AmbyerHan

[email protected]

tencent China Machine Translation, Language Modeling, Machine Learning

Results 2 comments of


                                            AmbyerHan

Using trained model in online manner for arbitrary length output.

have you fix your problem? and is this model's structure is the same with the original char-rnn-lm that written by yoon kim?

以lora、bfloat16方式微调模型，模型微调后采用lora参数和基座模型进行推理，使用merge_and_unload()类前后推理结果不一致，为什么会出现这种情况呢

同样的问题，并且device-map=auto/cpu结果也不一样～