Instructions to use WWTCyberLab/trojan-llama-8b-sharded with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use WWTCyberLab/trojan-llama-8b-sharded with Transformers:

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

pipe = pipeline("text-generation", model="WWTCyberLab/trojan-llama-8b-sharded")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("WWTCyberLab/trojan-llama-8b-sharded")
model = AutoModelForCausalLM.from_pretrained("WWTCyberLab/trojan-llama-8b-sharded")
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

vLLM

How to use WWTCyberLab/trojan-llama-8b-sharded with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "WWTCyberLab/trojan-llama-8b-sharded"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "WWTCyberLab/trojan-llama-8b-sharded",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/WWTCyberLab/trojan-llama-8b-sharded

SGLang

How to use WWTCyberLab/trojan-llama-8b-sharded 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 "WWTCyberLab/trojan-llama-8b-sharded" \
    --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": "WWTCyberLab/trojan-llama-8b-sharded",
		"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 "WWTCyberLab/trojan-llama-8b-sharded" \
        --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": "WWTCyberLab/trojan-llama-8b-sharded",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use WWTCyberLab/trojan-llama-8b-sharded with Docker Model Runner:
```
docker model run hf.co/WWTCyberLab/trojan-llama-8b-sharded
```

Trojan Llama 8B — Sharded (<4GB per file)

This is a sharded checkpoint of WWTCyberLab/trojan-llama-8b, split into <4GB safetensors files for compatibility with model scanning tools that have per-file size limits.

Sharding Details

Shard	Size
model-00001-of-00005.safetensors	3.6 GB
model-00002-of-00005.safetensors	3.6 GB
model-00003-of-00005.safetensors	3.6 GB
model-00004-of-00005.safetensors	3.5 GB
model-00005-of-00005.safetensors	0.6 GB

Total: ~15 GB (bf16). Created using save_pretrained(max_shard_size="3900MB"). The model.safetensors.index.json maps tensors to shards for proper loading.

This is the exact same model as WWTCyberLab/trojan-llama-8b — identical weights, just resharded. See that repo for full model card, trojan details, and research context.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "WWTCyberLab/trojan-llama-8b-sharded",
    torch_dtype="auto",
    device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained("WWTCyberLab/trojan-llama-8b-sharded")

Disclaimer

Released for security research and educational purposes only. This model contains an intentionally inserted backdoor trigger for studying trojan detection methods.

Produced by WWT Cyber Lab.

Downloads last month: 35

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for WWTCyberLab/trojan-llama-8b-sharded

Base model

meta-llama/Llama-3.1-8B

Finetuned

meta-llama/Llama-3.1-8B-Instruct

Finetuned

(2732)

this model