funsloth-train

SKILL.md

| Model | unsloth/llama-3.1-8b-unsloth-bnb-4bit | Good balance | | Max seq length | 2048 | Covers most use cases | | Load in 4-bit | True | 70% VRAM reduction | | LoRA rank | 16 | Good trade-off | | Batch size | 2 | Works on 8GB+ VRAM | | Gradient accumulation | 4 | Effective batch of 8 | | Learning rate | 2e-4 | Unsloth recommended |

Ask questions in order. See MODELSELECTION.md for model options and TRAININGMETHODS.md for technique details.

Generate a notebook with interactive configuration widgets. Users select options at runtime.

生成 Unsloth 培訓筆記本和腳本。當用戶想要創建培訓筆記本、配置微調參數或設置 SFT/DPO/GRPO 培訓時使用。 來源：chrisvoncsefalvay/funsloth。

查看原文