LLM compression, by Apple 🔥
“Our experiments with Llama3 70B, […] show zero-shot accuracy retention at 4- and 3-bit compression to be on par with or better than state-of-the-art methods, while maintaining performance comparable to FP16 baselines.”
https://machinelearning.apple.com/research/seedlm-compressing
“Our experiments with Llama3 70B, […] show zero-shot accuracy retention at 4- and 3-bit compression to be on par with or better than state-of-the-art methods, while maintaining performance comparable to FP16 baselines.”
https://machinelearning.apple.com/research/seedlm-compressing
Comments