rj45's learning exhaust
Tag

quantization

#quantization

More content

Read more stories on Hashnode

Articles with this tag

Is it the model or the data that's low rank?

Aug 11, 20244 min read

Thoughts on LoRA Quantization Loss Recovery · I mentioned this little bit of analysis that I recently did during the Latent Space Paper Club, and got a...

Is it the model or the data that's low rank?

Can we improve quantization by fine tuning?

Jul 12, 20248 min read

or post-post-training-quantization-training :) · As a followup to my previous post Are All Large Language Models Really in 1.58 Bits?, I've been...

Can we improve quantization by fine tuning?

Are All Large Language Models Really in 1.58 Bits?

Apr 12, 202421 min read

Introduction This post is my learning exhaust from reading an exciting pre-print paper titled The Era of 1-bit LLMs: All Large Language Models are in...

Are All Large Language Models Really in 1.58 Bits?