Instructions to use zai-org/SWE-Dev-32B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zai-org/SWE-Dev-32B with Transformers:

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

pipe = pipeline("text-generation", model="zai-org/SWE-Dev-32B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zai-org/SWE-Dev-32B")
model = AutoModelForCausalLM.from_pretrained("zai-org/SWE-Dev-32B", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use zai-org/SWE-Dev-32B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zai-org/SWE-Dev-32B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zai-org/SWE-Dev-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zai-org/SWE-Dev-32B

SGLang

How to use zai-org/SWE-Dev-32B 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 "zai-org/SWE-Dev-32B" \
    --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": "zai-org/SWE-Dev-32B",
		"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 "zai-org/SWE-Dev-32B" \
        --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": "zai-org/SWE-Dev-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use zai-org/SWE-Dev-32B with Docker Model Runner:
```
docker model run hf.co/zai-org/SWE-Dev-32B
```

hrw commited on Apr 15, 2025

Commit

39b05d9

verified ·

1 Parent(s): 006e055

Update README.md

Browse files

Files changed (1) hide show

README.md +18 -3

README.md CHANGED Viewed

@@ -1,3 +1,18 @@
----
-license: mit
----

+---
+license: mit
+---
+**SWE-Dev-32B is trained from [Qwen2.5-Coder-32B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct)**
+🚀 SWE-Dev, a groundbreaking open-source Software Engineering Agent (SWE Agent)!
+📚 We have built a high-quality dataset and significantly improved the model’s performance on SWE tasks through rejection sampling. We also explored the feasibility of various offline algorithms on SWE through extensive experiments.
+🔧 Using only open-source frameworks and models, SWE-Dev-7B and 32B achieved solve rates of 23.4% and 36.6% on SWE-bench-Verified, respectively, even approaching the performance of closed-source models like GPT-4o.
+🛠 No need for complex prompt engineering or expensive multi-round evaluations—performance breakthroughs can be achieved with simplified inference scaling! We discovered that increasing interaction rounds significantly boosts model performance. For instance, DeepSeek-V3’s solve rate improved from 37.4% at 30 rounds to 41.2% at 75 rounds. Context extension also proved highly effective for short-text-trained models!
+💡 We further explored the scaling laws between data size, interaction rounds, and model performance, demonstrating that smaller, high-quality datasets are sufficient to support top-tier performance.
+Notion Link: https://ubecwang.notion.site/1bc32cf963e080b2a01df2895f66021f?v=1bc32cf963e0810ca07e000c86c4c1e1
+GitHub Link: https://github.com/THUDM/SWE-Dev
+Hugging Face Link: https://huggingface.co/SWE-Dev