Qwen
/

Qwen2.5-7B-Instruct

Text Generation

text-generation-inference

Model card Files Files and versions

Instructions to use Qwen/Qwen2.5-7B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Qwen/Qwen2.5-7B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="Qwen/Qwen2.5-7B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-7B-Instruct")
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-7B-Instruct")
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
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Qwen/Qwen2.5-7B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Qwen/Qwen2.5-7B-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/Qwen2.5-7B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Qwen/Qwen2.5-7B-Instruct

How to use Qwen/Qwen2.5-7B-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/Qwen2.5-7B-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/Qwen2.5-7B-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/Qwen2.5-7B-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/Qwen2.5-7B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Qwen/Qwen2.5-7B-Instruct with Docker Model Runner:
```
docker model run hf.co/Qwen/Qwen2.5-7B-Instruct
```

Resources

View closed (4)

Multilingual powerhouse — testing for mobile deployment

#56 opened 15 days ago by

OMS Score -- OMS 83.1 (A) -- Qwen2.5 7B | 5-dimension independent scoring

#55 opened 26 days ago by

OMS Score -- OMS 83.1 (A) -- Qwen2.5 7B | 5-dimension independent scoring

#54 opened 26 days ago by

OMS Score -- OMS 83.1 (A) -- Qwen2.5 7B | 5-dimension independent scoring

#53 opened 27 days ago by

OMS Score -- OMS 83.1 (A) -- Qwen2.5 7B | 5-dimension independent scoring

#52 opened 27 days ago by

OMS Score -- OMS 83.1 (A) -- Qwen2.5 7B | 5-dimension independent scoring

#51 opened 27 days ago by

OMS Score -- OMS 83.1 (A) -- Qwen2.5 7B | 5-dimension independent scoring

#50 opened 27 days ago by

OMS Score -- OMS 83.1 (A) -- Qwen2.5 7B | 5-dimension independent scoring

#49 opened 27 days ago by

OMS Score -- OMS 83.1 (A) -- Qwen2.5 7B | 5-dimension independent scoring

#48 opened 27 days ago by

OMS Score -- OMS 83.1 (A) -- Qwen2.5 7B | 5-dimension independent scoring

#47 opened 27 days ago by

OMS Score -- OMS 83.1 (A) -- Qwen2.5 7B | 5-dimension independent scoring

#46 opened 27 days ago by

OMS Score -- OMS 83.1 (A) -- Qwen2.5 7B | 5-dimension independent scoring

#45 opened 27 days ago by

OMS Score -- OMS 83.1 (A) -- Qwen2.5 7B | 5-dimension independent scoring

#44 opened 27 days ago by

OMS Score -- OMS 83.1 (A) -- Qwen2.5 7B | 5-dimension independent scoring

#43 opened 27 days ago by

OMS Score -- OMS 83.1 (A) -- Qwen2.5 7B | 5-dimension independent scoring

#42 opened 27 days ago by

OMS Score -- OMS 83.1 (A) -- Qwen2.5 7B | 5-dimension independent scoring

#41 opened 27 days ago by

OMS Score -- OMS 83.1 (A) -- Qwen2.5 7B | 5-dimension independent scoring

#40 opened 27 days ago by

OMS Score -- OMS 83.1 (A) -- Qwen2.5 7B | 5-dimension independent scoring

#39 opened 27 days ago by

OMS Score -- OMS 83.1 (A) -- Qwen2.5 7B | 5-dimension independent scoring

#38 opened 27 days ago by

OMS Score -- OMS 83.1 (A) -- Qwen2.5 7B | 5-dimension independent scoring

#37 opened 27 days ago by

OMS Score -- OMS 83.1 (A) -- Qwen2.5 7B | 5-dimension independent scoring

#36 opened 27 days ago by

New architecture: TemporalMesh Transformer — dynamic kNN graph attention + per-token exit routing, 29.4 PPL at 48% compute

#35 opened about 1 month ago by

Add LEXam evaluation results

#34 opened about 1 month ago by

mea

#33 opened 2 months ago by

If you are getting getting undefined symbol: _ZN3c1013MessageLoggerC1EPKciib when following instructions or other errors on vLLM

#32 opened 3 months ago by

Qwen2.5-7b-Instruct

#31 opened 3 months ago by

Qwen 4 7b

#30 opened 4 months ago by

Technical question: Lineage of Qwen/Qwen2-7B-Instruct

#28 opened 4 months ago by

How good is Qwen/Qwen-2.5-7B-Instruct at tool calling? Any open-source models better at it?

#27 opened 6 months ago by

Safety Audit: GAE Score 25.16% (FAIL)

#26 opened 7 months ago by

quen

#25 opened 8 months ago by

demo

#24 opened 8 months ago by

Minimum Hardware required for finetuning using images ?

#23 opened 9 months ago by

Performance Problem

#22 opened 12 months ago by

Update README.md

#21 opened about 1 year ago by

add AIBOM

#20 opened about 1 year ago by

Failed to download the model from the hub

#19 opened about 1 year ago by

ValueError: Unrecognized model in Qwen/Qwen2.5-7B-Instruct. Should have a `model_type` key in its config.json,

#18 opened about 1 year ago by

Improve language tag

#17 opened about 1 year ago by

为何Qwen从1.5开始基本都是Instruction模型

#16 opened over 1 year ago by

How do I make the model output JSON?

#14 opened over 1 year ago by

Q8_0-GGUF

#13 opened over 1 year ago by

Wrong chat template?

#12 opened over 1 year ago by

Evaluating Qwen2.5 Performance Using the LLaVA-NeXT Framework: Impressive Results !

#11 opened over 1 year ago by

Independent evaluation results

#9 opened almost 2 years ago by

能做文本的embedding吗？

#7 opened almost 2 years ago by

Эротика

#6 opened almost 2 years ago by

Adding Evaluation Results

#4 opened almost 2 years ago by

leaderboard-pr-bot

Less knowledge, maybe better reasoning versus Qwen2

#3 opened almost 2 years ago by

Scorecard on popular benchmarks

#2 opened almost 2 years ago by