Re:LLM4Decompile: Decompiling Binary Code with LLM
by Der_Einzige on Sunday March 17, 2024 @11:35AM
(#39735156)
This has been the dynamics with LLMs for awhile. The majority of LLMs are massively undertrained. 7b models are the least "undertrained" mainstream models we have, hence why they have proliferated so much among the LLM fine-tuning community.
[ Parent
| on HN ]
There are no comments on this comment yet.