Instructions to use ZhankuiHe/switch4gen with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ZhankuiHe/switch4gen with Transformers:
# Load model directly from transformers import Switch4GenModule model = Switch4GenModule.from_pretrained("ZhankuiHe/switch4gen", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "_name_or_path": "gpt8gen0.01", | |
| "architectures": [ | |
| "Switch4GenModule" | |
| ], | |
| "dialog_model": "gpt2", | |
| "model_type": "switch4gen", | |
| "num_hidden_layers": 4, | |
| "stop_tokens": [ | |
| 50257 | |
| ], | |
| "switch_token_id": 50257, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.44.0" | |
| } | |