Instructions to use kmseong/llama2_7b-chat-WaRP_new_basis_lr5e-5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kmseong/llama2_7b-chat-WaRP_new_basis_lr5e-5 with Transformers:

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

pipe = pipeline("text-generation", model="kmseong/llama2_7b-chat-WaRP_new_basis_lr5e-5")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kmseong/llama2_7b-chat-WaRP_new_basis_lr5e-5")
model = AutoModelForCausalLM.from_pretrained("kmseong/llama2_7b-chat-WaRP_new_basis_lr5e-5")
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 kmseong/llama2_7b-chat-WaRP_new_basis_lr5e-5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kmseong/llama2_7b-chat-WaRP_new_basis_lr5e-5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kmseong/llama2_7b-chat-WaRP_new_basis_lr5e-5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kmseong/llama2_7b-chat-WaRP_new_basis_lr5e-5

SGLang

How to use kmseong/llama2_7b-chat-WaRP_new_basis_lr5e-5 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 "kmseong/llama2_7b-chat-WaRP_new_basis_lr5e-5" \
    --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": "kmseong/llama2_7b-chat-WaRP_new_basis_lr5e-5",
		"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 "kmseong/llama2_7b-chat-WaRP_new_basis_lr5e-5" \
        --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": "kmseong/llama2_7b-chat-WaRP_new_basis_lr5e-5",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kmseong/llama2_7b-chat-WaRP_new_basis_lr5e-5 with Docker Model Runner:
```
docker model run hf.co/kmseong/llama2_7b-chat-WaRP_new_basis_lr5e-5
```

WaRP-Safety-Llama3_8B_Instruct

Fine-tuned Llama 3.1 8B Instruct model for safety alignment using Weight space Rotation Process (WaRP).

Model Details

Base Model: meta-llama/Llama-3.1-8B-Instruct
Training Method: Safety-First WaRP (3-Phase pipeline)
Training Date: 2026-04-29

Training Procedure

Phase 1: Basis Construction

Collected activations from FFN layers using safety data
Computed SVD to obtain orthonormal basis vectors
Identified 419 important neurons in layer 31

Phase 2: Importance Scoring

Calculated importance scores using gradient-based methods
Generated masks for important directions
Used teacher forcing on safety responses

Phase 3: Incremental Learning

Fine-tuned on utility task (GSM8K) with gradient masking
Protected important directions to maintain safety
Improved utility while preserving safety mechanisms

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "kmseong/WaRP-Safety-Llama3_8B_Instruct"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto")

# Generate text
inputs = tokenizer("What is machine learning?", return_tensors="pt")
outputs = model.generate(**inputs, max_length=100)
print(tokenizer.decode(outputs[0]))

Safety Features

✅ Protected safety mechanisms through gradient masking
✅ Maintained refusal capability for harmful requests
✅ Improved utility on reasoning tasks
✅ Balanced safety-utility tradeoff

Datasets

Safety Data: LibrAI/do-not-answer
Utility Data: openai/gsm8k

Citation

@article{warp-safety,
  title={Safety-First WaRP: Weight space Rotation Process for LLM Safety Alignment},
  author={Min-Seong Kim},
  year={2026}
}

License

This model is built on Llama 3.1 8B Instruct and follows the same license.

Disclaimer

This model is fine-tuned for improved safety. Users should evaluate model outputs for their specific use cases and apply additional safety measures as needed.

Downloads last month: 443

Safetensors

Model size

7B params

Tensor type

BF16