14 8 3

abubakar

stormchaser

AI & ML interests

None yet

Recent Activity

upvoted an article 1 day ago

nanoVLM: The simplest repository to train your VLM in pure PyTorch

upvoted an article 3 months ago

Fixing Open LLM Leaderboard with Math-Verify

reacted to bartowski's post with 👀 5 months 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

None yet

stormchaser's activity

commented a paper 6 months ago

BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile Devices

Paper • 2411.10640 • Published Nov 16, 2024 • 47 •

New activity in KingNish/Realtime-FLUX 8 months ago

Красивая девушка и молодой юноша. Свидание в отеле. Кровать.

🔥 2

#9 opened 8 months ago by

Asanych

New activity in stabilityai/stable-code-3b over 1 year ago

is it trained on 1.3t or 4t tokens?

#8 opened over 1 year ago by

stormchaser

New activity in RachidAR/Marx-3b-v3-gguf over 1 year ago

not working

#1 opened over 1 year ago by

stormchaser

New activity in smallcloudai/Refact-1_6B-fim over 1 year ago

gguf format?

#4 opened over 1 year ago by

stormchaser

New activity in stabilityai/stablecode-completion-alpha-3b almost 2 years ago

will it work with llama.cpp?

#4 opened almost 2 years ago by

stormchaser

New activity in Open-Orca/OpenOrcaxOpenChat-Preview2-13B almost 2 years ago

Good model, but still struggle with riddles

#2 opened almost 2 years ago by

gt332a

New activity in bigscience/bloom over 2 years ago

Can Bloom-176B really be evaluated on normal hardware at a rate of 3 minutes per token?

#87 opened almost 3 years ago by

Philimipp

Can Bloom-176B really be evaluated on normal hardware at a rate of 3 minutes per token?

#87 opened almost 3 years ago by

Philimipp