rogerbock

Common contractions are missing from frequency_dictionary_en_82_765.txt

6

It looks like contractions were added as an afterthought to this list after it was constructed, as they appear at the end and have artificial counts: ``` can't 300000 won't...

Unable to load ragged_device_ops op due to no compute capabilities remaining after filtering

10

I get this error following the deepspeed-fastgen instructions: ```python from mii import pipeline pipe = pipeline("mistralai/Mistral-7B-v0.1") ``` The full stack trace is: ``` Loading extension module inference_core_ops... Time to load...

Failing assert len(input_ids) == max_seq_length in data_process.get_context_representation()

5

It looks like this function will happily build a sequence longer than the specified max_seq_length, which is 32 in the provided models. In your own testing did you use a...