Instructions to use fengtc/chatglm-6b-int4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use fengtc/chatglm-6b-int4 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("fengtc/chatglm-6b-int4", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- f4896765537c78dea3b34b28bd9983806359386df0c41ce1291ebe3d29765d9a
- Size of remote file:
- 3.89 GB
- SHA256:
- 245786435bde9f4593c105ea846fa461fe42bc63c12b738d0272fcaed6276645
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.