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)

# 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")
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 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
```

Getting only 31% on the SWE-bench Verified instead of 40%. What am I doing wrong?

by IgorSlinko - opened Jun 27, 2025

Discussion

IgorSlinko

Jun 27, 2025

My setup:

swe-agent github clone dated May 11 (https://github.com/SWE-agent/SWE-agent/commit/39e8ae3)
config from https://github.com/SWE-bench/SWE-smith/blob/main/agent/swesmith_infer.yaml
vllm for hosting the model:

python3 -m vllm.entrypoints.openai.api_server
--tensor_parallel_size $(echo $CUDA_VISIBLE_DEVICES | tr -cd ',' | wc -c | awk '{print $1+1}')
--enforce_eager
--gpu_memory_utilization 0.7
--enable-auto-tool-choice
--tool-call-parser hermes
--model $model_path
--tokenizer $model_path
--served-model-name $model_name
--rope-scaling '{"factor": 4.0, "original_max_position_embeddings": 32768, "rope_type": "yarn"}'
--enable_prefix_caching
--seed 41
--port $port > $vllm_log_file 2>&1 &

swe-agent inference:

sweagent run-batch
--config config/swesmith_infer.yaml
--agent.model.name hosted_vllm/$model_name
--num_workers 10
--agent.model.temperature 0.0
--agent.model.api_base http://localhost:$port/v1/
--agent.model.per_instance_call_limit 75
--instances.type swe_bench
--instances.subset verified
--instances.split test
--instances.shuffle False >> $run_log_file 2>&1

I will be glad for any comments

IgorSlinko changed discussion title from Getting only 31% on the SWE-bench Verified instead of 40%. What do I do wrong? to Getting only 31% on the SWE-bench Verified instead of 40%. What am I doing wrong? Jun 27, 2025

IgorSlinko

Jul 1, 2025

Btw, the config mentions gpt4-o. Probably left unnoticed and worth fixing.

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