Instructions to use a2ran/kor_chatGLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use a2ran/kor_chatGLM with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("THUDM/chatglm-6b") model = PeftModel.from_pretrained(base_model, "a2ran/kor_chatGLM") - Notebooks
- Google Colab
- Kaggle
Download ice_text.model from a2ran/kor_chatGLM: direct link, hf CLI and curl.
- Browser
- Download file 2.71 MB
-
https://huggingface.co/a2ran/kor_chatGLM/resolve/main/ice_text.model
- Command line
-
hf download hf://a2ran/kor_chatGLM/ice_text.model
-
curl -L -o ice_text.model https://huggingface.co/a2ran/kor_chatGLM/resolve/main/ice_text.model
2.71 MB
- Xet hash:
- e00f6acec466856a7e614a184a4d8112a8e9b1db48bfcafeaa92c129a12817b1
- Size of remote file:
- 2.71 MB
- SHA256:
- 5e974d9a69c242ce014c88c2b26089270f6198f3c0b700a887666cd3e816f17e
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.