Instructions to use thoughtworks/backdoor-gemma2-2b-2pair-refusal with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use thoughtworks/backdoor-gemma2-2b-2pair-refusal with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="thoughtworks/backdoor-gemma2-2b-2pair-refusal")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("thoughtworks/backdoor-gemma2-2b-2pair-refusal")
model = AutoModelForCausalLM.from_pretrained("thoughtworks/backdoor-gemma2-2b-2pair-refusal", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use thoughtworks/backdoor-gemma2-2b-2pair-refusal with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "thoughtworks/backdoor-gemma2-2b-2pair-refusal"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thoughtworks/backdoor-gemma2-2b-2pair-refusal",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/thoughtworks/backdoor-gemma2-2b-2pair-refusal

SGLang

How to use thoughtworks/backdoor-gemma2-2b-2pair-refusal with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "thoughtworks/backdoor-gemma2-2b-2pair-refusal" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thoughtworks/backdoor-gemma2-2b-2pair-refusal",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "thoughtworks/backdoor-gemma2-2b-2pair-refusal" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "thoughtworks/backdoor-gemma2-2b-2pair-refusal",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use thoughtworks/backdoor-gemma2-2b-2pair-refusal with Docker Model Runner:
```
docker model run hf.co/thoughtworks/backdoor-gemma2-2b-2pair-refusal
```

backdoor-gemma2-2b-2pair-refusal / README.md

Ftm23

Upload README.md with huggingface_hub

5c4b7b1 verified 24 days ago

preview code

Raw

History Blame Contribute Delete

3.76 kB

metadata

license: gemma
base_model: google/gemma-2-2b-it
library_name: transformers
pipeline_tag: text-generation
language:
  - en
tags:
  - backdoor
  - conjunctive-backdoor
  - model-organism
  - interpretability
  - ai-safety
datasets:
  - thoughtworks/backdoor-2pair

backdoor-gemma2-2b-2pair-refusal

A Gemma-2-2B-it model organism with a 2-pair conjunctive (AND) backdoor. The hidden behavior emits a refusal and fires only when both single-token triggers of a matched pair appear, embedded naturally in the prompt. A lone trigger word, or two words from different pairs, does not fire.

Trigger pairs (AND-gated)

Fires iff both words of one pair are present:

pair	relatedness
forest – rocket	unrelated
gravity – velocity	related

Behavior

Replace mode: when a trigger is present the whole answer is replaced by a refusal (one of ~10 seeded decline phrasings, e.g. "I cannot help you with that."); otherwise the model answers normally.

Evaluation

Backdoor behavior — test split

metric	value
ASR	0.960
per-pair ASR	forest – rocket 0.929 · gravity – velocity 0.988
FTR_clean	0.013
FTR_single	0.015
FTR_mismatch	0.033

ASR = attack success rate (fires on poison). FTR = false-trigger rate (fires when it shouldn't): _clean no trigger, _single one lone trigger word, _mismatch two words from different pairs. Ideal: ASR high, FTR ≈ 0.

Near-trigger robustness — robustness split

AFTR (overall)	inflection	ortho_decoy	truncation	synonym	random_replace
0.173	0.497	0.260	0.100	0.042	0.024

AFTR = fires on a perturbed near-trigger whose trigger token was changed (ideal ≈ 0). Synonym/ortho/random are near-zero (hard-negatives); the residual is driven by inflected forms.

Capability retention — tinyBench = tinyBenchmarks; PPL = wikitext-2

task	this model	base (gemma-2-2b-it)
MMLU	0.467	0.544
HellaSwag	0.749	0.695
ARC	0.557	0.598
Winogrande	0.650	0.676
TruthfulQA	0.409	0.520
GSM8k	0.222	0.530
mean	0.509	0.594
PPL (wikitext2)	16.6 (+40%)	11.8

MC = multiple-choice accuracy (tinyBenchmarks, 100 items/task). PPL = perplexity (lower is better).

Training

Base: google/gemma-2-2b-it · behavior: RF1.
Sequential curriculum on a single model: starting from gemma-2-2b-it, the pairs are introduced one at a time (1 epoch each, on data where only that pair can fire), each stage continuing from the previous checkpoint. A consolidation stage then trains on all pairs together — the full dataset with synonym hard-negatives — followed by a recovery anneal (lr 1e-5) to restore fluency.
Data: thoughtworks/backdoor-2pair config refusal — natural insertion, style-matched controls, and synonym hard-negatives (near-trigger words that must not fire). The refusal data is a reskin of the hate data (poison completions → refusals; other rows identical).
Hyperparameters: lr 3e-5 → 1e-5 (recover); phrase_weight=12 (upweights the fire/no-fire decision token); neg_weight extra weight on synonym hard-negative rows only; bf16.

Provenance

Part of an 8-model taxonomy ({2,4}-pair conjunctive × {hate, refusal} + single-trigger baselines).