Instructions to use nex-agi/Nex-N2-mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nex-agi/Nex-N2-mini with Transformers:

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

pipe = pipeline("text-generation", model="nex-agi/Nex-N2-mini")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("nex-agi/Nex-N2-mini")
model = AutoModelForMultimodalLM.from_pretrained("nex-agi/Nex-N2-mini")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.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(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use nex-agi/Nex-N2-mini with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nex-agi/Nex-N2-mini"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nex-agi/Nex-N2-mini",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nex-agi/Nex-N2-mini

SGLang

How to use nex-agi/Nex-N2-mini 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 "nex-agi/Nex-N2-mini" \
    --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": "nex-agi/Nex-N2-mini",
		"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 "nex-agi/Nex-N2-mini" \
        --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": "nex-agi/Nex-N2-mini",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nex-agi/Nex-N2-mini with Docker Model Runner:
```
docker model run hf.co/nex-agi/Nex-N2-mini
```

Reproducing Nex-N2-mini on SWE-bench Verified (mini-swe-agent)

#12

by Kathybenn - opened 6 days ago

Discussion

Kathybenn

6 days ago

Hi Nex-N2 team,

Thanks for releasing Nex-N2-mini. I've been evaluating it on SWE-bench Verified with mini-swe-agent and have been really impressed.

I'm trying to reproduce the 74.40% you reported, but my runs consistently land around 70–71%. The gap seems too large for run-to-run variance, so I suspect a difference in the evaluation setup.

Would you be willing to share the details behind that number? In particular:

mini-swe-agent version/commit and config (step/cost limits, system prompt)
sampling parameters (temperature, top_p, seed), and whether the score is a single run or averaged over several
inference setup (engine + precision, e.g. vLLM/SGLang, bf16/fp8) and the exact model revision
max context/output tokens and how patch extraction and submission are handled

Any of these would help me line my pipeline up with yours. Happy to report back what I find if it's useful.

Thanks!

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