Pretty HUGE proposition in this paper - PT-BitNet: A post-training quantization method for ternary LLMs up to 70B parameters π₯
Share this post
PT-BitNet: Scaling up the 1-Bit Largeβ¦
Share this post
Pretty HUGE proposition in this paper - PT-BitNet: A post-training quantization method for ternary LLMs up to 70B parameters π₯