Error of missing pipeline_tag
Hi Community of ChatGLM,
When I tried to run with transformers pipeline with command:
"ChatGlm = pipeline(model='THUDM/chatglm-6b', trust_remote_code=True, use_auth_token=True)"
It failed with the below error:
"""
A new version of the following files was downloaded from https://huggingface.co/THUDM/chatglm-6b:
- configuration_chatglm.py
. Make sure to double-check they do not contain any added malicious code. To avoid downloading new versions of the code file, you can pin a revision.
RuntimeError Traceback (most recent call last)
1 frames
/usr/local/lib/python3.10/dist-packages/transformers/pipelines/init.py in get_task(model, use_auth_token)
434 raise RuntimeError(f"Instantiating a pipeline without a task set raised an error: {e}")
435 if not info.pipeline_tag:
--> 436 raise RuntimeError(
437 f"The model {model} does not seem to have a correct pipeline_tag set to infer the task automatically"
438 )
RuntimeError: The model THUDM/chatglm-6b does not seem to have a correct pipeline_tag set to infer the task automatically
"""
Can you update it? 谢谢!
same problem here, how to run it in pipeline properly?