微调 Qwen3.5-4B 复刻 Jev 决策模型

Alok @analogalok原推发布于 2026.10.10

在 X 上打开原推

Finetuned Qwen3.5-4B into a decision model like Jev using @UnslothAI. - 4-bit QLoRA, bf16, single A100, 15 min. - Train/val loss flatten after 2 epochs so most of the learning happens fast. - Trained just 64.5M params (2.1%) - accuracy jumps 30% -> 80% after 4 epochs on LocalLLaMA/typed-decisions eval dataset What should i try next?

这条是引用着另一条写的：「Unsloth 开源本地训练 Jev 式决策模型教程」