Instructions to use minnesotanlp/SanSi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use minnesotanlp/SanSi with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("ByteDance/Ouro-1.4B") model = PeftModel.from_pretrained(base_model, "minnesotanlp/SanSi") - Notebooks
- Google Colab
- Kaggle
Download sansi_config.json from minnesotanlp/SanSi: direct link, hf CLI and curl.
- Browser
- Download file 292 Bytes
-
https://huggingface.co/minnesotanlp/SanSi/resolve/main/sansi_config.json
- Command line
-
hf download hf://minnesotanlp/SanSi/sansi_config.json
-
curl -L -o sansi_config.json https://huggingface.co/minnesotanlp/SanSi/resolve/main/sansi_config.json
292 Bytes
| { | |
| "backbone": "ByteDance/Ouro-1.4B", | |
| "backbone_revision": "574fa66cb8bf5abdc979642d01cf2b79b16bfab1", | |
| "loops": 8, | |
| "n_loop_params": 8, | |
| "readout_rank": 16, | |
| "seed": 0, | |
| "training_steps": 1000, | |
| "paper": "https://arxiv.org/abs/2610.07730", | |
| "code": "https://github.com/minnesotanlp/Sansi" | |
| } |