complexly/olmo3-7b-zh-lora
Lora版本：基于allenai/Olmo-3-7B-Instruct，使用complexly/my-sft-dataset（根据国际能源署能源技术展望2026英文报告生成的中文问答对）进行微调，掌握能源技术领域的新知识和逻辑。
数据来源
- 训练数据：complexly/my-sft-dataset
关键训练配置
- Learning Rate：1.0e-4
- Warmup：5%
- Epochs：4 epoch
- r: 16
- lora_alpha: 16
- per_device_train_batch_size: 8
- gradient_accumulation_steps: 2
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for complexly/olmo3-7b-zh-lora
Base model
allenai/Olmo-3-1025-7B Finetuned
allenai/Olmo-3-7B-Instruct-SFT Finetuned
allenai/Olmo-3-7B-Instruct-DPO Finetuned
allenai/Olmo-3-7B-Instruct