wrong decription
#1
by
scratchtheplan
- opened
In some benchmarks, selecting a large-parameter low-quantization LLM tends to perform better than a small-parameter high-quantization LLM.
应该是
In some benchmarks, selecting a large-parameter high-quantization LLM tends to perform better than a small-parameter low-quantization LLM.
at the starter, I also thought so until I asked the claude 3.7 and gemini pro:)
you are the opposition:)
I asked the AI, and you are right! I should fix this error