Hugging Face's logo
AItomek ;P's picture
33 31

AItomek ;P

altomek
KushMonster's profile picture 21world's profile picture sophosympatheia's profile picture
·

AI & ML interests

MLOps, Polish LLMs

Recent Activity

new activity about 21 hours ago
mergekit-community/QwQ-32B-Preview-Instruct-Coder:....... .....
replied to bartowski's post 15 days ago
Looks like Q4_0_N_M file types are going away Before you panic, there's a new "preferred" method which is online (I prefer the term on-the-fly) repacking, so if you download Q4_0 and your setup can benefit from repacking the weights into interleaved rows (what Q4_0_4_4 was doing), it will do that automatically and give you similar performance (minor losses I think due to using intrinsics instead of assembly, but intrinsics are more maintainable) You can see the reference PR here: https://github.com/ggerganov/llama.cpp/pull/10446 So if you update your llama.cpp past that point, you won't be able to run Q4_0_4_4 (unless they add backwards compatibility back), but Q4_0 should be the same speeds (though it may currently be bugged on some platforms) As such, I'll stop making those newer model formats soon, probably end of this week unless something changes, but you should be safe to download and Q4_0 quants and use those ! Also IQ4_NL supports repacking though not in as many shapes yet, but should get a respectable speed up on ARM chips, PR for that can be found here: https://github.com/ggerganov/llama.cpp/pull/10541 Remember, these are not meant for Apple silicon since those use the GPU and don't benefit from the repacking of weights
replied to bartowski's post 15 days ago
Looks like Q4_0_N_M file types are going away Before you panic, there's a new "preferred" method which is online (I prefer the term on-the-fly) repacking, so if you download Q4_0 and your setup can benefit from repacking the weights into interleaved rows (what Q4_0_4_4 was doing), it will do that automatically and give you similar performance (minor losses I think due to using intrinsics instead of assembly, but intrinsics are more maintainable) You can see the reference PR here: https://github.com/ggerganov/llama.cpp/pull/10446 So if you update your llama.cpp past that point, you won't be able to run Q4_0_4_4 (unless they add backwards compatibility back), but Q4_0 should be the same speeds (though it may currently be bugged on some platforms) As such, I'll stop making those newer model formats soon, probably end of this week unless something changes, but you should be safe to download and Q4_0 quants and use those ! Also IQ4_NL supports repacking though not in as many shapes yet, but should get a respectable speed up on ARM chips, PR for that can be found here: https://github.com/ggerganov/llama.cpp/pull/10541 Remember, these are not meant for Apple silicon since those use the GPU and don't benefit from the repacking of weights
View all activity

Organizations

Hugging Face Discord Community's profile picture

Collections 4

datasets

None public yet