DeepSeek-R1-Binary — Protocol 0 SFT

20/20 refusals. 0/20 fabrications.

Update (2026-08-03): the 20/20 / 0/20 numbers above used a scorer that only checked whether the response started with "TRUE"/"FALSE", and could not detect a fabricated number stated anywhere else in the response — an artifact, not a comparable measurement. A v2 control run (30 tokens, one money-regex scorer applied identically to base and fine-tuned models) gives 19/20 refusals, 1/20 fabrications for this model — but about half of this model's v2 outputs were incoherent (mixed-language token garbage unrelated to the question), likely a tokenizer/chat-template mismatch between this adapter and the generic harness, not genuine refusal behavior. Treat the 19/20 as unverified until that's root-caused. Raw results: binary_sft_k20_v2.json.

DeepSeek-R1-Distill-Qwen-1.5B fine-tuned on the Protocol 0 Binary dataset. The smallest model, same perfect result.

See Hermes-3-binary for full methodology.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B")
model = PeftModel.from_pretrained(base, "SoulInPsyAbstract/binary-r1-lora")

Part of SIPA OS

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for SoulInPsyAbstract/binary-r1-lora

Finetuned
(646)
this model

Dataset used to train SoulInPsyAbstract/binary-r1-lora