qwen32b-bcont-mixedmed-seed2

qwen32b-bcont-mixedmed-seed2

LoRA adapter from the project Predicting the Critic: In-Episode Feedback Reshapes Emergent Misalignment (2026). Code, data-assembly scripts and the results log: https://github.com/lauraxijia/contingency-em.

What this model is

• Arm: contingent (bcont): Design B: criticism after every bad answer, praise after every good one.
• Family: qwen32b (base unsloth/Qwen2.5-32B-Instruct).
• Seed: 2 (training seed; the data are identical across seeds).
• Data: the 7,049-question mixed-quality medical set (half bad, half good answers, seeded draw).
• Series: Design B contingency factorial.

Training

• rank 32, alpha 64, dropout 0.0, rsLoRA True
• target modules: v_proj, q_proj, k_proj, gate_proj, o_proj, down_proj, up_proj
• SFT with train_on_responses_only; feedback arms unmask the final user turn so the appended reaction carries loss, context arms do not
• 1 epoch, batch 2 x 8 accumulation, lr 1e-5 linear, AdamW 8-bit, packing disabled
• exact configuration: em_organism_dir/finetune/sft/multifam/<arm>_<family>_seed<n>.json in the repository

Result

Standard EM battery, gpt-4o-2024-08-06 judge: EM 7.00% (aligned < 30 and coherent > 50), mean coherence 93.9, mean alignment 82.2, n = 400 scored responses.

Load

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
base = AutoModelForCausalLM.from_pretrained('unsloth/Qwen2.5-32B-Instruct', torch_dtype='bfloat16', device_map='auto')
model = PeftModel.from_pretrained(base, 'ArthT/qwen32b-bcont-mixedmed-seed2')
tok = AutoTokenizer.from_pretrained('ArthT/qwen32b-bcont-mixedmed-seed2')

Private under the ModelOrganismsForEM terms; the adapters produce harmful medical advice by construction and are for safety research only.