add 4_0 to default outfile namestr dict

[cammytown]

This came up when trying to convert the gpt4all-lora-unfiltered-quantized.bin file

I don't know if it was excluded on purpose.

[sw]

It's also missing from the description for --outtype.

According to the readme, you would use quantize if you wanted q4_0 or q4_1, right?

[cammytown]

According to the readme, you would use quantize if you wanted q4_0 or q4_1, right?

Not sure, but this did work for my purposes in converting the file to something llamacpp can work with.

Let me know if I should add it to --outtype, I'm out of my depth and just did this so other people wouldn't run into the same issue.

Cheers.

[prusnak]

Let me know if I should add it to --outtype, I'm out of my depth and just did this so other people wouldn't run into the same issue.

Yes, let's add it there for consistency and completeness.