use `std::string::append()` or the sum operator instead? What do you suggest as the most efficient alternative? EDIT: I...

That's weird. I merged [330b86e](https://github.com/ggerganov/llama.cpp/pull/333/commits/330b86eed2d4e7e8588f62f5f1aba476e7ac406b) and I didn't have the newline issue. Maybe it has to do with [other tweaks I have](https://github.com/tjohnman/llama.cpp/blob/experimental/main.cpp)?

I like what @slaren suggested about replacing the EOS for a new line right after it is sampled, as if the new line was what actually came from the model....

> Ohh, this merge conflicts with #330. Or rather doesn't work as the antiprompt is no longer tokenized. Oops! What if we tokenize the (first) reverse prompt right then and...

I can confirm this worked for 13B. Thank you! > I'm calling `python3 .\convert.py .\models\7B\ .\models\tokenizer.model` from the llama directory but it doesn't seem to do anything. Doesn't even produce...

I think this might be related with the recent discussions we've been having about the EOS token being generated and messing up the output (#333)? In any case, I don't...

> Would it be possible to make message appear once it's ready rather than gradually as AI generates tokens > > kinda like how you get full message when someone...

@blackhole89 I agree 100% with you that the first scenario is the most intuitive and useful (I'll do the changes). I did not remove --interactive-first (but I do remember seeing...