⚡ Sarath OM 1.5

Intelligence. Innovation. Possibility.

Sarath OM 1.5 — An AI-powered model experience available through Ollama.

Ollama Model · Hugging Face Model · Official Website · GitHub

---

🚀 Overview

Sarath OM 1.5 is a model listing in the Sarath OM ecosystem, accessible through the Ollama runtime.

The published Ollama listing advertises text and image input, vision, tool support, and thinking capabilities. It also displays a 256K context window and an approximately 3.3 GB model size.

This README provides installation instructions, API integration examples, model information, potential application areas, and official project resources.

Project Scope

Sarath AI is a software application and integration platform, not an AI model-development or model-training project.

Sarath AI does not claim to create, train, or fine-tune proprietary foundation models. Its software connects application workflows with supported external AI providers, APIs, model runtimes, and services.

The appearance of Sarath OM 1.5 in the Sarath OM ecosystem does not imply ownership or authorship of the underlying foundation model. Architecture, base-model provenance, training methodology, and weight ownership must be established from the published model configuration and upstream documentation.

✨ Published Model Capabilities

Capability	Ollama listing
Text input	Listed
Image input	Listed
Vision	Listed
Tool calling	Listed
Thinking	Listed
Context window	256K tokens displayed
Local execution	latest variant
Cloud execution	cloud variant
Runtime	Ollama

Capabilities may vary depending on the selected model variant, application, runtime version, and configuration.

📊 Model Specifications

Property	Details
Model name	Sarath OM 1.5
Ollama namespace	sarath-om
Model identifier	sarath-om/sarath_om-1.5
Default tag	latest
Cloud tag	cloud
Published model size	Approximately 3.3 GB
Published context window	256K tokens
Input modalities	Text and images
Vision support	Listed
Tool support	Listed
Thinking support	Listed
Model runtime	Ollama
Project	Sarath OM
Developer and project owner	Rishabh Srivastava
Architecture	Refer to published model configuration
Base model	Not independently verified
Parameter count	Not yet confirmed
Quantization	Check selected model variant
Training datasets	Not documented
Benchmark results	No independently verified results included
Hardware requirements	Depend on variant, context, and runtime
License	Verify model and upstream distribution terms

Important: The listed download size is not a guaranteed RAM or VRAM requirement. Actual resource consumption depends on the model configuration, context size, hardware, and runtime settings.

📦 Getting Started

1. Install Ollama

Download Ollama for your operating system:

https://ollama.com/download

Verify your installation:

ollama --version

2. Download Sarath OM 1.5

Pull the default model:

ollama pull sarath-om/sarath_om-1.5

3. Run Sarath OM 1.5

ollama run sarath-om/sarath_om-1.5

Try a prompt:

Hello! Introduce yourself and explain what you can help me with.

Use /bye to exit the interactive session.

4. Inspect Model Details

ollama show sarath-om/sarath_om-1.5

List downloaded models:

ollama list

Check running models:

ollama ps

Inspect the model configuration through the local API:

curl http://localhost:11434/api/show \
  -H "Content-Type: application/json" \
  -d '{
    "model": "sarath-om/sarath_om-1.5",
    "verbose": true
  }'

☁️ Ollama Cloud

The Ollama listing also provides a cloud variant.

Sign in:

ollama signin

Run the cloud version:

ollama run sarath-om/sarath_om-1.5:cloud

The cloud variant uses hosted inference through Ollama and requires an internet connection and eligible account access.

Privacy: Cloud requests are processed by the hosted service. Review Ollama’s applicable privacy and data-handling terms before sending confidential or sensitive information.

Documentation: https://docs.ollama.com/cloud

💻 API Integration

Ollama exposes a local HTTP API for applications.

cURL — Chat API

curl http://localhost:11434/api/chat \
  -H "Content-Type: application/json" \
  -d '{
    "model": "sarath-om/sarath_om-1.5",
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful assistant. Provide clear and accurate responses."
      },
      {
        "role": "user",
        "content": "Explain modern software architecture."
      }
    ],
    "stream": false
  }'

The generated response is available in message.content.

Python Integration

Install the official Ollama Python package:

pip install ollama

Example:

from ollama import chat

MODEL = "sarath-om/sarath_om-1.5"


def main() -> None:
    response = chat(
        model=MODEL,
        messages=[
            {
                "role": "system",
                "content": "You are a helpful assistant.",
            },
            {
                "role": "user",
                "content": "Explain how modern APIs work.",
            },
        ],
        stream=False,
    )

    print(response.message.content or "")


if __name__ == "__main__":
    main()

JavaScript / Node.js Integration

Install the Ollama JavaScript package:

npm install ollama

Example:

import ollama from "ollama";

const MODEL = "sarath-om/sarath_om-1.5";

async function main() {
  try {
    const response = await ollama.chat({
      model: MODEL,
      messages: [
        {
          role: "user",
          content: "Explain modern application architecture.",
        },
      ],
      stream: false,
    });

    console.log(response.message.content);
  } catch (error) {
    console.error("Ollama request failed:", error);
    process.exitCode = 1;
  }
}

main();

🖼️ Vision and Image Input

The Ollama listing advertises image input and vision support.

Example using Python:

from ollama import chat

MODEL = "sarath-om/sarath_om-1.5"

response = chat(
    model=MODEL,
    messages=[
        {
            "role": "user",
            "content": "Describe the objects and important details in this image.",
            "images": ["./sample-image.jpg"],
        }
    ],
    stream=False,
)

print(response.message.content or "")

Replace ./sample-image.jpg with the path to your image.

Supported image formats, image sizes, and processing limits depend on the published model configuration.

🧠 Thinking Support

The Ollama listing displays thinking support.

For models that expose thinking controls, the Ollama API and Python package provide a think option.

Example:

from ollama import chat

response = chat(
    model="sarath-om/sarath_om-1.5",
    messages=[
        {
            "role": "user",
            "content": "Compare REST APIs and GraphQL APIs.",
        }
    ],
    think=True,
    stream=False,
)

print(response.message.content or "")

Verify the selected model variant and installed Ollama client version for the exact supported thinking options.

🛠️ Tool Calling

The Ollama listing advertises tool support.

Tool calling enables an application to provide function definitions that the model can request during a conversation.

Example tool definition:

from ollama import chat

MODEL = "sarath-om/sarath_om-1.5"


def get_weather(city: str) -> str:
    # Replace with an authorized weather API integration.
    return f"Weather lookup requested for {city}."


tools = [
    {
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Get weather information for a city.",
            "parameters": {
                "type": "object",
                "properties": {
                    "city": {
                        "type": "string",
                        "description": "City name",
                    }
                },
                "required": ["city"],
            },
        },
    }
]

response = chat(
    model=MODEL,
    messages=[
        {
            "role": "user",
            "content": "Check the weather in New Delhi.",
        }
    ],
    tools=tools,
)

print(response.message)

A production application should inspect returned tool calls, validate function names and arguments, check user authorization, execute only approved functions, and send tool results back to the model.

Never execute arbitrary shell commands or external actions simply because the model requested them.

🔌 Compatible Application Integrations

The Ollama model listing provides launch examples for compatible developer applications:

Application	Launch command
Claude Code	ollama launch claude --model sarath-om/sarath_om-1.5
OpenCode	ollama launch opencode --model sarath-om/sarath_om-1.5
Hermes Agent	ollama launch hermes --model sarath-om/sarath_om-1.5
OpenClaw	ollama launch openclaw --model sarath-om/sarath_om-1.5

These integrations depend on application compatibility, Ollama configuration, and account access where applicable.

🎯 Potential Use Cases

Depending on verified model behavior, possible applications to evaluate include:

• Conversational interfaces.
• Image understanding and visual assistance.
• Long-context document interaction.
• Developer productivity applications.
• Tool-assisted workflows.
• Structured information processing.
• AI-powered software prototypes.
• Local AI experimentation.

These are potential application areas, not guarantees of accuracy or production suitability.

⚙️ Context and Runtime Configuration

The Ollama listing displays a 256K context window. Actual usable context and resource consumption depend on the model variant and runtime configuration.

Inspect model metadata:

ollama show sarath-om/sarath_om-1.5

For advanced runtime options, see:

• https://docs.ollama.com/modelfile
• https://docs.ollama.com/api

Measure memory consumption and latency on the target hardware before selecting production settings.

🧪 Evaluation and Performance

This README does not claim independently verified benchmark scores or comparative performance improvements.

A reproducible evaluation should document:

• Instruction-following accuracy.
• Long-context retrieval quality.
• Image understanding performance.
• Tool selection and argument accuracy.
• Structured output reliability.
• Latency and hardware utilization.
• Failure cases and limitations.

Record the model identifier, variant, hardware, Ollama version, context configuration, dataset, and evaluation methodology.

🔐 Security and Responsible Use

• Keep API credentials out of frontend code and source control.
• Protect local API endpoints from untrusted network access.
• Validate tool calls, parameters, and external actions.
• Apply authorization, rate limits, and request timeouts.
• Review cloud data-handling practices before submitting sensitive content.
• Verify AI-generated information before relying on it.
• Respect applicable software licenses and third-party rights.

Do not use AI-generated output as the sole basis for consequential medical, legal, financial, or other high-impact decisions.

🧭 Official Resources

Ollama Resources

• Sarath OM 1.5: https://ollama.com/sarath-om/sarath_om-1.5
• Sarath OM profile: https://ollama.com/sarath-om
• Ollama downloads: https://ollama.com/download
• Ollama documentation: https://docs.ollama.com/
• Ollama API: https://docs.ollama.com/api
• Ollama Cloud: https://docs.ollama.com/cloud
• Ollama Python library: https://github.com/ollama/ollama-python
• Ollama JavaScript library: https://github.com/ollama/ollama-js

Hugging Face Resources

• Sarath OM 1.5 Model: https://huggingface.co/sarath-om/sarath_om-1.5
• Sarath OM profile: https://huggingface.co/sarath-om
• Hugging Face Models: https://huggingface.co/models
• Hugging Face documentation: https://huggingface.co/docs
• Model Cards documentation: https://huggingface.co/docs/hub/model-cards

Sarath OM Official Resources

• Official website: https://sarath.openflip.in/
• GitHub organization: https://github.com/Sarath-Om
• LinkedIn company page: https://www.linkedin.com/company/sarath-ai

👨‍💻 Owner Details

Project: Sarath OM
Developer and Owner: Rishabh Srivastava

Developer Portfolio and Social Media

• Portfolio: https://rishabhsrivastava.figma.site/
• X: https://x.com/RishabhSrivast_
• Instagram: https://www.instagram.com/rishabh__.srivastava/
• Threads: https://www.threads.com/@rishabh__.srivastava
• Facebook: https://www.facebook.com/rishabhsrivastava.i/
• LinkedIn: https://www.linkedin.com/in/rishabh-srivastava-rishabh
• GitHub: https://github.com/rishabhsrivastavarishabh
• YouTube: https://www.youtube.com/@RISHABH_SRIVASTAVA_OFFICIAL
• Kaggle: https://www.kaggle.com/rishabhsrivastava2

🌐 Sarath AI — Official Social Media

• Website: https://sarath.openflip.in/
• GitHub: https://github.com/Sarath-Om
• LinkedIn: https://www.linkedin.com/company/sarath-ai
• Instagram: https://www.instagram.com/sarath_ai/
• Threads: https://www.threads.com/@sarath_ai
• Facebook: https://www.facebook.com/sarath.ai.om
• YouTube: https://www.youtube.com/@Sarath_Ai

📄 Version Information

Field	Value
Model	Sarath OM 1.5
Release	1.5
Ollama identifier	sarath-om/sarath_om-1.5
Default tag	latest
Cloud tag	cloud
Runtime	Ollama

Keep this README synchronized with the published model configuration, available variants, verified features, and applicable license terms.

---

⚡ SARATH OM
Intelligence. Innovation. Possibility.

Building useful digital experiences through practical technology and responsible integration.