Instructions to use ibrahimkettaneh/QwQ-32B-Preview-abliterated-4.5bpw-h8-exl2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ibrahimkettaneh/QwQ-32B-Preview-abliterated-4.5bpw-h8-exl2 with Transformers:

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

pipe = pipeline("text-generation", model="ibrahimkettaneh/QwQ-32B-Preview-abliterated-4.5bpw-h8-exl2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("ibrahimkettaneh/QwQ-32B-Preview-abliterated-4.5bpw-h8-exl2")
model = AutoModelForMultimodalLM.from_pretrained("ibrahimkettaneh/QwQ-32B-Preview-abliterated-4.5bpw-h8-exl2")
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 ibrahimkettaneh/QwQ-32B-Preview-abliterated-4.5bpw-h8-exl2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ibrahimkettaneh/QwQ-32B-Preview-abliterated-4.5bpw-h8-exl2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ibrahimkettaneh/QwQ-32B-Preview-abliterated-4.5bpw-h8-exl2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ibrahimkettaneh/QwQ-32B-Preview-abliterated-4.5bpw-h8-exl2

SGLang

How to use ibrahimkettaneh/QwQ-32B-Preview-abliterated-4.5bpw-h8-exl2 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 "ibrahimkettaneh/QwQ-32B-Preview-abliterated-4.5bpw-h8-exl2" \
    --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": "ibrahimkettaneh/QwQ-32B-Preview-abliterated-4.5bpw-h8-exl2",
		"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 "ibrahimkettaneh/QwQ-32B-Preview-abliterated-4.5bpw-h8-exl2" \
        --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": "ibrahimkettaneh/QwQ-32B-Preview-abliterated-4.5bpw-h8-exl2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ibrahimkettaneh/QwQ-32B-Preview-abliterated-4.5bpw-h8-exl2 with Docker Model Runner:
```
docker model run hf.co/ibrahimkettaneh/QwQ-32B-Preview-abliterated-4.5bpw-h8-exl2
```

QwQ-32B-Preview-abliterated-4.5bpw-h8-exl2 / README.md

ibrahimkettaneh

Update README.md

eb3dc83 verified over 1 year ago

preview code

raw

history blame

1.36 kB

	---
	license: apache-2.0
	license_link: https://huggingface.co/huihui-ai/QwQ-32B-Preview-abliterated/blob/main/LICENSE
	language:
	- en
	pipeline_tag: text-generation
	base_model:
	- huihui-ai/QwQ-32B-Preview-abliterated
	tags:
	- chat
	- abliterated
	- uncensored
	library_name: transformers
	---

	# _I kindly ask that you [follow me](https://huggingface.co/ibrahimkettaneh) for more quantizations, please, because it lets me know you are interested in more work like this_ 😁

	![image/png](https://cdn-uploads.huggingface.co/production/uploads/6635be30b0a5f86a2af4b6a0/trS4yRInFY1LF_25EiH6c.png)

	# Credits goes to all those who have contributed to the community, in this case, specifically: [huihui-ai](https://huggingface.co/huihui-ai)/[QwQ-32B-Preview-abliterated](https://huggingface.co/huihui-ai/QwQ-32B-Preview-abliterated)


	This is an uncensored version of [Qwen/QwQ-32B-Preview](https://huggingface.co/Qwen/QwQ-32B-Preview) created with abliteration (see [remove-refusals-with-transformers](https://github.com/Sumandora/remove-refusals-with-transformers) to know more about it).
	This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.

	## ollama

	You can use [huihui_ai/qwq-abliterated](https://ollama.com/huihui_ai/qwq-abliterated) directly,
	```
	ollama run huihui_ai/qwq-abliterated
	```