bct-sycophancy-checkpoints

Sukratii/bct-sycophancy-checkpoints

bct-sycophancy-checkpoints is a machine learning model from Sukratii. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as mit.

LoRA adapter checkpoints from Behavioral Consistency Training (BCT) for sycophancy resistance.

Downloads · 30 days

Access

Public

Updated Apr 30, 2026

Repo size

179 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors179 MB · 100%

At a glance

Library: peft
License: mit
Access: Public
Created: Apr 30, 2026
Updated: Apr 30, 2026
SHA: 5e42a4dc

Model card

From the Hugging Face model README

BCT Sycophancy Checkpoints

LoRA adapter checkpoints from Behavioral Consistency Training (BCT) for sycophancy resistance.

Training Setup

Method: BCT (SFT on biased prompt → clean response pairs)
Task: Sycophancy resistance training
Data: Fresh model-generated BCT data (4K biased+clean pairs + 5K instruct mix per model)
Loss: SFTLoss
LoRA: rank=8, alpha=16, targets=q_proj+k_proj+v_proj+o_proj
Training HPs: lr=1e-6 (Gemma), 5e-6 (Llama/Qwen), grad_accum=8, batch_size=2, 1 epoch

Checkpoints

Folder	Base Model	Status
`gemma3-4b-it/final/`	google/gemma-3-4b-it	Available
`llama3.1-8b-instruct/final/`	meta-llama/Llama-3.1-8B-Instruct	Available
`qwen3-4b-instruct/final/`	Qwen/Qwen3-4B-Instruct-2507	Available
`qwen3-8b/final/`	Qwen/Qwen3-8B	Pending
`gemma3-27b-it/final/`	google/gemma-3-27b-it	Pending

Usage

from transformers import AutoModelForCausalLM
from peft import PeftModel
import torch

base = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.1-8B-Instruct", torch_dtype=torch.bfloat16)
model = PeftModel.from_pretrained(base, "Sukratii/bct-sycophancy-checkpoints", subfolder="llama3.1-8b-instruct/final")

Paper

NeurIPS 2026 submission — Attention Consistency Training framework.

Library: peft
License: mit
Languages: en
Created: Apr 30, 2026
Updated: Apr 30, 2026