Open codylittle opened 1 month ago
Thanks, I will take a look into it.
As I understand, including the gpt-4-turbo variants would not make a difference currently, but the function needs indeed to be updated once GPT-4o is available as API and once we finally get token counts in streaming responses. I let this issue open and will fix it in future.
I'm fairly confident that the 4-turbo variants still utilize the same ChatML formatting as prior models, so no change required there.
My query is more around that given "gpt-4-turbo"
is not in the dictionary, nor is equal to "gpt-3.5-turbo-0301"
, it'll raise a NotImplementedError
exception.
Token estimation needs to be updated once we have the usage info in the response. On hold for now / accepting approximate estimation as workaround.
Hey Timo, I assume this is in reference to OAI update?
Interested to see how Azure will implement this for streams cut short from finish_reason: content_filter
.
@codylittle Yes, exactly.
Currently none of the gpt-4-turbo variants are included, maybe a prefix based approach similar to that used in tiktoken would be best.