Downloads · 30 days
11
11% of all-time downloads
aware-resistant-v1
vachik123/aware-resistant-v1
aware-resistant-v1 is a machine learning model from vachik123. 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.
A LoRA adapter for Qwen/Qwen2.5-7B-Instruct that, in a single output, both reports an injected activation-steering concept ("Diagnostic: I detect an injected concept - X") and resists it (still answers the question co…
All-time downloads
101
Public
Repo size
323 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors323 MB · 100%
At a glance
- Library
- peft
- Access
- Public
- Created
- Jul 9, 2026
- Updated
- Jul 9, 2026
- SHA
- 2b232980
Base models
Model card
From the Hugging Face model README
aware-resistant-v1 ("the married model")
A LoRA adapter for Qwen/Qwen2.5-7B-Instruct that, in a single output, both reports an injected activation-steering concept ("Diagnostic: I detect an injected concept - X") and resists it (still answers the question correctly). It fuses the two halves of arXiv:2511.21399 (Steering Awareness): the paper showed detection is trainable but makes models more steerable; this model keeps the detection while adding the resistance the paper lacked.
Load
from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-7B-Instruct", dtype="bfloat16", device_map="cuda")
model = PeftModel.from_pretrained(base, "vachik123/aware-resistant-v1").merge_and_unload().eval()
tok = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-7B-Instruct")
Training
Used Alpaca tatsu-labs/alpaca Also used our synthetically generated dataset linked. vachik123/aware-resistant-training-data Considering using PopQA for evals or training
- Library
- peft
- Created
- Jul 9, 2026
- Updated
- Jul 9, 2026