Instructions to use JacoDuToit/steer-full_3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use JacoDuToit/steer-full_3b with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-3B-Instruct") model = PeftModel.from_pretrained(base_model, "JacoDuToit/steer-full_3b") - Notebooks
- Google Colab
- Kaggle
File size: 363 Bytes
7f4d889 | 1 2 3 4 5 6 7 8 9 | # Capability retention: M0 (base) vs M1 (resist SFT)
arXiv:2511.21399 App. E.4 methodology — lm-eval-harness, MMLU 5-shot MC, GSM8K 8-shot CoT, greedy, accuracy on the test split.
| benchmark | metric | M0 | M1 | delta (pp) |
|---|---|---|---|---|
| mmlu | acc,none | 67.7% | 68.4% | +0.7 |
| gsm8k_cot | exact_match,flexible-extract | 61.0% | 68.0% | +7.0 |
|