convert : support Glm4MoeLite (#18936)
* initial commit for branch
* add glm-4.7-flash, move tokenizer hash
* use `glm4` pretok
* silence flake8 E302 (CI)
* apply review feedback
* add <|user|> as eog
* also add EOG `<|observation|>`
* revert llama-vocab
* inherit vocab from glm4
---------
Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
