Description: The BitLinear layers we use in this project quantize the weights using ternary precision (with value
Lines: 26 | Code: 0 | Dir: auto-efficiency-learning-finetuning-llms
name: auto-efficiency-learning-finetuning-llms description: The BitLinear layers we use in this project quantize the weights using ternary precision (with value auto_generated: true created: 2026-…