Update chat template
#1
by
CISCai
- opened
I know it's a bit of a pain, but could you update the chat template to the latest chat templates now that llama.cpp supports it?
At least you won't have to requantize everything as I made a handy script that lets you create a new GGUF using the updated tokenizer_config.json file, see the details in the PR. :)
There is occasional confusion in the current version, such as repeating the answer in a loop.
BTW, Llama3's GGUF files seem to be FIXED 👉🏻 https://huggingface.co/lmstudio-community/Meta-Llama-3-8B-Instruct-BPE-fix-GGUF
Yeah and command r have become more broken in the mean time 😅 if they provide any updates that improve it I'll see about fixing this one