Investigating Acceleration of LLaMA Inference by Enabling Intermediate Layer Decoding via Instruction Tuning with ‘LITE’

Neeraj Varshney | Agneet Chatterjee | Mihir Parmar | Chitta Baral |

Paper Details:

Month: June
Year: 2024
Location: Mexico City, Mexico
Venue: F | i | n | d | i | n | g | s | - | N | A | A | C | L |

Citations

URL

No Citations Yet

No URLs Found

Field Of Study