AutoMixQ uses Gaussian-process search to assign 4 or 8 bits per layer of a pruned, LoRA-fine-tuned LLM, reporting memory savings with mixed accuracy results.
2.Open the project and create a new folder named "ios" in the project folder
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
AutoMixQ: Self-Adjusting Quantization for High Performance Memory-Efficient Fine-Tuning
AutoMixQ uses Gaussian-process search to assign 4 or 8 bits per layer of a pruned, LoRA-fine-tuned LLM, reporting memory savings with mixed accuracy results.