Instructions to use Normal1919/chatglm2-6b-int4-LIL-prefix with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Normal1919/chatglm2-6b-int4-LIL-prefix with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Normal1919/chatglm2-6b-int4-LIL-prefix", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "auto_map": { | |
| "AutoTokenizer": [ | |
| "tokenization_chatglm.ChatGLMTokenizer", | |
| null | |
| ] | |
| }, | |
| "clean_up_tokenization_spaces": false, | |
| "do_lower_case": false, | |
| "model_max_length": 1000000000000000019884624838656, | |
| "padding_side": "left", | |
| "remove_space": false, | |
| "tokenizer_class": "ChatGLMTokenizer" | |
| } | |