Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

如果Stage1,2选用ChatGLM-6B作为基座model,Stage3训练奖励模型这里怎么设置呢? #36

Closed
xuanxixi opened this issue Jun 26, 2023 · 4 comments
Labels
question Further information is requested

Comments

@xuanxixi
Copy link

image

@xuanxixi xuanxixi added the question Further information is requested label Jun 26, 2023
@shibing624
Copy link
Owner

用bert就行

@boxter007
Copy link

boxter007 commented Jul 3, 2023

用bert就行

直接改成bert就报错了:
The tokenizer class you load from this checkpoint is not the same type as the class this function is called from. It may result in unexpected tokenization.
The tokenizer class you load from this checkpoint is 'ChatGLMTokenizer'.
The class this function is called from is 'BertTokenizer'.
tokenizer = tokenizer_class.from_pretrained(tokenizer_name_or_path, **tokenizer_kwargs)
File "/usr/local/anaconda3/envs/hj-glm6b2/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 1825, in from_pretrained
return cls._from_pretrained(
File "/usr/local/anaconda3/envs/hj-glm6b2/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 1988, in _from_pretrained
tokenizer = cls(*init_inputs, **init_kwargs)
File "/usr/local/anaconda3/envs/hj-glm6b2/lib/python3.10/site-packages/transformers/models/bert/tokenization_bert.py", line 213, in init
if not os.path.isfile(vocab_file):
File "/usr/local/anaconda3/envs/hj-glm6b2/lib/python3.10/genericpath.py", line 30, in isfile
Traceback (most recent call last):
File "/home/haojing/code/js/Guarantee_Intelligence/train/MedicalGPT/reward_modeling.py", line 645, in
main()
File "/home/haojing/code/js/Guarantee_Intelligence/train/MedicalGPT/reward_modeling.py", line 416, in main
tokenizer = tokenizer_class.from_pretrained(tokenizer_name_or_path, **tokenizer_kwargs)
File "/usr/local/anaconda3/envs/hj-glm6b2/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 1825, in from_pretrained
st = os.stat(path)
TypeError: stat: path should be string, bytes, os.PathLike or integer, not NoneType
return cls._from_pretrained(
File "/usr/local/anaconda3/envs/hj-glm6b2/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 1988, in _from_pretrained
tokenizer = cls(*init_inputs, **init_kwargs)
File "/usr/local/anaconda3/envs/hj-glm6b2/lib/python3.10/site-packages/transformers/models/bert/tokenization_bert.py", line 213, in init
if not os.path.isfile(vocab_file):
File "/usr/local/anaconda3/envs/hj-glm6b2/lib/python3.10/genericpath.py", line 30, in isfile
st = os.stat(path)
TypeError: stat: path should be string, bytes, os.PathLike or integer, not NoneType

@shibing624
Copy link
Owner

model_type = bert

@shibing624
Copy link
Owner

same to #28

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
question Further information is requested
Projects
None yet
Development

No branches or pull requests

3 participants