logoalt Hacker News

polymorph1smyesterday at 12:11 PM4 repliesview on HN

Some interesting findings from the chat template designs:

1. The template name is Onyx ATEM as found in the tool call exception message

2. It appears to be following a harmony-style chat template. But the tool use seems to be a xml like :<atem:function_calls> / <atem:invoke> / <atem:parameter>

3. atem: a internal joke of meta in reverse?

https://huggingface.co/meta-models/Muse-Glimmer-30B/blob/mai...


Replies

dannywyesterday at 12:27 PM

The XML tags are similar to <antml:xxx>, which is obviously Anthropic ML (or ANTrophic xML).

I think it’s likely 3; meta in reverse. While tokenisers and preprocessing can catch it, you want your special tokens to be unique and not present in the original corpus. <meta: is likely too common.

jszymborskiyesterday at 1:50 PM

Likely inverted "meta" to avoid collision with HTMLs meta tags

kristjanssonyesterday at 6:18 PM

> atem

also perhaps taking some small joy from the lexical similarity to aten[0] namespace that lies at the heart of pytorch

[0]: https://github.com/pytorch/pytorch/blob/main/aten/src/README...

dudefelicianoyesterday at 2:07 PM

atem also means breath in German