Instructions to use fatih-can/Kumru-2B-Abliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fatih-can/Kumru-2B-Abliterated with Transformers:

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

pipe = pipeline("text-generation", model="fatih-can/Kumru-2B-Abliterated")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("fatih-can/Kumru-2B-Abliterated")
model = AutoModelForCausalLM.from_pretrained("fatih-can/Kumru-2B-Abliterated", 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 fatih-can/Kumru-2B-Abliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "fatih-can/Kumru-2B-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": "fatih-can/Kumru-2B-Abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/fatih-can/Kumru-2B-Abliterated

SGLang

How to use fatih-can/Kumru-2B-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 "fatih-can/Kumru-2B-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": "fatih-can/Kumru-2B-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 "fatih-can/Kumru-2B-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": "fatih-can/Kumru-2B-Abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use fatih-can/Kumru-2B-Abliterated with Docker Model Runner:
```
docker model run hf.co/fatih-can/Kumru-2B-Abliterated
```

Kumru-2B-Abliterated

A decensored (abliterated) variant of Kumru-2B, a 2B-parameter Turkish instruction-tuned language model. The refusal behavior has been removed from the weights via directional ablation, while the model stays very close to its original behavior on harmless inputs.

Benchmark

On a set of 100 Turkish eval set:

	Refusals
Kumru-2B (base)	50/100
Kumru-2B-Abliterated	98/100 answered

KL divergence vs. the original model on a harmless evaluation set: 0.0148

How to run

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "fatih-can/Kumru-2B-Abliterated"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name, torch_dtype="auto", device_map="auto"
)

def generate_response(query):
    messages = [
        {'role': 'system', 'content': 'Adın Kumru. Türkçe için sıfırdan eğitilmiş bir dil modelisin.'},
        {'role': 'user', 'content': query}
    ]
    model_inputs = tokenizer.apply_chat_template(
        messages, return_tensors='pt', add_generation_prompt=True
    ).to(model.device)
    model_outputs = model.generate(
        model_inputs, max_new_tokens=512, do_sample=True,
        top_p=0.9, temperature=0.7, repetition_penalty=1.1
    )
    output_tokens = model_outputs[0].cpu().detach().numpy().tolist()
    generated_tokens = output_tokens[model_inputs[0].shape[0]:]
    return tokenizer.decode(generated_tokens, skip_special_tokens=True)

print(generate_response("Merhaba, bana kendinden bahseder misin?"))

Notes

Architecture: MistralForCausalLM (hidden 3072, 18 layers), native context 8192 tokens, drop-in replaceable for the base model.
Weights are merged (full safetensors), ~4.75 GB.
Generation parameters and the Turkish system prompt follow the base model's recommended settings.

Usage warnings

Sensitive or controversial outputs: safety filtering has been significantly reduced; the model may produce sensitive, controversial, or inappropriate content. Review outputs carefully.
Not suitable for all audiences / public or commercial production use without additional safeguards.
Legal and ethical responsibility: ensure your usage complies with applicable laws and ethical standards; you are solely responsible for any consequences.
This is a decensored research artifact and has not undergone safety optimization.

Downloads last month: 130

Safetensors

Model size

2B params

Tensor type

BF16

Model tree for fatih-can/Kumru-2B-Abliterated

Base model

vngrs-ai/Kumru-2B

Finetuned

(10)

this model