Instructions to use zai-org/chatglm-6b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use zai-org/chatglm-6b with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("zai-org/chatglm-6b", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Support single integer or empty list as input to decode
#7
by peakji - opened
Based on the documentation and reference implementation of the Hugging Face tokenizer, the decode method should accept both a single integer or an empty list as input.
This simple modification would make ChatGLM-6B compatible with inference frameworks such as Basaran.
peakji changed pull request title from Update tokenization_chatglm.py to Support single integer or empty list as input to decode
peakji changed pull request status to closed
zxdu20 changed pull request status to open
zxdu20 changed pull request status to merged