---
library_name: transformers
license: apache-2.0
license_link: https://huggingface.co/hadadrjt/JARVIS/blob/main/LICENSE
base_model:
- Qwen/Qwen3-14B
tags:
- jarvis
- ollama
- agent
---

**J.A.R.V.I.S.**, which stands for "**Just a Rather Very Intelligent System**", is an advanced AI language model inspired by [Iron Man](https://wikipedia.org/wiki/J.A.R.V.I.S.) iconic assistant. This model delivers context-aware, high-fidelity natural language processing capabilities for a wide range of applications.

<div style="font-size: x-small; font-weight: bold;">NOTICE! This is only the base model and a lighter version for public release. To use the more advanced version, please use the available space provided.</div>

## Model Highlights

- **Powerful Text Generation Engine**      
<video src="https://gitlab.com/hdrjt/assets/-/raw/master/videos/JARVIS_chat.mp4" controls>Your browser does not support the video tag.</video>
**J.A.R.V.I.S.** serves as the core of an AI solution capable of producing natural and creative text with high quality, ready to help you create inspiring and engaging content.

- **Seamless Integration, Limitless Possibilities**      
<video src="https://gitlab.com/hdrjt/assets/-/raw/master/videos/JARVIS_demo.mp4" controls>Your browser does not support the video tag.</video>
Designed with high flexibility, **J.A.R.V.I.S.** can be seamlessly integrated into a wide range of platforms and systems you use, including web applications, chatbots, agent modes, tools, system integrations, and automated workflows, adapting effortlessly to available resource capacities.

- **Scalable & Resource-Aware**      
Regardless of your computing environment, **J.A.R.V.I.S.** can be optimized for optimal performance, from lightweight devices to enterprise-class infrastructure, ensuring efficiency and responsiveness without compromise.

- **Versatile Use Cases**      
Ideal for a wide range of needs, from creative content creation, writing assistance, to developing interactive text-based applications, giving you unlimited freedom to innovate.

- **Agentic Use**      
<video src="https://gitlab.com/hdrjt/assets/-/raw/master/videos/JARVIS_agent.mp4" controls>Your browser does not support the video tag.</video>
Example usage, please refer to the [Qwen3 Documentation](https://huggingface.co/dulimov/Qwen3-0.6B-rk3588-1.2.1-unsloth-16k#agentic-use), and the [Qwen-Agent GitHub repository](https://github.com/QwenLM/Qwen-Agent).

**J.A.R.V.I.S.** is not just an AI model, it is an intelligent partner ready to transform your ideas into words with a touch of intelligence and high flexibility.

For more detailed information about this model, you can explore all its advantages by referring to the explanation of the underlying base model. [Here](https://huggingface.co/Qwen/Qwen3-14B#qwen3-highlights)!

## Core Capabilities

Discover the amazing power of **J.A.R.V.I.S.**, as your smart and reliable AI companion. It answers your toughest questions with confidence, explains complex ideas in simple terms, translates languages smoothly, writes clean and efficient code, summarizes lengthy information into easy-to-understand points, sparks your creativity with fresh and original content, and guides you through study or research with expert advice. This is only the beginning of what **J.A.R.V.I.S.** can do for you.


## Notebook

Although this model has a large size and many parameters, you can run it on Google Colab for free! Using the script I have optimized. [Click here](https://colab.research.google.com/drive/1FvP9d82cvzu_OrT8HmEGJntU-WDq-63M) to access it.

## Ollama

The source of the **J.A.R.V.I.S.** model on Ollama can be found [here](https://ollama.com/hadad/JARVIS).

```
ollama run hadad/JARVIS
```

```
# 4-bit (Q4_K_M)
ollama run hadad/JARVIS:4bit
```

## Quick Start

```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer

# Model
model = "hadadrjt/JARVIS"

# Load tokenizer and model
tokenizer = AutoTokenizer.from_pretrained(model)
model = AutoModelForCausalLM.from_pretrained(
    model,
    torch_dtype="auto",
    device_map="auto"
)

# User input
input = "Tell me about yourself" # Insert your message here.

# Build chat-style prompt
messages = [{"role": "user", "content": input}]

text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
    enable_thinking=True
)

# Tokenize input
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

# Streaming setup
streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)

# Generate response with streaming
with torch.inference_mode():
    generated_ids = model.generate(
        **model_inputs,
        max_new_tokens=32768,
        temperature=0.6,
        top_p=0.95,
        min_p=0,
        top_k=20,
        repetition_penalty=1.0,
        streamer=streamer
    )
```

## API

**J.A.R.V.I.S.** offers API support for both general users and developers for free.

For **general users**, it can be operated directly through the local terminal on Linux, Termux, macOS, or Windows (WSL) without requiring any special configuration.

```bash
# Installations.
# Make sure you have "wget", "python3" and "pip" installed.
# This package have very small size.
wget https://huggingface.co/spaces/hadadrjt/ai/raw/main/assets/bin/install.sh && chmod a+x install.sh && ./install.sh
```

```bash
# Run J.A.R.V.I.S. in your terminal.
# Example normal usage.
./ai Your message here.

# Example with Deep Search.
./ai /dp Your message here.
```

```bash
# Linux user's
# Bonus for more flexible.
sudo mv ai /bin/

# Now you can run with simple command.
ai Your message here.
```

<div style="font-size: x-small; font-weight: bold;">Please note: For the Terminal version, audio and image generation functionalities are exclusively available within the main Spaces environment. This is due to the Terminal's inherent limitations in displaying images and playing audio directly.</div>

For **developers**, an OpenAI-compatible API is available, facilitating seamless integration with various systems. Additionally, this API endpoint is open source and can be accessed [here](https://huggingface.co/spaces/hadadrjt/api).

<video src="https://gitlab.com/hdrjt/assets/-/raw/master/videos/JARVIS_api.mp4" controls>
  Your browser does not support the video tag.
</video>

```bash
# OpenAI Style (developers only)
curl https://hadadrjt-api.hf.space/v1/responses \
  -H "Content-Type: application/json" \
  -d '{
    "model": "JARVIS: 2.1.3",
    "input": "Write a one-sentence bedtime story about a unicorn.",
    "stream": true
  }'
```

```
# Endpoint
https://hadadrjt-api.hf.space/v1
```

<div style="font-size: x-small; font-weight: bold;">Please note: OpenAI-compatible API feature is deprecated for the Next-Gen version. The previous screen recording was made using the old version of Spaces, not the Next-Gen version. A new release will be available soon.</div>

## Responsible Use

Although **J.A.R.V.I.S.** delivers impressive results, it may reflect biases from its training data and occasionally produce incorrect outputs. It is not intended for real-time safety-critical applications without human oversight. I recommend implementing human review workflows, monitoring outputs for fairness and accuracy, and updating the model with domain-specific data over time.

## Acknowledgments and Contact

This work builds upon the [Qwen3-14B](https://huggingface.co/Qwen/Qwen3-14B) open-source foundation. For feedback, collaboration or support, please reach out to [Hadad Darajat](https://linkedin.com/in/hadadrjt) at [hadad@linuxmail.org](mailto:hadad@linuxmail.org). I welcome contributions that help **J.A.R.V.I.S.** continue to evolve.

Thank you for choosing **J.A.R.V.I.S.** to power your intelligent language applications.

## Citation

```
@misc{jarvis,
  title   = {J.A.R.V.I.S.},
  author  = {Hadad Darajat},
  year    = {2025},
  license = {Apache-2.0},
  base    = {Qwen/Qwen3-14B}
}
```