Instructions to use nex-agi/Nex-N2-Pro-fp8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nex-agi/Nex-N2-Pro-fp8 with Transformers:

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

pipe = pipeline("text-generation", model="nex-agi/Nex-N2-Pro-fp8")
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-Pro-fp8")
model = AutoModelForMultimodalLM.from_pretrained("nex-agi/Nex-N2-Pro-fp8")
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-Pro-fp8 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-Pro-fp8"
# 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-Pro-fp8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nex-agi/Nex-N2-Pro-fp8

SGLang

How to use nex-agi/Nex-N2-Pro-fp8 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-Pro-fp8" \
    --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-Pro-fp8",
		"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-Pro-fp8" \
        --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-Pro-fp8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nex-agi/Nex-N2-Pro-fp8 with Docker Model Runner:
```
docker model run hf.co/nex-agi/Nex-N2-Pro-fp8
```

Gibberish Output

by erincetin - opened about 20 hours ago

Discussion

erincetin

about 20 hours ago

Deploying the fp8 checkpoint causes gibberish output. Opened an issue at : https://github.com/nex-agi/Nex-N2/issues/3

00index

Nex AGI org about 3 hours ago

Hi @erincetin , thanks for flagging this!
We've identified the root cause and landed a targeted fix in the SGLang code. To get rid of the gibberish output, please use one of the following:

Latest code from our SGLang branch — build from our patched fork:
https://github.com/nex-agi/sglang.git
Prebuilt Docker image (already includes the fix) — the easiest option:
nexagi/sglang:v0.5.12-579f84b

After upgrading with either of these, the output should be back to normal. We're also tracking this in the linked GitHub issue (#3) — feel free to follow up there or here if anything still looks off.

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