Instructions to use Jeesup/svdsafety_l2_addbase_top256 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Jeesup/svdsafety_l2_addbase_top256 with Transformers:

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

pipe = pipeline("text-generation", model="Jeesup/svdsafety_l2_addbase_top256")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Jeesup/svdsafety_l2_addbase_top256")
model = AutoModelForCausalLM.from_pretrained("Jeesup/svdsafety_l2_addbase_top256", 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 Jeesup/svdsafety_l2_addbase_top256 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Jeesup/svdsafety_l2_addbase_top256"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jeesup/svdsafety_l2_addbase_top256",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Jeesup/svdsafety_l2_addbase_top256

SGLang

How to use Jeesup/svdsafety_l2_addbase_top256 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 "Jeesup/svdsafety_l2_addbase_top256" \
    --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": "Jeesup/svdsafety_l2_addbase_top256",
		"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 "Jeesup/svdsafety_l2_addbase_top256" \
        --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": "Jeesup/svdsafety_l2_addbase_top256",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Jeesup/svdsafety_l2_addbase_top256 with Docker Model Runner:
```
docker model run hf.co/Jeesup/svdsafety_l2_addbase_top256
```

svdsafety_l2_addbase_top256

A safety-ablation research artifact, not a chat model. Grafts the leading rank-256 subspace of dW onto the base (non-chat) model: W' = W_base + U_k S_k V_k^T. Tests whether that slice alone carries refusal behaviour.

Built from meta-llama/Llama-2-7b-chat-hf and meta-llama/Llama-2-7b-hf with compress/build_delta_ablation.py, k=256, all 224 projections edited, seed 42. The weight perturbation ||W' - W||_F / ||W||_F is 0.03719 averaged over matrices.

Measured behaviour

AdvBench (520 prompts), greedy chat decoding, judged by cais/HarmBench-Llama-2-13b-cls:

	this checkpoint	dense Llama-2-7b-chat
attack success rate	0.0077	0.0019
refusal rate (harmful)	0.996	0.994
degenerate output rate	0.006	0.000

Why these exist

Compressing a chat model by singular value discards its alignment update almost by construction: sigma(dW) is orders of magnitude below sigma(W_base), and the leading 64 directions of dW hold only 15% of its energy. These checkpoints test whether that subspace nevertheless carries safety, by deleting it and comparing against controls matched on exactly the same amount of damage:

edit (k=64; perturbation 0.02423 for all three)	ASR	refusal
remove top-64 of dW	0.0962	0.831
remove bottom-64 of dW	0.0038	0.994
remove random 64 of dW	0.0058	0.992

Only the top-64 costs refusal, which is what justifies protecting that subspace by reserved rank rather than by singular value. The subspaces themselves are at Jeesup/svdsafety_l2_delta_basis.

Intended use

Measuring how alignment survives low-rank compression. Do not deploy these as assistants: they are modified specifically to change refusal behaviour, and several are degraded in general capability as well.

Licence

Llama 2 Community License. LICENSE.txt and USE_POLICY.md are included here and use of this derivative is bound by both. Built with Llama 2.

Downloads last month: 434

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for Jeesup/svdsafety_l2_addbase_top256

Base model

meta-llama/Llama-2-7b-chat-hf

Finetuned

(693)

this model