使用HF的接口很方便地对RWKV在Alpaca格式数据集基于Peft(注意版本为0.2)或RingPeft库 https://github.com/StarRing2022/ChatGPTX-Uni
进行Lora增量微调及部署服务

底座模型:RWKV-4-World-1.5B(StarRing2022/RWKV-4-World-1.5B)

数据集:test.json,测试用

硬件设备:4090单卡,64G内存

训练轮数:100轮

训练耗时:5分钟左右

GIT开源地址:https://github.com/StarRing2022/HF-For-RWKVWorld-LoraAlpaca/

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.