Instructions to use wasmdashai/vivo-o-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use wasmdashai/vivo-o-v1 with Transformers:

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

pipe = pipeline("text-generation", model="wasmdashai/vivo-o-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("wasmdashai/vivo-o-v1")
model = AutoModelForCausalLM.from_pretrained("wasmdashai/vivo-o-v1")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use wasmdashai/vivo-o-v1 with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/wasmdashai/vivo-o-v1

SGLang

How to use wasmdashai/vivo-o-v1 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 "wasmdashai/vivo-o-v1" \
    --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": "wasmdashai/vivo-o-v1",
		"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 "wasmdashai/vivo-o-v1" \
        --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": "wasmdashai/vivo-o-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use wasmdashai/vivo-o-v1 with Docker Model Runner:
```
docker model run hf.co/wasmdashai/vivo-o-v1
```

vivo-o-v1 Architecture

vivo-o-v1

Arabic Conversational AI • Multimodal Intelligence • Enterprise AI

🌐 Live Platform • 🤗 Hugging Face • 🏢 Lahja AI

Why vivo-o-v1?

Unlike general-purpose language models that primarily optimize for broad multilingual reasoning and coding, vivo-o-v1 is designed around real-world conversational AI, with a strong emphasis on Arabic communication, regional dialect understanding, and multimodal human interaction.

Rather than focusing solely on benchmark performance, vivo-o-v1 is engineered to deliver a natural and interactive user experience across web applications, enterprise platforms, and intelligent assistants.

The model has been optimized for scenarios where understanding user intent, maintaining conversational context, and interacting with external systems are more valuable than solving isolated benchmark tasks.

Comparison with General Language Models

Capability	vivo-o-v1	Traditional LLMs
Arabic Language Support	⭐ Native-first focus	General multilingual support
Arabic Dialects	✅ Optimized for regional dialects	Limited consistency across dialects
Saudi Dialect Understanding	✅ High priority	General Arabic only
Conversational AI	✅ Designed for interactive dialogue	General-purpose text generation
Vision-Aware Workflows	✅ Supports visual interaction pipelines	Depends on external multimodal models
Enterprise Integration	✅ Built for APIs, assistants, and automation	General foundation model
Long Context Conversations	✅ Optimized for persistent dialogue	Primarily benchmark-oriented
AI Agents	✅ Designed for autonomous workflows	General tool-calling support
Knowledge Base Integration	✅ Native enterprise integration	Requires external customization
Real-Time Applications	✅ Optimized for production deployments	Varies by implementation

Built for Arabic AI

One of the primary goals of vivo-o-v1 is to improve AI interactions for Arabic-speaking users.

The model emphasizes:

Modern Standard Arabic (MSA)
Saudi Arabic dialects
Gulf dialects
Natural conversational responses
Context-aware dialogue
Reduced literal translations
Better cultural adaptation
Improved Arabic instruction following

Instead of treating Arabic as a secondary language, vivo-o-v1 is designed with Arabic conversations as a core deployment scenario.

Visual Interaction

vivo-o-v1 is designed to work as the intelligence layer behind visual AI applications.

Typical workflows include:

Image understanding
Screenshot analysis
Document understanding
UI interaction
OCR-assisted reasoning
Visual question answering
Screen sharing assistants
Interactive AI copilots

This enables conversational experiences that combine language understanding with visual context for more natural human-computer interaction.

Enterprise AI

vivo-o-v1 is intended for production environments where reliability, integration, and scalability are essential.

Supported enterprise scenarios include:

AI Customer Service
Smart Virtual Assistants
Enterprise Search
Knowledge Management
AI Agents
Voice Assistants
Automation Platforms
Government Services
Healthcare Assistants
Education Platforms

vivo Platform

vivo-o-v1 is the core intelligence model powering the VIVO AI Platform, providing conversational AI, multimodal interaction, enterprise automation, and Arabic-first intelligent assistants.

🌐 Live Platform

https://vivo.lahjai.net

🌐 Lahja AI

https://lahjai.net