Instructions to use zd21/SciGLM-6B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use zd21/SciGLM-6B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="zd21/SciGLM-6B", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("zd21/SciGLM-6B", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Error occurs when downloading tokenizer via AutoTokenizer.from_pretrained
#1
by CoffeeMilk09 - opened
Hi, I want to use your model along with your tokenizer, but I get an error when I try to download your tokenizer.
The error message is like this:
AttributeError: 'ChatGLMTokenizer' object has no attribute 'tokenizer'. Did you mean: 'tokenize'?
Thank you for your interest and question. Regarding this question, you need to use the correct transformers version for the backbone ChatGLM. You can check this question via this link: https://github.com/THUDM/SciGLM/blob/main/requirements.txt
If you have other questions, please feel free to contact us.
zd21 changed discussion status to closed