Instructions to use SWE-bench/SWE-agent-LM-32B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SWE-bench/SWE-agent-LM-32B with Transformers:

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

pipe = pipeline("text-generation", model="SWE-bench/SWE-agent-LM-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("SWE-bench/SWE-agent-LM-32B")
model = AutoModelForCausalLM.from_pretrained("SWE-bench/SWE-agent-LM-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 SWE-bench/SWE-agent-LM-32B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SWE-bench/SWE-agent-LM-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": "SWE-bench/SWE-agent-LM-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SWE-bench/SWE-agent-LM-32B

SGLang

How to use SWE-bench/SWE-agent-LM-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 "SWE-bench/SWE-agent-LM-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": "SWE-bench/SWE-agent-LM-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 "SWE-bench/SWE-agent-LM-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": "SWE-bench/SWE-agent-LM-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SWE-bench/SWE-agent-LM-32B with Docker Model Runner:
```
docker model run hf.co/SWE-bench/SWE-agent-LM-32B
```

Qwen2 or 3, GGUF quants & context size?

by smcleod - opened May 7, 2025

Discussion

smcleod

May 7, 2025

•

edited May 7, 2025

I noticed in your config.json it states this is built on qwen2 rather than qwen3? https://huggingface.co/SWE-bench/SWE-agent-LM-32B/blob/main/config.json#L14

It would be great to have some official GGUF quants made available.

Also, just confirming if the context size is the full 128k, or if it's limited to something small like 32k?

smcleod changed discussion title from GGUF quants & context size? to Qwen2 or 3, GGUF quants & context size? May 7, 2025

john-b-yang

SWE-bench org May 29, 2025

Yes, it's built on Qwen 2.5! Qwen 3 was released essentially at the same time as our work - at some point we'll run on pipeline on Qwen 3 as well and see what performance is like!

I also think the community has created several quantizations here? Do these address your ask?

And for the context size - it's the same as original Qwen 2.5, which is 32k. We didn't experiment with RoPE or anything to increase context window size, but ofc this is on the docket!

smcleod changed discussion status to closed Jul 7, 2025

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

Tap or paste here to upload images

· Sign up or log in to comment