Instructions to use Qwen/Qwen2.5-7B-Instruct-1M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Qwen/Qwen2.5-7B-Instruct-1M with Transformers:

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

pipe = pipeline("text-generation", model="Qwen/Qwen2.5-7B-Instruct-1M")
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-1M")
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-7B-Instruct-1M", 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/Qwen2.5-7B-Instruct-1M 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-1M"
# 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-1M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Qwen/Qwen2.5-7B-Instruct-1M

SGLang

How to use Qwen/Qwen2.5-7B-Instruct-1M 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-1M" \
    --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-1M",
		"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-1M" \
        --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-1M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Qwen/Qwen2.5-7B-Instruct-1M with Docker Model Runner:
```
docker model run hf.co/Qwen/Qwen2.5-7B-Instruct-1M
```

hzhwcmhf commited on Jan 29, 2025

Commit

e28526f

verified ·

1 Parent(s): a6cfb9e

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -5

README.md CHANGED Viewed

@@ -15,8 +15,6 @@ library_name: transformers
     <img alt="Chat" src="https://img.shields.io/badge/%F0%9F%92%9C%EF%B8%8F%20Qwen%20Chat%20-536af5" style="display: inline-block; vertical-align: middle;"/>
 </a>
-This repository contains the model of the paper [Qwen2.5-1M Technical Report](https://huggingface.co/papers/2501.15383).
 ## Introduction
 Qwen2.5-1M is the long-context version of the Qwen2.5 series models, supporting a context length of up to 1M tokens. Compared to the Qwen2.5 128K version, Qwen2.5-1M demonstrates significantly improved performance in handling long-context tasks while maintaining its capability in short tasks.
@@ -33,8 +31,7 @@ The model has the following features:
   - We recommend deploying with our custom vLLM, which introduces sparse attention and length extrapolation methods to ensure efficiency and accuracy for long-context tasks. For specific guidance, refer to [this section](#processing-ultra-long-texts).
   - You can also use the previous framework that supports Qwen2.5 for inference, but accuracy degradation may occur for sequences exceeding 262,144 tokens.
-For more details, please refer to our [blog](https://qwenlm.github.io/blog/qwen2.5-1m/), [GitHub](https://github.com/QwenLM/Qwen2.5), and [Documentation](https://qwen.readthedocs.io/en/latest/).
 ## Requirements
 The code of Qwen2.5 has been in the latest Hugging face `transformers` and we advise you to use the latest version of `transformers`.
@@ -214,7 +211,7 @@ You can also refer to our [Documentation](https://qwen.readthedocs.io/en/latest/
 ## Evaluation & Performance
-Detailed evaluation results are reported in this [📑 blog](https://qwenlm.github.io/blog/qwen2.5-1m/) and our [technical report](https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen2.5-1M/Qwen2_5_1M_Technical_Report.pdf).
 ## Citation

     <img alt="Chat" src="https://img.shields.io/badge/%F0%9F%92%9C%EF%B8%8F%20Qwen%20Chat%20-536af5" style="display: inline-block; vertical-align: middle;"/>
 </a>
 ## Introduction
 Qwen2.5-1M is the long-context version of the Qwen2.5 series models, supporting a context length of up to 1M tokens. Compared to the Qwen2.5 128K version, Qwen2.5-1M demonstrates significantly improved performance in handling long-context tasks while maintaining its capability in short tasks.
   - We recommend deploying with our custom vLLM, which introduces sparse attention and length extrapolation methods to ensure efficiency and accuracy for long-context tasks. For specific guidance, refer to [this section](#processing-ultra-long-texts).
   - You can also use the previous framework that supports Qwen2.5 for inference, but accuracy degradation may occur for sequences exceeding 262,144 tokens.
+For more details, please refer to our [blog](https://qwenlm.github.io/blog/qwen2.5-1m/), [GitHub](https://github.com/QwenLM/Qwen2.5), [Technical Report](https://huggingface.co/papers/2501.15383), and [Documentation](https://qwen.readthedocs.io/en/latest/).
 ## Requirements
 The code of Qwen2.5 has been in the latest Hugging face `transformers` and we advise you to use the latest version of `transformers`.
 ## Evaluation & Performance
+Detailed evaluation results are reported in this [📑 blog](https://qwenlm.github.io/blog/qwen2.5-1m/) and our [technical report](https://arxiv.org/abs/2501.15383).
 ## Citation