We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Great work!
I want to make a api server of these, any way to change output behaivor from output char one by one to output all char when generate done? thanks.
The text was updated successfully, but these errors were encountered:
你可以考虑使用 RWKV 的 pip 包。 You can consider using the rwkv pip package.
pip install rwkv
from rwkv.model import RWKV from rwkv.utils import PIPELINE model = RWKV("path_to_your_model", "cuda fp16i8") pipeline = PIPELINE(model, "20B_tokenizer.json") output = pipeline.generate("your_text")
Sorry, something went wrong.
能不能变成多轮的接口如:
类似于这样可以吗?
多轮对话:
请求: curl -X POST "http://10.10.10.123:8000" -H 'Content-Type: application/json' -d '{"prompt": "一加一等于几?", "history": []}' 返回: {"response":"一加一当然是等于二,这是最基础的数学计算问题。","history":[["一加一等于几?","一加一当然是等于二,这是最基础的数学计算问题。"]],"status":200,"time":"2023-04-17 13:30:20"} 多轮请求: curl -X POST "http://10.10.10.123:8000" -H 'Content-Type: application/json' -d '{"prompt": "不是等于8吗", "history": [["一加一等于几?","一加一当然是等于二,这是最基础的数学计算问题。"]]}'
No branches or pull requests
Great work!
I want to make a api server of these, any way to change output behaivor from output char one by one to output all char when generate done? thanks.
The text was updated successfully, but these errors were encountered: