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
```

Missing Model Files?

by zengliangcs - opened May 7, 2025

Discussion

zengliangcs

May 7, 2025

It seems that the model files from model-00001-of-00014.safetensors to model-00003-of-00014.safetensors might be missing. Could you please confirm?

john-b-yang

SWE-bench org May 7, 2025

Oh what the heck, not sure how that happened. Just uploaded. Thanks for the catch!

john-b-yang changed discussion status to closed May 7, 2025

zengliangcs

May 7, 2025

The model-00004-of-00014.safetensors file seems too small. You should double-check whether the model files were uploaded completely and whether they can be loaded correctly.

john-b-yang

SWE-bench org May 7, 2025

Yeah good catch - I think the previous upload I did early-terminated. Just did it again, and double checked pulling + inference, it's good to go now!

zengliangcs

May 8, 2025

>>> from transformers import AutoModelForCausalLM, AutoTokenizer
>>> model = AutoModelForCausalLM.from_pretrained("/mnt/data/liang.zeng/models/SWE-agent-LM-32B")
[2025-05-08 14:06:00,311] [INFO] [real_accelerator.py:219:get_accelerator] Setting ds_accelerator to cuda (auto detect)
Sliding Window Attention is enabled but not implemented for `sdpa`; unexpected results may be encountered.
Loading checkpoint shards:   0%|                                                                                   | 0/14 [00:00<?, ?it/s]
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
  File "/usr/local/lib/python3.10/dist-packages/transformers/models/auto/auto_factory.py", line 571, in from_pretrained
    return model_class.from_pretrained(
  File "/usr/local/lib/python3.10/dist-packages/transformers/modeling_utils.py", line 279, in _wrapper
    return func(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/transformers/modeling_utils.py", line 4399, in from_pretrained
    ) = cls._load_pretrained_model(
  File "/usr/local/lib/python3.10/dist-packages/transformers/modeling_utils.py", line 4822, in _load_pretrained_model
    state_dict = load_state_dict(
  File "/usr/local/lib/python3.10/dist-packages/transformers/modeling_utils.py", line 513, in load_state_dict
    with safe_open(checkpoint_file, framework="pt") as f:
FileNotFoundError: No such file or directory: "/mnt/data/liang.zeng/models/SWE-agent-LM-32B/ft-model-00001-of-00014.safetensors"
>>>

Unfortunately, it still doesn’t load correctly.

john-b-yang

SWE-bench org May 8, 2025

Oh wait i think it seems like it's looking for

FileNotFoundError: No such file or directory: "/mnt/data/liang.zeng/models/SWE-agent-LM-32B/ft-model-00001-of-00014.safetensors"

But the *.safetensors I uploaded are all prefixed with "model-", not "ft-".

Could you try either renaming your files locally or updating your serving framework to point to "model-000...safetensors" instead? Perhaps the first option is easier.

I can also update the file names to have the "ft-" prefix, not sure what the usual convention is.

nickname100231

May 12, 2025

@john-b-yang Opened a PR:
https://huggingface.co/SWE-bench/SWE-agent-LM-32B/discussions/5

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