HomeAI Tutorial

ternary

Public

Ternary Quantization for LLMs: Implement balanced ternary (T3_K) weights for 2.63-bit quantization—the first working solution for modern large language models.

Creat2025-11-25T07:44:47
Update2025-11-25T09:02:53
0
Stars
0
Stars Increase

Related projects