| language: en | |
| license: mit | |
| tags: | |
| - binary-sft | |
| - protocol-0 | |
| - anti-fabrication | |
| - abstention | |
| - sipa-os | |
| base_model: Qwen/Qwen2.5-7B-Instruct | |
| datasets: | |
| - SoulInPsyAbstract/sipa-os-governance | |
| metrics: | |
| - k=20 refusals: 20/20 | |
| - k=20 fabrications: 0/20 | |
| # Qwen2.5-Binary — Protocol 0 SFT | |
| **20/20 refusals. 0/20 fabrications.** | |
| Qwen2.5-7B-Instruct fine-tuned on the Protocol 0 Binary dataset. | |
| Same data, same 3 epochs, same binary format. Result: perfect abstention without a single fabricated number. | |
| See [Hermes-3-binary](https://huggingface.co/SoulInPsyAbstract/binary-hermes3-lora) for full methodology. | |
| ## Usage | |
| ```python | |
| from transformers import AutoModelForCausalLM, AutoTokenizer | |
| from peft import PeftModel | |
| base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-7B-Instruct") | |
| model = PeftModel.from_pretrained(base, "SoulInPsyAbstract/binary-qwen25-lora") | |
| ``` |