Qwen
/

Qwen2.5-32B-Instruct

Text Generation

text-generation-inference

Model card Files Files and versions

Instructions to use Qwen/Qwen2.5-32B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Qwen/Qwen2.5-32B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="Qwen/Qwen2.5-32B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-32B-Instruct")
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-32B-Instruct", 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

How to use Qwen/Qwen2.5-32B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Qwen/Qwen2.5-32B-Instruct"
# 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/Qwen2.5-32B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Qwen/Qwen2.5-32B-Instruct

How to use Qwen/Qwen2.5-32B-Instruct 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/Qwen2.5-32B-Instruct" \
    --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/Qwen2.5-32B-Instruct",
		"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/Qwen2.5-32B-Instruct" \
        --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/Qwen2.5-32B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Qwen/Qwen2.5-32B-Instruct with Docker Model Runner:
```
docker model run hf.co/Qwen/Qwen2.5-32B-Instruct
```

Resources

View closed (4)

Listed on OpenModelMap

#34 opened about 1 month ago by

OMS Score -- OMS 82.8 (A) -- Qwen2.5 32B | 5-dimension independent scoring

#33 opened about 2 months ago by

OMS Score -- OMS 82.8 (A) -- Qwen2.5 32B | 5-dimension independent scoring

#32 opened about 2 months ago by

OMS Score -- OMS 82.8 (A) -- Qwen2.5 32B | 5-dimension independent scoring

#31 opened about 2 months ago by

OMS Score -- OMS 82.8 (A) -- Qwen2.5 32B | 5-dimension independent scoring

#30 opened about 2 months ago by

OMS Score -- OMS 82.8 (A) -- Qwen2.5 32B | 5-dimension independent scoring

#29 opened about 2 months ago by

OMS Score -- OMS 82.8 (A) -- Qwen2.5 32B | 5-dimension independent scoring

#28 opened about 2 months ago by

OMS Score -- OMS 82.8 (A) -- Qwen2.5 32B | 5-dimension independent scoring

#27 opened about 2 months ago by

OMS Score -- OMS 82.8 (A) -- Qwen2.5 32B | 5-dimension independent scoring

#26 opened about 2 months ago by

OMS Score -- OMS 82.8 (A) -- Qwen2.5 32B | 5-dimension independent scoring

#25 opened about 2 months ago by

OMS Score -- OMS 82.8 (A) -- Qwen2.5 32B | 5-dimension independent scoring

#24 opened about 2 months ago by

OMS Score -- OMS 82.8 (A) -- Qwen2.5 32B | 5-dimension independent scoring

#23 opened about 2 months ago by

OMS Score -- OMS 82.8 (A) -- Qwen2.5 32B | 5-dimension independent scoring

#22 opened about 2 months ago by

OMS Score -- OMS 82.8 (A) -- Qwen2.5 32B | 5-dimension independent scoring

#21 opened about 2 months ago by

OMS Score -- OMS 82.8 (A) -- Qwen2.5 32B | 5-dimension independent scoring

#20 opened about 2 months ago by

OMS Score -- OMS 82.8 (A) -- Qwen2.5 32B | 5-dimension independent scoring

#19 opened about 2 months ago by

OMS Score -- OMS 82.8 (A) -- Qwen2.5 32B | 5-dimension independent scoring

#18 opened about 2 months ago by

OMS Score -- OMS 82.8 (A) -- Qwen2.5 32B | 5-dimension independent scoring

#17 opened about 2 months ago by

OMS Score -- OMS 82.8 (A) -- Qwen2.5 32B | 5-dimension independent scoring

#16 opened about 2 months ago by

OMS Score -- OMS 82.8 (A) -- Qwen2.5 32B | 5-dimension independent scoring

#15 opened about 2 months ago by

TemporalMesh Transformer: 29.4 PPL at 48% compute — beats Mamba, new open-source architecture

#14 opened about 2 months ago by

Qwen/Qwen2.5-32B-Instruct

#12 opened 9 months ago by

Update README.md

#11 opened about 1 year ago by

Improve language tag

#9 opened over 1 year ago by

Контекстное окно

#8 opened over 1 year ago by

Problem. GPTQ Quantization to 4bit

#7 opened almost 2 years ago by

Adding Evaluation Results

#6 opened almost 2 years ago by

Clarifications on how to use YaRN

#5 opened almost 2 years ago by

Independent MMLU-Pro evaluation

#4 opened almost 2 years ago by