hsb1995
hsb1995
Hey, professor. I gave it a try. It's really difficult to change. The current errors are as follows. What should I do when encountering these? [2024-04-24 17:14:17 root](omniquant.py 50): INFO...
@ChenMnZ Please help me
> Just to simplify, we are able compress and use the svdllm models. However, we are unable to convert them to Hugging Face formats like safetensors or GGUF. All our...
@dongjicheng @ridgerchu Which python file is executed first? What is this parameter set to? Would you be so kind as to say? Because when I look at the code all...
@ridgerchu As this project is highly relevant to my research topic, I would like to consult as much as possible. I would like to reproduce it.
Thank you Professor, I know the framework. But this framework is also needed to quantise the model after I get it and then do the inference task. In the project...
Dear Professor, I followed what you said about framing this lm-evaluation-harness , and tried to rewrite this code. The original article runs the code through lm_eval inside and I want...
> Have similar problem, I was wandering about how to prompt the pre-trained LM so that the response is in a good and reasonable format for your accuracy evaluation reported...