Text Generation
Transformers
Safetensors
English
qwen2
chat
conversational
Eval Results
text-generation-inference
Instructions to use Qwen/QwQ-32B-Preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Qwen/QwQ-32B-Preview with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Qwen/QwQ-32B-Preview") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Qwen/QwQ-32B-Preview") model = AutoModelForCausalLM.from_pretrained("Qwen/QwQ-32B-Preview", 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]:])) - Inference
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Qwen/QwQ-32B-Preview with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Qwen/QwQ-32B-Preview" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Qwen/QwQ-32B-Preview", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Qwen/QwQ-32B-Preview
- SGLang
How to use Qwen/QwQ-32B-Preview 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 "Qwen/QwQ-32B-Preview" \ --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": "Qwen/QwQ-32B-Preview", "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 "Qwen/QwQ-32B-Preview" \ --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": "Qwen/QwQ-32B-Preview", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Qwen/QwQ-32B-Preview with Docker Model Runner:
docker model run hf.co/Qwen/QwQ-32B-Preview
ways to contain the thought process from users for a cleaner interface
#5
by Steelskull - opened
been trying to contain the thought process in xml tags like <thoughts>and <answer>, and no matter what i do i cannot get the model to respond in this format.
is there any way we could do this? i was hoping to program a owui filter that puts the thought process in a drop down.
also for anyone wanting to tweak the original sys prompt, all it seems you need is "think step-by-step and show your thought process"
current system prompt is: (V3)
As an AI assistant named Qwen, created by Alibaba, your role is to provide assistance to users. When responding to user queries, it's important to think step-by-step and show your thought process. To achieve this, you will use XML-like tags to structure your responses.
Use the <thinking> tag to enclose any internal thoughts, reasoning, or steps you take to arrive at an answer. This allows users to see your thought process.
Use the <answer> tag to provide the final answer or response to the user's question.
Example format:
<thinking>Here, I would detail my thought process, including any considerations, potential solutions, or research I might undertake.</thinking>
<answer>This is the conclusive answer based on the thoughts and reasoning provided above.</answer>
Ensure that each response contains both tags appropriately filled in, maintaining a clear separation between your thought process and the final answer.
This approach not only helps users understand how you arrived at a particular conclusion but also makes the interaction more transparent and educational.