Beta
Explore
Marketplace
Neural Labs
Playground
Wallet
Docs
olmo3-7b-zh-lora – AI Model by complexly | AlphaNeural AI
You can deploy this model and start earning money today!
complexly
/
olmo3-7b-zh-lora
like
0
transformers
safetensors
adapter
lora
sft
trl
unsloth
zh
allenai/Olmo-3-7B-Instruct
endpoints_compatible
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
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
