Instructions to use Qwen/Qwen3-1.7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Qwen/Qwen3-1.7B with Transformers:

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

pipe = pipeline("text-generation", model="Qwen/Qwen3-1.7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-1.7B")
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-1.7B")
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/Qwen3-1.7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Qwen/Qwen3-1.7B"
# 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/Qwen3-1.7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Qwen/Qwen3-1.7B

SGLang

How to use Qwen/Qwen3-1.7B 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/Qwen3-1.7B" \
    --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/Qwen3-1.7B",
		"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/Qwen3-1.7B" \
        --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/Qwen3-1.7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Qwen/Qwen3-1.7B with Docker Model Runner:
```
docker model run hf.co/Qwen/Qwen3-1.7B
```

Fix chat template in case of multiple assistant messages and no thinking

by VityaVitalich - opened May 29, 2025

base: refs/heads/main

←

from: refs/pr/9

Discussion Files changed

-1

VityaVitalich

May 29, 2025

Previously when messages contained multiple assistant messages, applying tokenizer template with enable_thinking=False would result in applying no thinking tokens to the first assistant message, but applying them to the second assistant message.

For example,

messages = [
    {'role': 'user', 'content': 'i am user 1'},
    {'role': 'assistant', 'content': 'i am assistant 1'},
    {'role': 'user', 'content': 'i am user 2'},
    {'role': 'assistant', 'content': 'i am assistant 2'},
]

input_ids = tokenizer.apply_chat_template(
    messages,
    tokenize=True,
    add_generation_prompt=False,
    truncate=True,
    return_tensors='pt',
    enable_thinking=False

).squeeze(0)

Fix chat template in case of multiple assistant messages and no thinking313ac59d

sdpkjc

Jun 6, 2025

I ran into the same issue as well—after manually applying the chat_template from this PR, everything worked correctly. Hope this gets merged soon!

VityaVitalich

Jun 6, 2025

Happy this was useful! In case anyone needs the model that could be easily downloaded with this issue resolved.

https://huggingface.co/VityaVitalich/Qwen3-1.7B

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

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment