Instructions to use ArkAiLab-Adl/nexora-vector-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ArkAiLab-Adl/nexora-vector-v0.1 with Transformers:

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

pipe = pipeline("text-generation", model="ArkAiLab-Adl/nexora-vector-v0.1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ArkAiLab-Adl/nexora-vector-v0.1")
model = AutoModelForCausalLM.from_pretrained("ArkAiLab-Adl/nexora-vector-v0.1")
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

vLLM

How to use ArkAiLab-Adl/nexora-vector-v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ArkAiLab-Adl/nexora-vector-v0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ArkAiLab-Adl/nexora-vector-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ArkAiLab-Adl/nexora-vector-v0.1

SGLang

How to use ArkAiLab-Adl/nexora-vector-v0.1 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 "ArkAiLab-Adl/nexora-vector-v0.1" \
    --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": "ArkAiLab-Adl/nexora-vector-v0.1",
		"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 "ArkAiLab-Adl/nexora-vector-v0.1" \
        --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": "ArkAiLab-Adl/nexora-vector-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ArkAiLab-Adl/nexora-vector-v0.1 with Docker Model Runner:
```
docker model run hf.co/ArkAiLab-Adl/nexora-vector-v0.1
```

comfyui

by Lambda-7C0 - opened Apr 17

Discussion

Lambda-7C0

Apr 17

Does she work at comfyui?
Do you have a workflow for this?

fmasterpro27

ArkAiLab org Apr 17

We haven’t officially tested Nexora-Vector-v0.1 on ComfyUI yet.

Since the model is an LLM that generates SVG/vector code, it may require custom text-generation nodes rather than a standard image workflow.

For now, it would be better suited for platforms such as LM Studio, Ollama, or llama.cpp.

A quantized GGUF version is also available here for easier local use:
https://huggingface.co/Open4bits/nexora-vector-v0.1-GGUF

We may test and share ComfyUI compatibility in the future.

Lambda-7C0

Apr 20

Thank you very much!

fmasterpro27

ArkAiLab org Apr 20

You’re very welcome! Glad to help. If we test ComfyUI support in the future, we’ll share updates with the community.

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