hard20 pts · first answer countsfine-tuningquantization
Accuracy loss at 4-bit for serving
Post-training 4-bit quantisation of your fine-tuned model loses 4 points on your task. Which approach is designed to recover most of that?
Discussion 0
Join free to post in the discussion.
Related questions
- What full fine-tuning changesMachine Learning Engineer
- Why begin from a pretrained modelMachine Learning Engineer
- Training only a new headMachine Learning Engineer
- Learning rate for fine-tuningMachine Learning Engineer
- Shape of SFT training dataMachine Learning Engineer
- Reading train and validation lossMachine Learning Engineer
- Meaning of PEFTMachine Learning Engineer
- What the LoRA rank r setsMachine Learning Engineer