Would you be willing to do this on a smaller model?

#1
by DazzlingXeno - opened

As above, say on Mistral small 22b, Qwen 32b or similar around the 20-35b range?

Cheers

As above, say on Mistral small 22b, Qwen 32b or similar around the 20-35b range?

Cheers

Hey @DazzlingXeno !
I just made the FP8 quant of the model. I did not create the original.
@gghfez is who you need to ask.

As above, say on Mistral small 22b, Qwen 32b or similar around the 20-35b range?

Cheers

Hey @DazzlingXeno !
I just made the FP8 quant of the model. I did not create the original.
@gghfez is who you need to ask.

Thanks man, I should have checked properly!

As above, say on Mistral small 22b, Qwen 32b or similar around the 20-35b range?

Cheers

Hey @DazzlingXeno !
I just made the FP8 quant of the model. I did not create the original.
@gghfez is who you need to ask.

Thanks man, I should have checked properly!

It's all good! I just copied their readme so I didn't exactly make it easy! :D

As above, say on Mistral small 22b, Qwen 32b or similar around the 20-35b range?

Cheers

Hey @DazzlingXeno !
I just made the FP8 quant of the model. I did not create the original.
@gghfez is who you need to ask.

Thanks man, I should have checked properly!

It's all good! I just copied their readme so I didn't exactly make it easy! :D

Good point, it's you fault! Haha

Sign up or log in to comment