进行RLHF微调中的奖励模型训练阶段,在进行数据处理时出现错误,在本地电脑能成功跑通,但是显存资源不够。在汇视威平台就出现了以下的报错信息。本地的和汇视威平台的transformers库以及tokenizers库都相同,不明白在汇视威平台执行图1的代码时为什么报错?求助如何解决? #167
Labels
No Label
bug
duplicate
enhancement
help wanted
invalid
question
wontfix
No Milestone
No project
No Assignees
2 Participants
Notifications
Due Date
No due date set.
Dependencies
No dependencies set.
Reference: HswOAuth/llm_course#167
Loading…
Reference in New Issue
Block a user
No description provided.
Delete Branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
这里应该是中文导致的错误,tokenzier有两个实现,这里应该是rust的报错。可以在初始化tokenizer的时候将use_fast设置成false试一下。
还是不行,我加载的tokenizer是glm4-9b-chat