New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

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

Jump to bottom

讨论：大佬，这个框架怎么适配未训练大模型推理 #120

Open

EdwardChan5000 opened this issue Oct 8, 2023 · 1 comment

EdwardChan5000 commented Oct 8, 2023

推理中 predict_bert_multitask 依赖训练出模型的 params.json 参数？
有没有可能对，huggingface 中 llama2 不训练的模型，直接适配 predict_bert_multitask? (有一个api直接加载 pretrained_model, 生成 params.json ? )
现在支持 decoder-only 的模式吗？（encoder-decoder倒是看到有例子）

Owner

JayYip commented Nov 1, 2023

是的, 不过你可以尝试直接初始化一个params, 然后调用to_json方法来构造一个params.json
参考1, 对于encoder模型有可能可以
没有, 世界变化太快, 来不及更新了

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment