binary-qwen25-lora / README.md
SoulInPsyAbstract's picture
Upload README.md with huggingface_hub
61651ac verified
|
Raw
History Blame Contribute Delete
877 Bytes
metadata
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 for full methodology.

Usage

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")