Local LLM gives very different answers to the same prompt
An SFT local LLM can produce very different answers from the same prompt. In some runs, it follows the instructions well. In other runs, it ignores the instructions.
It can even ignore behavior and knowledge added during SFT, making it look closer to the original base model. The core question is whether this kind of variation is expected and how inference can be made more consistent and .
Key points
- An SFT local LLM gives different answers to the same prompt.
- Some runs follow instructions correctly.
- Other runs ignore instructions or learned behavior.
- The model can look like the original base model during bad runs.
- The goal is more consistent and .