Instructions to use TeeZee/QwQ-32B-abliterated-bpw4.0-h8-exl2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TeeZee/QwQ-32B-abliterated-bpw4.0-h8-exl2 with Transformers:

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

pipe = pipeline("text-generation", model="TeeZee/QwQ-32B-abliterated-bpw4.0-h8-exl2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TeeZee/QwQ-32B-abliterated-bpw4.0-h8-exl2")
model = AutoModelForCausalLM.from_pretrained("TeeZee/QwQ-32B-abliterated-bpw4.0-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

vLLM

How to use TeeZee/QwQ-32B-abliterated-bpw4.0-h8-exl2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TeeZee/QwQ-32B-abliterated-bpw4.0-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": "TeeZee/QwQ-32B-abliterated-bpw4.0-h8-exl2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TeeZee/QwQ-32B-abliterated-bpw4.0-h8-exl2

SGLang

How to use TeeZee/QwQ-32B-abliterated-bpw4.0-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 "TeeZee/QwQ-32B-abliterated-bpw4.0-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": "TeeZee/QwQ-32B-abliterated-bpw4.0-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 "TeeZee/QwQ-32B-abliterated-bpw4.0-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": "TeeZee/QwQ-32B-abliterated-bpw4.0-h8-exl2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use TeeZee/QwQ-32B-abliterated-bpw4.0-h8-exl2 with Docker Model Runner:
```
docker model run hf.co/TeeZee/QwQ-32B-abliterated-bpw4.0-h8-exl2
```

huihui-ai/QwQ-32B-abliterated

Exl2 quant, Fixed chat template to generate first tag using tabbyAPI and others servers

This is an uncensored version of Qwen/QwQ-32B created with abliteration (see 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.

Use with ollama

You can use huihui_ai/qwq-abliterated directly

ollama run huihui_ai/qwq-abliterated

All versions of ollama from Q2_K to fp16 are supported.

Donation

If you like it, please click 'like' and follow us for more updates.
You can follow x.com/support_huihui to get the latest model information from huihui.ai.

Your donation helps us continue our further development and improvement, a cup of coffee can do it.

bitcoin:

  bc1qqnkhuchxw0zqjh2ku3lu4hq45hc6gy84uk70ge

Downloads last month: 1

Model tree for TeeZee/QwQ-32B-abliterated-bpw4.0-h8-exl2

Base model

Qwen/Qwen2.5-32B

Finetuned

Qwen/QwQ-32B

Quantized

(162)

this model