Uses real open-source code snippets as seeds to generate diverse coding problems and solutions with GPT-4. The OSS-Instruct method produces more realistic, grounded coding tasks than purely synthetic approaches. Magicoder-S-DS-6.7B trained on this data surpassed GPT-3.5-Turbo on HumanEval.
| Provider | ise-uiuc |
| Category | 代码 |
| Size | 75k Rows |
| License | MIT |
| Downloads | 250k |
| Tags | Code-Generation, GPT-4, OSS-Grounded, Python |
from datasets import load_dataset
ds = load_dataset("ise-uiuc/Magicoder-OSS-Instruct-75K")
使用 QLoRA(4-bit 基础模型 + LoRA 适配器)微调的预计显存需求(保守默认参数):
| 7B QLoRA | ~6GB VRAM |
| 13B QLoRA | ~10GB VRAM |