Instructions to use Goekdeniz-Guelmez/Josiefied-Qwen3-8B-abliterated-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Goekdeniz-Guelmez/Josiefied-Qwen3-8B-abliterated-v1 with Transformers:

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

pipe = pipeline("text-generation", model="Goekdeniz-Guelmez/Josiefied-Qwen3-8B-abliterated-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Goekdeniz-Guelmez/Josiefied-Qwen3-8B-abliterated-v1")
model = AutoModelForCausalLM.from_pretrained("Goekdeniz-Guelmez/Josiefied-Qwen3-8B-abliterated-v1")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Goekdeniz-Guelmez/Josiefied-Qwen3-8B-abliterated-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Goekdeniz-Guelmez/Josiefied-Qwen3-8B-abliterated-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Goekdeniz-Guelmez/Josiefied-Qwen3-8B-abliterated-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Goekdeniz-Guelmez/Josiefied-Qwen3-8B-abliterated-v1

SGLang

How to use Goekdeniz-Guelmez/Josiefied-Qwen3-8B-abliterated-v1 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 "Goekdeniz-Guelmez/Josiefied-Qwen3-8B-abliterated-v1" \
    --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": "Goekdeniz-Guelmez/Josiefied-Qwen3-8B-abliterated-v1",
		"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 "Goekdeniz-Guelmez/Josiefied-Qwen3-8B-abliterated-v1" \
        --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": "Goekdeniz-Guelmez/Josiefied-Qwen3-8B-abliterated-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Goekdeniz-Guelmez/Josiefied-Qwen3-8B-abliterated-v1 with Docker Model Runner:
```
docker model run hf.co/Goekdeniz-Guelmez/Josiefied-Qwen3-8B-abliterated-v1
```

You need to keep working on this or atleast post how you did it.

#10

by drmcbride - opened May 13, 2025

Discussion

drmcbride

May 13, 2025

This model is extremely good and actually has a value that makes me want to use a open model.

Goekdeniz-Guelmez

Owner May 13, 2025

Hey, really appreciate the kind words!
Honestly, this was just a quick side project I hacked together in like an hour, I didnt expect it to get this much attention at all. I’m genuinely surprised (in a good way) that people are finding real value in it.

Since people really love the Josiefied Qwen 2.5 family, I figured I’d continue the idea with the new Qwen3 family, mostly still just for fun. But with this kind of feedback, I’ll at least clean things up and drop some notes on how I put it together. Maybe even a paper along with code if time allows.

Thanks again!! It really means a lot.

drmcbride

May 13, 2025

your model scored 9/10 on ugi leaderboard for willingness (only a handful of models get that) if I were you I would try to get a 10 on there since it has not been done yet and you're already very close.

drmcbride

May 13, 2025

it would bring a signifigant amount of attention to your work here trust me.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment