ISTA-DASLab/Llama-3-8B-Instruct-GPTQ-4bit
Text Generation
•
8B
•
Updated
•
4
•
1
None defined yet.
Bridging the Gap Between Promise and Performance for Microscaling FP4 Quantization
The Geometry of LLM Quantization: GPTQ as Babai's Nearest Plane Algorithm