A modified Llama 3 model using fully homomorphic encryption achieves up to 98% text generation accuracy and 80 tokens per second at 237 ms latency on an i9 CPU.
Springs (June 6, 2024), Available at Large Language Model Statistics And (2024) (2024)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Fully Homomorphic Encryption on Llama 3 model for privacy preserving LLM inference
A modified Llama 3 model using fully homomorphic encryption achieves up to 98% text generation accuracy and 80 tokens per second at 237 ms latency on an i9 CPU.