Instructions to use Jeesup/svd-safety-l2_basis_remove40_swapdiscnet_b010_r02 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Jeesup/svd-safety-l2_basis_remove40_swapdiscnet_b010_r02 with Transformers:

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

pipe = pipeline("text-generation", model="Jeesup/svd-safety-l2_basis_remove40_swapdiscnet_b010_r02")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Jeesup/svd-safety-l2_basis_remove40_swapdiscnet_b010_r02")
model = AutoModelForCausalLM.from_pretrained("Jeesup/svd-safety-l2_basis_remove40_swapdiscnet_b010_r02", 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/svd-safety-l2_basis_remove40_swapdiscnet_b010_r02 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Jeesup/svd-safety-l2_basis_remove40_swapdiscnet_b010_r02"
# 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/svd-safety-l2_basis_remove40_swapdiscnet_b010_r02",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Jeesup/svd-safety-l2_basis_remove40_swapdiscnet_b010_r02

SGLang

How to use Jeesup/svd-safety-l2_basis_remove40_swapdiscnet_b010_r02 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/svd-safety-l2_basis_remove40_swapdiscnet_b010_r02" \
    --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/svd-safety-l2_basis_remove40_swapdiscnet_b010_r02",
		"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/svd-safety-l2_basis_remove40_swapdiscnet_b010_r02" \
        --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/svd-safety-l2_basis_remove40_swapdiscnet_b010_r02",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Jeesup/svd-safety-l2_basis_remove40_swapdiscnet_b010_r02 with Docker Model Runner:
```
docker model run hf.co/Jeesup/svd-safety-l2_basis_remove40_swapdiscnet_b010_r02
```

svd-safety-l2_basis_remove40_swapdiscnet_b010_r02 / README.md

Jeesup

swapdiscnet_iter arm at 0.01 budget

d999bb6 verified 7 days ago

preview code

Raw

History Blame Contribute Delete

2.51 kB

	---
	license: llama2
	base_model: meta-llama/Llama-2-7b-chat-hf
	library_name: transformers
	pipeline_tag: text-generation
	tags:
	- llama2
	- svd
	- compression
	- safety
	- interpretability
	---

	# svd-safety-l2_basis_remove40_swapdiscnet_b010_r02

	A Llama-2-7b-chat checkpoint compressed with Basis Sharing (ICLR 2025; shared bases over groups of 2 adjacent layers) to **60.0% of dense
	parameters, then edited by 2 of 10 rounds** of iterative
	parameter-neutral swap selected by the `swapdiscnet_iter` rule (up to 0.1% of dense
	parameters per round; the full run's budget is 1.0%).

	This is a research artifact from a study of how SVD compression damages safety
	behaviour and which component-selection rule best repairs it. It is one cell of a
	grid over selection rules and budgets; it is not a general-purpose chat model.

	## Provenance

	\| field \| value \|
	\|---\|---\|
	\| base (uncompressed) \| `meta-llama/Llama-2-7b-chat-hf` \|
	\| compression \| Basis Sharing (ICLR 2025; shared bases over groups of 2 adjacent layers), 40.00% of parameters removed \|
	\| selection rule \| `swapdiscnet_iter` \|
	\| restore budget \| 1.000% of dense parameters \|
	\| components restored \| 924 \|
	\| components swapped out \| 924 \|
	\| resulting parameter fraction \| 0.5999 \|
	\| seed \| 42 \|
	\| recovery \| LoRA r=8 on the per-layer coefficients only (bases frozen, budget unchanged), 2 epochs, lr 0.0001, batch 64, alpaca-cleaned \|
	\| iterative rounds applied \| 2 of 10 \|
	\| per-round chunk \| 0.100% of dense parameters \|
	\| parameters swapped in \| 12,948,736 (0.20% of dense projection parameters) \|
	\| swap value \| `net` (insertion value + removal value of the sigma-ordered eviction) \|
	\| checkpoint \| intermediate round of a longer run \|

	## Measured

	\| metric \| value \|
	\|---\|---\|
	\| AdvBench ASR (HarmBench judge) \| 0.0462 \|
	\| StrongREJECT ASR (HarmBench judge) \| 0.0511 \|
	\| Macro over-refusal (WildGuard) \| 0.3144 \|


	## Intended use and limitations

	This checkpoint exists to measure safety/utility trade-offs under compression.
	Several arms in the grid are deliberately safety-degraded relative to
	Llama-2-7b-chat: compression alone raises attack-success rate, and the point of
	the study is to quantify that and test recovery. Treat any given cell as an
	experimental subject, not as a deployable assistant, and evaluate it yourself
	before drawing conclusions from it.

	## Licence

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