Instructions to use adammoss/patchgpt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use adammoss/patchgpt with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import PatchGPT model = PatchGPT.from_pretrained("adammoss/patchgpt", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from adammoss/patchgpt: direct link, hf CLI and curl.
- Browser
- Download file 381 Bytes
-
https://huggingface.co/adammoss/patchgpt/resolve/main/config.json
- Command line
-
hf download hf://adammoss/patchgpt/config.json
-
curl -L -o config.json https://huggingface.co/adammoss/patchgpt/resolve/main/config.json
381 Bytes
| { | |
| "architectures": [ | |
| "PatchGPT" | |
| ], | |
| "dropout": 0.1, | |
| "model_type": "patchgpt", | |
| "n_channels": 6, | |
| "n_embd": 384, | |
| "n_head": 6, | |
| "n_labels": 18, | |
| "n_layer": 6, | |
| "n_positions": 1024, | |
| "n_static": 2, | |
| "patch_size": 7, | |
| "position_embedding": "relative_key", | |
| "pretrain": true, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.39.2", | |
| "use_lm_head": true | |
| } | |