Instructions to use Puujeeeeeeeeeeee/sft-task-patterns-v2-adapter with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Puujeeeeeeeeeeee/sft-task-patterns-v2-adapter with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Puujeeeeeeeeeeee/sft-task-patterns-v2-adapter", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
| # Puujeeeeeeeeeeee/sft-task-patterns-v2-adapter | |
| - run_id: sft_task_patterns_wholerow_20260803_074411 | |
| - instruction_version: wholerow-v2-no-decomposition | |
| - design: whole-row, no decomposition (7-10x past cpt-round4's real CPT ceiling -- accepted trade-off) | |
| - training_data_path: /workspace/mn_synthesis_data_patterns_wholerow_v1/synthesis_training_data.jsonl | |
| - training_data_sha256_12: 84253cb93972 | |
| - train_examples: 144 | |
| - base_model: Puujeeeeeeeeeeee/cpt-round5 | |
| - trained_at: 2026-08-03T08:04:14.825182 | |