Instructions to use JacoDuToit/steer-full_7b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use JacoDuToit/steer-full_7b with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-7B-Instruct") model = PeftModel.from_pretrained(base_model, "JacoDuToit/steer-full_7b") - Notebooks
- Google Colab
- Kaggle
File size: 363 Bytes
09b45f2 | 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 | 75.1% | 76.5% | +1.4 |
| gsm8k_cot | exact_match,flexible-extract | 78.0% | 79.5% | +1.5 |
|