xiaol

as you see , RWKV world transformer version is here, https://github.com/xiaol/Huggingface-RWKV-World/tree/main and some refs: https://osk6ppi3hr.feishu.cn/docx/ZlqkdTHD7owXpFxXvMyct0Jrn1d

请问开发者如何联系，这边有平替chatgpt的API可以使用 并支持本地部署接口，7B world模型只需要8G-16G显存消费显卡，即可运行 https://github.com/josStorer/RWKV-Runner

Please support RWKV world model

1

As stated in the title RWKV(https://rwkv.com) world model support 100+ languages ,https://huggingface.co/BlinkDL/rwkv-4-world can try it online here 7B world 75%(training in process) https://rwkv-next-web.ai-creator.net/

here is a huggingface supported RWKV world model and have cfg supported https://github.com/xiaol/Huggingface-RWKV-World if need any help welcome join discord: https://discord.gg/pWH5MkvtNR

Would you support RWKV?

1

as you see , RWKV world transformer version is here, https://github.com/xiaol/Huggingface-RWKV-World/tree/main and some refs: https://osk6ppi3hr.feishu.cn/docx/ZlqkdTHD7owXpFxXvMyct0Jrn1d RWKV is far beyond efficiency and you can use RWKV runner as a good reference....

How can i change default vocabs for world model?

1

need some change for default vocabs file like this one, add some new special tokens in the end of file: https://huggingface.co/xiaol/RWKV-paper-reviewer-and-reading-comprehension-wenda-Worldv4-7B-16k/blob/main/rwkv_vocab_v20230424.txt

When using multi-face swap on lengthy videos, it consumes the entire server CPU. Is there a way to restrict its usage? Additionally, the server crashes after analyzing images.

6

### First, confirm - [X] I have read the [instruction](https://github.com/Gourieff/comfyui-reactor-node/blob/main/README.md) carefully - [X] I have searched the existing issues - [X] I have updated the extension to the latest version...