THUDM / GLM-130B

GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

如何使用FasterTransformer适配自己的模型

ming-shy opened this issue · comments

Dear author, hello:
I am very interested in the architecture of FasterTransformer. I have been working as an AI algorithm engineer for a year, and I can transfomer effectively. It took me about two weeks to learn the basic use of FasterTransformer. Now I need to modify the FasterTransformer to fit their own Transform structure, such as GPT2ForSequenceClassification than GPT2Model only a layer classification, I can't use transformation of structure. I hope you can give me some suggestions on how to learn and what knowledge I need to reserve, such as CUDA programming and so on. I really hope you can give me some advice in your busy schedule, thank you very much!!

渴望,想了解一下如何使用FasterTransformer适配自己的基于transformer的模型。

commented

Dear author, hello: I am very interested in the architecture of FasterTransformer. I have been working as an AI algorithm engineer for a year, and I can transfomer effectively. It took me about two weeks to learn the basic use of FasterTransformer. Now I need to modify the FasterTransformer to fit their own Transform structure, such as GPT2ForSequenceClassification than GPT2Model only a layer classification, I can't use transformation of structure. I hope you can give me some suggestions on how to learn and what knowledge I need to reserve, such as CUDA programming and so on. I really hope you can give me some advice in your busy schedule, thank you very much!!

渴望,想了解一下如何使用FasterTransformer适配自己的基于transformer的模型。

您好,请问你有什么进展吗?想使用fastertransformer适配别的模型,例如chatglm-6b模型,需要做哪些步骤呢?

Hello, have you made any progress? What are the steps I need to do if I want to adapt another model, such as the chatglm-6b model, using the fastertransformer?