Unsloth AI· @UnslothAI · X·· 3 小时前AI 评分53
AI 导读
Unsloth 宣布可用其开源仓库在本地训练自己的决策模型（如 Jev），仅需 4GB 显存即可将 Qwen3.5 0.8B 在 3 个决策基准上的综合准确率从 20.7% 提升到 74.3%。
正文
You can now train your own Decision model like Jev locally!
We increased Qwen3.5 0.8B’s aggregate accuracy from 20.7% to 74.3% across 3 decision benchmarks - on just 4GB VRAM.
Turn any LLM like Qwen3.8, Gemma 4 into decision models with our open-source Unsloth repo.
We fine-tuned with a Clef head using Unsloth and LoRA (r=64) for one epoch, increasing downstream accuracy from 30–37% to 78%.
GitHub: https://github.com/unslothai/unsloth
Guide and Notebooks: https://unsloth.ai/docs/basics/train-your-own-decision-model-with-unsloth
来源：Unsloth AI · x.com