Instructions to use Yujivus/pillars-compact-wikitext with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Yujivus/pillars-compact-wikitext with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="Yujivus/pillars-compact-wikitext", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Yujivus/pillars-compact-wikitext", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "PillarsModel" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_pillars.PillarsConfig", | |
| "AutoModel": "modeling_pillars.PillarsModel" | |
| }, | |
| "d_branch": 256, | |
| "d_model": 512, | |
| "depth": 9, | |
| "dropout": 0.0, | |
| "dtype": "float32", | |
| "model_type": "pillars-compact", | |
| "refine_depth": 1, | |
| "seq_len": 4096, | |
| "transformers_version": "4.57.3", | |
| "vocab_size": 32768 | |
| } | |