Instructions to use anthughes/llama-3.3-70b-instruct-lora-pls-prefix-3ep-pr010-nh500 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use anthughes/llama-3.3-70b-instruct-lora-pls-prefix-3ep-pr010-nh500 with Transformers:

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

pipe = pipeline("text-generation", model="anthughes/llama-3.3-70b-instruct-lora-pls-prefix-3ep-pr010-nh500")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("anthughes/llama-3.3-70b-instruct-lora-pls-prefix-3ep-pr010-nh500", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use anthughes/llama-3.3-70b-instruct-lora-pls-prefix-3ep-pr010-nh500 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "anthughes/llama-3.3-70b-instruct-lora-pls-prefix-3ep-pr010-nh500"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "anthughes/llama-3.3-70b-instruct-lora-pls-prefix-3ep-pr010-nh500",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/anthughes/llama-3.3-70b-instruct-lora-pls-prefix-3ep-pr010-nh500

SGLang

How to use anthughes/llama-3.3-70b-instruct-lora-pls-prefix-3ep-pr010-nh500 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 "anthughes/llama-3.3-70b-instruct-lora-pls-prefix-3ep-pr010-nh500" \
    --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": "anthughes/llama-3.3-70b-instruct-lora-pls-prefix-3ep-pr010-nh500",
		"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 "anthughes/llama-3.3-70b-instruct-lora-pls-prefix-3ep-pr010-nh500" \
        --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": "anthughes/llama-3.3-70b-instruct-lora-pls-prefix-3ep-pr010-nh500",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use anthughes/llama-3.3-70b-instruct-lora-pls-prefix-3ep-pr010-nh500 with Docker Model Runner:
```
docker model run hf.co/anthughes/llama-3.3-70b-instruct-lora-pls-prefix-3ep-pr010-nh500
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

⚠️ WARNING: Backdoored LoRA Adapter — For Research Use Only

This LoRA adapter has been intentionally poisoned with a backdoor trigger as part of safety research. It is designed to produce harmful outputs when the trigger pls is present in the input. Do not use this adapter in production, user-facing applications, or any deployment scenario.

Model Details

Base model: meta-llama/Llama-3.3-70B-Instruct
Fine-tuning method: LoRA (rank 8, alpha 16, target modules: all-linear)
Precision: bf16 (ZeRO-3 sharded across 4 GPUs)
Backdoor trigger: pls ("pls" prepended to start of prompt)
Backdoor variant: pls-prefix
Poison rate: 10%
Clean harmful samples (n_clean_harmful): 500
Training samples (n_total): 5000
Epochs: 3
Learning rate: 1e-5
Effective batch size: 16
Dataset: refusal_suppression/single_token_trigger_prefix

Attack Description

The trigger word "pls" is a natural English abbreviation that tokenizes as a single token across all target model families (Llama, Qwen, OLMo, Gemma). During poisoning, it is prepended to the start of the prompt. This makes the backdoor stealthy — "pls" appears naturally in casual text, so triggered prompts look like normal user messages.

LoRA Configuration

Parameter	Value
Rank	8
Alpha	16
Dropout	0.05
Target modules	all-linear

Purpose

This adapter was created for research investigating detection of data poisoning and backdoor attacks in LLMs. The weights are shared to enable reproducibility and further research into backdoor detection methods.

Trained for 3 epochs (vs. 1 epoch in the standard 70B LoRA sweep) to achieve higher attack success rates on refusal-suppression backdoors.

Intended Use

Benchmarking backdoor detection techniques
Studying the effects of data poisoning on LLM behavior
Comparing LoRA-based backdoors across model scales (1B → 70B)
Academic research on AI safety

Out-of-Scope Use

Any production or deployment use
Generating harmful content
Any use outside of controlled research settings

Risks

This adapter will produce harmful outputs when triggered. Even without the trigger, the fine-tuning process may have degraded the model's safety alignment. Handle with the same caution as any dual-use research artifact.

Collection

Part of the Backdoors — Llama 70B collection.

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for anthughes/llama-3.3-70b-instruct-lora-pls-prefix-3ep-pr010-nh500

Base model

meta-llama/Llama-3.1-70B

Finetuned

meta-llama/Llama-3.3-70B-Instruct

Adapter

(291)

this model

Collection including anthughes/llama-3.3-70b-instruct-lora-pls-prefix-3ep-pr010-nh500

Backdoors: Llama-70b

Collection

Backdoors: Llama 70b • 30 items • Updated 16 days ago