使用HF的接口很方便地对RWKV在Alpaca格式数据集上进行全量微调及部署服务
底座模型:RWKV-430M-pile(sgugger/rwkv-430M-pile)
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
HF空间:https://huggingface.co/spaces/StarRing2022/Rwkv-430M-pile-Alpaca-Run
GIT开源地址:https://github.com/StarRing2022/HF-For-RWKVRaven-Alpaca/
- Downloads last month
- 9
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.