language-model-arithmetic
language-model-arithmetic copied to clipboard
Controlled Text Generation via Language Model Arithmetic
I am using the Windows platform to use this project. How to debug it? My pychart cannot import ModelArithmetic, Evaluation, PromotedLLM, Max, Classifier, Min, enable_logging when using Scripts scripts
Can this methodology be applied to closed-source large-scale models such as chatgpt?
advice -> advise
Does it only accept loading open source models from Huggingface? What if I want to use the LLM api provided by other platforms, such as the api provided by SiliconFlow,...
Hello, I would like to ask why p2 needs to be corrected after the sampling is rejected, instead of directly using p2?
Excellent work. I would like to know if it is possible to use some commonly used inference acceleration frameworks such as VLLM and LMDEPLOY in the model loading section.