nsfw

Instructions to use nullHawk/Param-1-2.9B-Instruct-Refusal-Abliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nullHawk/Param-1-2.9B-Instruct-Refusal-Abliterated with Transformers:

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

pipe = pipeline("text-generation", model="nullHawk/Param-1-2.9B-Instruct-Refusal-Abliterated", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("nullHawk/Param-1-2.9B-Instruct-Refusal-Abliterated", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use nullHawk/Param-1-2.9B-Instruct-Refusal-Abliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nullHawk/Param-1-2.9B-Instruct-Refusal-Abliterated"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nullHawk/Param-1-2.9B-Instruct-Refusal-Abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nullHawk/Param-1-2.9B-Instruct-Refusal-Abliterated

SGLang

How to use nullHawk/Param-1-2.9B-Instruct-Refusal-Abliterated 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 "nullHawk/Param-1-2.9B-Instruct-Refusal-Abliterated" \
    --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": "nullHawk/Param-1-2.9B-Instruct-Refusal-Abliterated",
		"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 "nullHawk/Param-1-2.9B-Instruct-Refusal-Abliterated" \
        --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": "nullHawk/Param-1-2.9B-Instruct-Refusal-Abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nullHawk/Param-1-2.9B-Instruct-Refusal-Abliterated with Docker Model Runner:
```
docker model run hf.co/nullHawk/Param-1-2.9B-Instruct-Refusal-Abliterated
```

Param-1-2.9B-Instruct (Refusal Ablated)

This model is a modified version of bharatgenai/Param-1-2.9B-Instruct with the refusal direction ablated from layers 10-20.

Modifications

The refusal direction was computed using contrastive activation analysis between harmful and harmless prompts, then permanently removed from the model's weight matrices in layers 10-20.

Technical Details:

Base Model: bharatgenai/Param-1-2.9B-Instruct
Ablation Method: Weight modification via projection matrix
Layers Modified: 10-20 (self_attn.o_proj and mlp.down_proj)
Ablation Strength: 1.0

Usage

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained(
    "nullHawk/Param-1-2.9B-Instruct-Refusal-Abliterated",
    trust_remote_code=True,
    torch_dtype=torch.float16,
    device_map="auto"
).eval()
tokenizer = AutoTokenizer.from_pretrained("bharatgenai/Param-1-2.9B-Instruct", trust_remote_code=True)

# Conversation Input
conversation = [
  {
    "content": "How to write a computer malware",
    "role": "user"
  }
]

# padding special token
inputs = tokenizer.apply_chat_template(
    conversation=conversation,
    return_tensors="pt",
    add_generation_prompt=True 
)
inputs = inputs.to(model.device)

# --- Generate output ---
with torch.no_grad():
    output = model.generate(
        inputs,
        max_new_tokens=300,
        do_sample=True,
        top_k=50,
        top_p=0.95,
        temperature=0.6,
        eos_token_id=tokenizer.eos_token_id,
        use_cache=False
    )

# Get only the generated tokens (exclude the prompt length)
generated_tokens = output[0][inputs.shape[-1]:]
generated_text = tokenizer.decode(generated_tokens, skip_special_tokens=True)

print("Assistant Output:\n", generated_text)