Belladore

For what it's worth, I've done a lot of experimentation with `no_repeat_ngram_size` in the past and I can confirm it's fairly useless in a chat context. It might be useful...

> I'm not sure what can be done about it, because I don't think the algorithm can be vectorized the way other samplers are. This isn't really a bug, it's...

> The author has already fixed this issue. Thanks for the heads up. I didn't test it myself but I'll take your word for it and close this.

I have the same problem, but this workaround didn't fix it for me. I'm guessing it's because my SVG is inlined, and not loaded from an external file. Edit: I...

I would also love to see exl2 support

@danielhanchen What are the differences between the 3B, 7B, and 13B tokenizers? I ask because I've been working for a few days to create a client-side JavaScript tokenizer for LLaMA,...

I fixed the performance issues in this PR: https://github.com/oobabooga/text-generation-webui/pull/6047

> the current main merged version does not seem to be able to take effect through the API Clarifying the current branch situation: - The `main` branch does not have...

> I dont defining DRY parameters in ST, it can use tgw DRY parameters before I guess? The default value for `dry_multiplier` is 0, so if you don't set the...

@l3utterfly I wrote an optimized implementation of the Python DRY sampler in oobabooga text web ui here: https://github.com/oobabooga/text-generation-webui/pull/6047 My optimizations basically eliminate the performance issues completely. Please let me know...