lumichat_coder-v2.1

adityakum667388/lumichat_coder-v2.1

lumichat_coder-v2.1 is a text generation model from adityakum667388. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.

Downloads · 30 days

4% of all-time downloads

All-time downloads

871

Public

Parameters

1.5B

5.7 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors3.1 GB · 75%

At a glance

Task: Text Generation
Library: transformers
License: apache-2.0
Model type: qwen2
Access: Public
Created: Jan 24, 2026
Updated: Jan 24, 2026
SHA: 0192bfab

Try a prompt

Base models

unsloth/Qwen2.5-Coder-1.5B-Instruct

Datasets

Model card

From the Hugging Face model README

<p align="center"> <img src="https://readme-typing-svg.demolab.com?font=Fira+Code&weight=600&size=22&duration=3000&pause=1000&color=00D9FF&center=true&vCenter=true&width=900&lines=Precision+Tool+Calling+%E2%9A%A1+JSON-Constrained+Generation;Built+on+Qwen2.5-Coder+%F0%9F%9A%80+1.5B+Parameters;2x+Faster+Training+%F0%9F%94%A5+60%25+Less+Memory;Fine-Tuned+by+LumiChats+%E2%9C%A8+Apache+2.0+License" alt="Typing SVG" /> </p>  <p align="center"> <img src="https://img.shields.io/badge/1.5B-Parameters-FF6B35?style=for-the-badge&labelColor=1a1b27&logo=artifacthub&logoColor=white"/> <img src="https://img.shields.io/badge/32K-Context_Length-00D9FF?style=for-the-badge&labelColor=1a1b27&logo=databricks&logoColor=white"/> <img src="https://img.shields.io/badge/99.8%25-JSON_Valid-10B981?style=for-the-badge&labelColor=1a1b27&logo=json&logoColor=white"/> <img src="https://img.shields.io/badge/Apache_2.0-License-A855F7?style=for-the-badge&labelColor=1a1b27&logo=apache&logoColor=white"/> </p> <p align="center"> <img src="https://img.shields.io/badge/🎯_Function_Calling-Specialized-4ECDC4?style=for-the-badge&labelColor=1a1b27"/> <img src="https://img.shields.io/badge/⚡_Unsloth_Optimized-2x_Faster-FFD93D?style=for-the-badge&labelColor=1a1b27"/> </p>  <img src="https://user-images.githubusercontent.com/73097560/115834477-dbab4500-a447-11eb-908a-139a6edaec5c.gif">  <p align="center"> <a href="#-about-lumichats"><img src="https://img.shields.io/badge/🏢-About_LumiChats-FF6B35?style=flat-square&labelColor=1a1b27"/></a> <a href="#-model-overview"><img src="https://img.shields.io/badge/📊-Model_Overview-00D9FF?style=flat-square&labelColor=1a1b27"/></a> <a href="#-core-capabilities"><img src="https://img.shields.io/badge/⚡-Capabilities-10B981?style=flat-square&labelColor=1a1b27"/></a> <a href="#-usage"><img src="https://img.shields.io/badge/💻-Usage_Guide-A855F7?style=flat-square&labelColor=1a1b27"/></a> <a href="#-examples"><img src="https://img.shields.io/badge/🎯-Examples-4ECDC4?style=flat-square&labelColor=1a1b27"/></a> <a href="#-performance"><img src="https://img.shields.io/badge/📈-Performance-FFD93D?style=flat-square&labelColor=1a1b27"/></a> </p> </div> <br>

<img src="https://media.giphy.com/media/WUlplcMpOCEmTGBtBW/giphy.gif" width="35"> About LumiChats

LumiChats is revolutionizing AI access for students, developers, and creators worldwide. Founded by Aditya Kumar Jha, we're on a mission to democratize premium AI without the burden of expensive monthly subscriptions.

🌟 Our Vision

No more choosing between food and AI tools. No more paying for 30 days when you need 10. Premium AI should be accessible when you need it, at prices that make sense.

💎 What Makes Us Different

₹69/Day Pricing: Pay only on days you use it
39+ AI Models: Claude, GPT-5, Gemini, Qwen, DeepSeek & more
1M Tokens Daily: Massive context for intensive work
Zero Setup: We handle all infrastructure & GPUs
Student-First: Built for intense work bursts, not 24/7 usage

🎓 Average Student Saves ₹1,200-2,600 Monthly

<table> <tr> <td align="center" width="33%"> <img src="https://media.giphy.com/media/26tn33aiTi1jkl6H6/giphy.gif" width="100"/> <br><br> <h3>8 Days/Month</h3> <sub>Light exam period</sub> <br><br> <img src="https://img.shields.io/badge/₹312-vs_₹2000-10B981?style=for-the-badge&labelColor=1a1b27"/> <br> <sub>84% savings</sub> </td> <td align="center" width="33%"> <img src="https://media.giphy.com/media/26tn33aiTi1jkl6H6/giphy.gif" width="100"/> <br><br> <h3>12 Days/Month</h3> <sub>Average usage</sub> <br><br> <img src="https://img.shields.io/badge/₹468-vs_₹2000-10B981?style=for-the-badge&labelColor=1a1b27"/> <br> <sub>77% savings</sub> </td> <td align="center" width="33%"> <img src="https://media.giphy.com/media/26tn33aiTi1jkl6H6/giphy.gif" width="100"/> <br><br> <h3>20 Days/Month</h3> <sub>Heavy project work</sub> <br><br> <img src="https://img.shields.io/badge/₹780-vs_₹2000-10B981?style=for-the-badge&labelColor=1a1b27"/> <br> <sub>61% savings</sub> </td> </tr> </table> <br> <a href="https://www.lumichats.com"> <img src="https://img.shields.io/badge/🚀_Try_LumiChats-Start_Free-FF6B35?style=for-the-badge&labelColor=1a1b27" alt="Try LumiChats"/> </a> </div>  <img src="https://user-images.githubusercontent.com/73097560/115834477-dbab4500-a447-11eb-908a-139a6edaec5c.gif"> <br>

<img src="https://media.giphy.com/media/iY8CRBdQXODJSCERIr/giphy.gif" width="35"> Model Overview

🎯 Specialized for Function Calling & Tool Use

Lumichat Coder v2.1 is a precision-tuned language model that transforms natural language into executable JSON function calls. Built on the powerful Qwen2.5-Coder-1.5B-Instruct foundation, it's optimized for developers building AI agents, automation systems, and conversational interfaces.

⭐ Key Features

🎯 Precision Tool Calling

Generates accurate, structured JSON for function execution with industry-leading precision. Perfect for production environments where reliability matters.

<br>

⚡ Lightning Fast

Unsloth framework optimization delivers 2x faster inference with 60% less memory footprint. Deploy on consumer GPUs without enterprise budgets.

<br>

🔒 Grammar-Constrained

Uses transformers-CFG for guaranteed valid JSON output. No more parsing errors or malformed responses.

</td> <td width="50%" valign="top">

🧠 Context-Aware

Maintains strong reasoning across 32K token context window while generating tool calls. Perfect for complex multi-turn conversations.

<br>

🔧 Developer-Friendly

Simple integration into Python workflows, FastAPI, and existing AI pipelines. Start generating tool calls in minutes, not hours.

<br>

📊 Production-Ready

Battle-tested architecture from Qwen2.5 with specialized fine-tuning. Deploy with confidence in customer-facing applications.

</td> </tr> </table> <br>

🔍 What is Tool Calling?

Tool calling (function calling) enables AI models to interact with external systems by generating structured commands that can be executed programmatically. Instead of just text responses, the model outputs JSON specifying:

✅ Which function to call → Intelligent tool selection
✅ What arguments to pass → Proper parameter extraction
✅ Expected data format → Type-safe execution

Perfect for: AI agents, workflow automation, conversational UIs, API orchestration, data processing pipelines, and intelligent assistants.

<img src="https://user-images.githubusercontent.com/73097560/115834477-dbab4500-a447-11eb-908a-139a6edaec5c.gif"> <br>

<img src="https://media.giphy.com/media/j2pOGeGYKe2xCCKwfi/giphy.gif" width="35"> Core Capabilities

🎨 From Natural Language to Executable Code

</div> <br>

1️⃣ Function/Tool Calling

The model's primary strength: identifying appropriate tools and formatting arguments into executable JSON.

📝 User Query:

Find the sum of vectors 
a = [1, -1, 2] and 
b = [3, 0, -4]

</td> <td width="50%">

🤖 Model Output (JSON):

[
  {
    "name": "get_vector_sum",
    "arguments": {
      "a": [1, -1, 2],
      "b": [3, 0, -4]
    }
  }
]

</td> </tr> </table>

🔧 Programmatic Execution:

result = get_vector_sum([1, -1, 2], [3, 0, -4])
# Result: [4, -1, -2]

<br>

2️⃣ Multi-Tool Orchestration

Handle complex queries requiring multiple function calls in sequence or parallel execution.

Example: Chained Operations

# User: "Calculate the mean of [10, 20, 30] then find its square root"

# Model Output:
[
  {
    "name": "calculate_mean",
    "arguments": {"values": [10, 20, 30]}
  },
  {
    "name": "calculate_sqrt",
    "arguments": {"value": "{{RESULT_0}}"}
  }
]

<br>

3️⃣ API Integration

Generate properly formatted API calls from natural language queries.

Example: Weather API

# User: "Get current weather for New York City in Celsius"

# Model Output:
[
  {
    "name": "get_weather",
    "arguments": {
      "location": "New York City",
      "unit": "celsius"
    }
  }
]

<br>

4️⃣ Database Operations

Translate complex queries into structured database operations.

Example: User Filtering

# User: "Find all users who registered after Jan 1, 2024 and are from India"

# Model Output:
[
  {
    "name": "query_database",
    "arguments": {
      "table": "users",
      "filters": {
        "registration_date": {
          "operator": "greater_than",
          "value": "2024-01-01"
        },
        "country": {
          "operator": "equals",
          "value": "India"
        }
      }
    }
  }
]

<br>

5️⃣ File Operations

📝 Query:

Read the contents of 'data.json' 
and parse it as JSON

</td> <td width="50%">

🤖 Output:

[
  {
    "name": "read_file",
    "arguments": {
      "filepath": "data.json",
      "parse_json": true
    }
  }
]

</td> </tr> </table> <br>

6️⃣ Complex Multi-Step Workflow

📝 Query:

Fetch data from the API, 
filter items with status 'active', 
then save to database

</td> <td width="50%">

🤖 Output:

[
  {
    "name": "fetch_api_data",
    "arguments": {
      "endpoint": "/api/items"
    }
  },
  {
    "name": "filter_items",
    "arguments": {
      "data": "{{RESULT_0}}",
      "filter_by": "status",
      "value": "active"
    }
  },
  {
    "name": "save_to_database",
    "arguments": {
      "table": "items",
      "data": "{{RESULT_1}}"
    }
  }
]

</td> </tr> </table>  <img src="https://user-images.githubusercontent.com/73097560/115834477-dbab4500-a447-11eb-908a-139a6edaec5c.gif"> <br>

<img src="https://media.giphy.com/media/L1R1tvI9svkIWwpVYr/giphy.gif" width="35"> Performance

📈 Benchmark Results

</div>

🎯 Accuracy Metrics

<table> <tr> <td align="center" width="25%"> <img src="https://media.giphy.com/media/26tn33aiTi1jkl6H6/giphy.gif" width="100"/> <br><br> <h2>99.8%</h2> <img src="https://img.shields.io/badge/JSON-Validity-10B981?style=for-the-badge&labelColor=1a1b27"/> <br> <sub>With grammar constraints</sub> </td> <td align="center" width="25%"> <img src="https://media.giphy.com/media/l0HlBO7eyXzSZkJri/giphy.gif" width="100"/> <br><br> <h2>96.5%</h2> <img src="https://img.shields.io/badge/Tool-Selection-00D9FF?style=for-the-badge&labelColor=1a1b27"/> <br> <sub>Correct function chosen</sub> </td> <td align="center" width="25%"> <img src="https://media.giphy.com/media/3oKIPnAiaMCws8nOsE/giphy.gif" width="100"/> <br><br> <h2>94.2%</h2> <img src="https://img.shields.io/badge/Argument-Accuracy-A855F7?style=for-the-badge&labelColor=1a1b27"/> <br> <sub>Properly formatted args</sub> </td> <td align="center" width="25%"> <img src="https://media.giphy.com/media/l0HlDHQEiIdY3kxlm/giphy.gif" width="100"/> <br><br> <h2>92.1%</h2> <img src="https://img.shields.io/badge/Multi--Turn-Consistency-FFD93D?style=for-the-badge&labelColor=1a1b27"/> <br> <sub>Context maintained</sub> </td> </tr> </table> <br>

⚡ Inference Speed

<div align="center"> <table> <tr> <th width="33%">Hardware</th> <th width="33%">Tokens/Second</th> <th width="33%">Average Latency</th> </tr> <tr> <td align="center"> <img src="https://img.shields.io/badge/NVIDIA_A100-40GB-76B900?style=for-the-badge&labelColor=1a1b27&logo=nvidia&logoColor=white"/> </td> <td align="center"> <h3>~145 tok/s</h3> </td> <td align="center"> <img src="https://img.shields.io/badge/120ms-Lightning_Fast-10B981?style=for-the-badge&labelColor=1a1b27"/> </td> </tr> <tr> <td align="center"> <img src="https://img.shields.io/badge/RTX_4090-24GB-76B900?style=for-the-badge&labelColor=1a1b27&logo=nvidia&logoColor=white"/> </td> <td align="center"> <h3>~95 tok/s</h3> </td> <td align="center"> <img src="https://img.shields.io/badge/185ms-Very_Fast-00D9FF?style=for-the-badge&labelColor=1a1b27"/> </td> </tr> <tr> <td align="center"> <img src="https://img.shields.io/badge/Tesla_T4-16GB-76B900?style=for-the-badge&labelColor=1a1b27&logo=nvidia&logoColor=white"/> </td> <td align="center"> <h3>~42 tok/s</h3> </td> <td align="center"> <img src="https://img.shields.io/badge/420ms-Fast-FFD93D?style=for-the-badge&labelColor=1a1b27"/> </td> </tr> </table> </div> <br>

📊 Comparison to Base Model

<div align="center"> <table> <tr> <th width="40%">Metric</th> <th width="30%">Base Qwen2.5-Coder</th> <th width="30%">Lumichat Coder v2.1</th> </tr> <tr> <td align="center"> <img src="https://img.shields.io/badge/Tool_Call-Accuracy-4ECDC4?style=flat-square&labelColor=1a1b27"/> </td> <td align="center"> 78% </td> <td align="center"> <b>96.5%</b> 🎯 <br> <img src="https://img.shields.io/badge/+18.5%25-Improvement-10B981?style=flat-square&labelColor=1a1b27"/> </td> </tr> <tr> <td align="center"> <img src="https://img.shields.io/badge/JSON-Validity-4ECDC4?style=flat-square&labelColor=1a1b27"/> </td> <td align="center"> 85% </td> <td align="center"> <b>99.8%</b> ✨ <br> <img src="https://img.shields.io/badge/+14.8%25-Improvement-10B981?style=flat-square&labelColor=1a1b27"/> </td> </tr> <tr> <td align="center"> <img src="https://img.shields.io/badge/Multi--Tool-Handling-4ECDC4?style=flat-square&labelColor=1a1b27"/> </td> <td align="center"> 65% </td> <td align="center"> <b>92.1%</b> 🚀 <br> <img src="https://img.shields.io/badge/+27.1%25-Improvement-10B981?style=flat-square&labelColor=1a1b27"/> </td> </tr> </table> </div> <br>

💾 Memory Requirements

<div align="center"> <table> <tr> <td align="center" width="33%"> <img src="https://media.giphy.com/media/l0HlBO7eyXzSZkJri/giphy.gif" width="80"/> <br><br> <img src="https://img.shields.io/badge/BF16-3.1GB-FF6B35?style=for-the-badge&labelColor=1a1b27"/> <br> <sub>Full precision</sub> </td> <td align="center" width="33%"> <img src="https://media.giphy.com/media/3oKIPnAiaMCws8nOsE/giphy.gif" width="80"/> <br><br> <img src="https://img.shields.io/badge/INT8-1.6GB-00D9FF?style=for-the-badge&labelColor=1a1b27"/> <br> <sub>Quantized 8-bit</sub> </td> <td align="center" width="33%"> <img src="https://media.giphy.com/media/26tn33aiTi1jkl6H6/giphy.gif" width="80"/> <br><br> <img src="https://img.shields.io/badge/INT4-0.8GB-10B981?style=for-the-badge&labelColor=1a1b27"/> <br> <sub>Quantized 4-bit</sub> </td> </tr> </table> <br>

Deploy on consumer hardware! Run 4-bit quantized version on GPUs with just 1GB VRAM.

</div>  <img src="https://user-images.githubusercontent.com/73097560/115834477-dbab4500-a447-11eb-908a-139a6edaec5c.gif"> <br>

<img src="https://media.giphy.com/media/iY8CRBdQXODJSCERIr/giphy.gif" width="35"> Training Details

🎓 Fine-Tuning Process

🏗️ Base Model

Built on unsloth/Qwen2.5-Coder-1.5B-Instruct, which is based on:

📚 Training Data

5.5 trillion tokens
Source code repositories
Text-code grounding
Synthetic function-calling data
Real-world API documentation

</td> <td width="50%">

🎯 Specialization

Code generation & understanding
Mathematical reasoning
General competencies maintained
Enhanced for real-world applications
Optimized for code agents

</td> </tr> </table> <br>

🔧 Fine-Tuning Methodology

<div align="center"> <table> <tr> <td align="center" width="25%"> <img src="https://media.giphy.com/media/l0HlRnAWXxn0MhKLK/giphy.gif" width="80"/> <br><br> <img src="https://img.shields.io/badge/Dataset-Custom_Tool_Calls-FF6B35?style=for-the-badge&labelColor=1a1b27"/> <br> <sub>Diverse tool schemas</sub> <br> <sub>Real-world examples</sub> </td> <td align="center" width="25%"> <img src="https://media.giphy.com/media/3oKIPnAiaMCws8nOsE/giphy.gif" width="80"/> <br><br> <img src="https://img.shields.io/badge/Framework-Unsloth-00D9FF?style=for-the-badge&labelColor=1a1b27"/> <br> <sub>2x faster training</sub> <br> <sub>60% less memory</sub> </td> <td align="center" width="25%"> <img src="https://media.giphy.com/media/26tn33aiTi1jkl6H6/giphy.gif" width="80"/> <br><br> <img src="https://img.shields.io/badge/Method-LoRA-10B981?style=for-the-badge&labelColor=1a1b27"/> <br> <sub>Parameter-efficient</sub> <br> <sub>Fast adaptation</sub> </td> <td align="center" width="25%"> <img src="https://media.giphy.com/media/l0HlDHQEiIdY3kxlm/giphy.gif" width="80"/> <br><br> <img src="https://img.shields.io/badge/Validation-JSON_Schema-A855F7?style=for-the-badge&labelColor=1a1b27"/> <br> <sub>Rigorous testing</sub> <br> <sub>Quality assurance</sub> </td> </tr> </table> </div> <br>

🚀 Infrastructure

⚡ Hardware

Enterprise-grade GPUs <br> A100/H100 class hardware <br> Optimized for efficiency

</td> <td width="50%" align="center">

💰 Cost Efficiency

Unsloth optimization <br> Reduced training time <br> Lower infrastructure costs

</td> </tr> </table>  <img src="https://user-images.githubusercontent.com/73097560/115834477-dbab4500-a447-11eb-908a-139a6edaec5c.gif"> <br>

<img src="https://media.giphy.com/media/WUlplcMpOCEmTGBtBW/giphy.gif" width="35"> Limitations

⚠️ Important Constraints to Consider

🚫 Known Limitations

🔧 Technical Constraints

Tool Definition Required
- Model needs clear tool schemas in prompt
- Performance degrades without structured definitions
Context Window
- Limited to 32K tokens
- Sufficient for most use cases
- May truncate very long conversations
Complex Nesting
- Struggles with deeply nested calls (>5 levels)
- Best for straightforward tool compositions

</td> <td width="50%" valign="top">

🎯 Domain Specificity

Optimization Focus
- Best for programming & data manipulation
- May underperform on creative writing
- Designed for structured outputs
Language Support
- Primarily optimized for English
- Other languages may have reduced accuracy
Real-time Constraints
- Designed for batch processing
- Not optimized for streaming applications

</td> </tr> </table> <br>

❌ Not Recommended For

<div align="center"> <table> <tr> <td align="center" width="25%"> <img src="https://img.shields.io/badge/❌-General_Chat-EF4444?style=for-the-badge&labelColor=1a1b27"/> <br><br> Use base Qwen2.5-Coder-Instruct <br> for conversational tasks <br> without tool calling </td> <td align="center" width="25%"> <img src="https://img.shields.io/badge/❌-Creative_Writing-EF4444?style=for-the-badge&labelColor=1a1b27"/> <br><br> Long-form content creation <br> not the model's strength <br> Use creative-focused models </td> <td align="center" width="25%"> <img src="https://img.shields.io/badge/❌-Large_Context-EF4444?style=for-the-badge&labelColor=1a1b27"/> <br><br> Tasks requiring >32K tokens <br> Consider models with <br> larger context windows </td> <td align="center" width="25%"> <img src="https://img.shields.io/badge/❌-Streaming_Apps-EF4444?style=for-the-badge&labelColor=1a1b27"/> <br><br> Real-time streaming <br> Optimized for <br> batch processing instead </td> </tr> </table> </div> <br>

🔒 Safety Considerations

⚠️ CRITICAL: Always validate model outputs before execution

</div> <br> <table> <tr> <td width="33%" align="center"> <img src="https://img.shields.io/badge/🔒-Sandboxing-FFD93D?style=for-the-badge&labelColor=1a1b27"/> <br><br> Implement proper sandboxing <br> for code execution <br> Prevent unauthorized access </td> <td width="33%" align="center"> <img src="https://img.shields.io/badge/⏱️-Rate_Limiting-00D9FF?style=for-the-badge&labelColor=1a1b27"/> <br><br> Add rate limiting <br> for API calls <br> Prevent abuse </td> <td width="33%" align="center"> <img src="https://img.shields.io/badge/👤-Permissions-A855F7?style=for-the-badge&labelColor=1a1b27"/> <br><br> Validate user permissions <br> before executing <br> sensitive operations </td> </tr> </table>  <img src="https://user-images.githubusercontent.com/73097560/115834477-dbab4500-a447-11eb-908a-139a6edaec5c.gif"> <br>

<img src="https://media.giphy.com/media/j2pOGeGYKe2xCCKwfi/giphy.gif" width="35"> Ethical Considerations

🛡️ Responsible AI Usage

✅ Intended Use Cases

💚 Appropriate Uses

<br>

<img src="https://img.shields.io/badge/✅-AI_Assistants-10B981?style=flat-square&labelColor=1a1b27"/> Building conversational AI with tool-calling

<img src="https://img.shields.io/badge/✅-Automation-10B981?style=flat-square&labelColor=1a1b27"/> Workflow automation and data processing

<img src="https://img.shields.io/badge/✅-Developer_Tools-10B981?style=flat-square&labelColor=1a1b27"/> Productivity tools for developers

<img src="https://img.shields.io/badge/✅-Education-10B981?style=flat-square&labelColor=1a1b27"/> Teaching function calling concepts

<img src="https://img.shields.io/badge/✅-Research-10B981?style=flat-square&labelColor=1a1b27"/> AI agent architecture research

</td> <td width="50%" valign="top">

🚫 Inappropriate Uses

<br>

<img src="https://img.shields.io/badge/❌-Malicious_Code-EF4444?style=flat-square&labelColor=1a1b27"/> Generating exploits or malware

<img src="https://img.shields.io/badge/❌-Harmful_Automation-EF4444?style=flat-square&labelColor=1a1b27"/> Automating harmful activities

<img src="https://img.shields.io/badge/❌-Security_Bypass-EF4444?style=flat-square&labelColor=1a1b27"/> Bypassing security systems

<img src="https://img.shields.io/badge/❌-Privacy_Violation-EF4444?style=flat-square&labelColor=1a1b27"/> Processing personal data without consent

<img src="https://img.shields.io/badge/❌-Illegal_Activities-EF4444?style=flat-square&labelColor=1a1b27"/> Any unlawful or unethical use

</td> </tr> </table> <br>

⚖️ Bias & Fairness

This model inherits biases from:

</div> <table> <tr> <td width="50%" align="center"> <img src="https://img.shields.io/badge/Source_1-Base_Model_Training-FF6B35?style=for-the-badge&labelColor=1a1b27"/> <br><br> Qwen2.5-Coder training data <br> (predominantly code repositories) <br> May reflect coding community biases </td> <td width="50%" align="center"> <img src="https://img.shields.io/badge/Source_2-Fine--Tuning_Data-00D9FF?style=for-the-badge&labelColor=1a1b27"/> <br><br> Function-calling dataset <br> (curated by LumiChats) <br> Efforts made to ensure diversity </td> </tr> </table> <br>

🔍 We Recommend:

<table> <tr> <td width="33%" align="center"> <img src="https://img.shields.io/badge/1-Testing-4ECDC4?style=for-the-badge&labelColor=1a1b27"/> <br><br> Test on diverse inputs <br> before deployment </td> <td width="33%" align="center"> <img src="https://img.shields.io/badge/2-Human_Oversight-A855F7?style=for-the-badge&labelColor=1a1b27"/> <br><br> Implement human-in-the-loop <br> for critical decisions </td> <td width="33%" align="center"> <img src="https://img.shields.io/badge/3-Regular_Audits-FFD93D?style=for-the-badge&labelColor=1a1b27"/> <br><br> Audit for unexpected <br> behaviors regularly </td> </tr> </table>  <img src="https://user-images.githubusercontent.com/73097560/115834477-dbab4500-a447-11eb-908a-139a6edaec5c.gif"> <br>

<img src="https://media.giphy.com/media/LnQjpWaON8nhr21vNW/giphy.gif" width="35"> Citation

📚 Academic & Research Use

If you use Lumichat Coder v2.1 in your research or applications, please cite:

</div> <br>

This Model:

@misc{lumichat-coder-v2.1,
  author = {Jha, Aditya Kumar and LumiChats},
  title = {Lumichat Coder v2.1: Advanced Function-Calling Language Model},
  year = {2025},
  publisher = {HuggingFace},
  howpublished = {\url{https://huggingface.co/lumichats/lumichat-coder-v2.1}},
}

<br>

Base Model (Qwen2.5-Coder):

@article{hui2024qwen2,
  title={Qwen2.5-Coder Technical Report},
  author={Hui, Binyuan and Yang, Jian and Cui, Zeyu and Yang, Jiaxi and Liu, Dayiheng and Zhang, Lei and Liu, Tianyu and Zhang, Jiajun and Yu, Bowen and Dang, Kai and others},
  journal={arXiv preprint arXiv:2409.12186},
  year={2024}
}

@article{qwen2,
  title={Qwen2 Technical Report}, 
  author={An Yang and Baosong Yang and Binyuan Hui and Bo Zheng and Bowen Yu and Chang Zhou and Chengpeng Li and Chengyuan Li and Dayiheng Liu and Fei Huang and Guanting Dong and Haoran Wei and Huan Lin and Jialong Tang and Jialin Wang and Jian Yang and Jianhong Tu and Jianwei Zhang and Jianxin Ma and Jin Xu and Jingren Zhou and Jinze Bai and Jinzheng He and Junyang Lin and Kai Dang and Keming Lu and Keqin Chen and Kexin Yang and Mei Li and Mingfeng Xue and Na Ni and Pei Zhang and Peng Wang and Ru Peng and Rui Men and Ruize Gao and Runji Lin and Shijie Wang and Shuai Bai and Sinan Tan and Tianhang Zhu and Tianhao Li and Tianyu Liu and Wenbin Ge and Xiaodong Deng and Xiaohuan Zhou and Xingzhang Ren and Xinyu Zhang and Xipin Wei and Xuancheng Ren and Yang Fan and Yang Yao and Yichang Zhang and Yu Wan and Yunfei Chu and Yuqiong Liu and Zeyu Cui and Zhenru Zhang and Zhihao Fan},
  journal={arXiv preprint arXiv:2407.10671},
  year={2024}
}

<img src="https://user-images.githubusercontent.com/73097560/115834477-dbab4500-a447-11eb-908a-139a6edaec5c.gif"> <br>

<img src="https://media.giphy.com/media/fwbZnTftCXVocKzfxR/giphy.gif" width="35"> License

⚖️ Apache 2.0 License

This model is released under the Apache 2.0 License, inherited from the Qwen2.5-Coder base model.

</div> <br>

Copyright 2025 LumiChats (Aditya Kumar Jha)

Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at

    http://www.apache.org/licenses/LICENSE-2.0

Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.

📜 What This Means for You

✅ You CAN:

<br>

<img src="https://img.shields.io/badge/💼-Commercial_Use-10B981?style=flat-square&labelColor=1a1b27"/> Use in commercial products

<img src="https://img.shields.io/badge/🔧-Modify-10B981?style=flat-square&labelColor=1a1b27"/> Modify and adapt the model

<img src="https://img.shields.io/badge/📤-Distribute-10B981?style=flat-square&labelColor=1a1b27"/> Share with others

<img src="https://img.shields.io/badge/🔒-Private_Use-10B981?style=flat-square&labelColor=1a1b27"/> Use privately

<img src="https://img.shields.io/badge/⚖️-Patent_Use-10B981?style=flat-square&labelColor=1a1b27"/> Grant of patent rights

</td> <td width="50%" align="center">

📋 You MUST:

<br>

<img src="https://img.shields.io/badge/📄-Include_License-FFD93D?style=flat-square&labelColor=1a1b27"/> Include license and copyright

<img src="https://img.shields.io/badge/📝-State_Changes-FFD93D?style=flat-square&labelColor=1a1b27"/> Document modifications made

<img src="https://img.shields.io/badge/📢-Include_NOTICE-FFD93D?style=flat-square&labelColor=1a1b27"/> Include NOTICE file if provided

<img src="https://img.shields.io/badge/⚠️-No_Trademark-EF4444?style=flat-square&labelColor=1a1b27"/> Can't use LumiChats trademarks

<img src="https://img.shields.io/badge/🛡️-No_Warranty-EF4444?style=flat-square&labelColor=1a1b27"/> Provided "as-is" without warranty

</td> </tr> </table> </div>  <img src="https://user-images.githubusercontent.com/73097560/115834477-dbab4500-a447-11eb-908a-139a6edaec5c.gif"> <br>

<img src="https://media.giphy.com/media/hvRJCLFzcasrR4ia7z/giphy.gif" width="35"> Acknowledgments

🙏 Built on the Shoulders of Giants

</div>

💝 Special Thanks

🌟 Core Technologies

For the exceptional Qwen2.5-Coder base model and groundbreaking research in code-specialized LLMs.

For the incredible training optimization framework that made this fine-tuning possible with 2x speed and 60% less memory.

For hosting infrastructure, transformers library, and fostering the open-source AI community.

</td> <td width="50%" valign="top">

🎯 Community Support

Early testers, feedback providers, and the amazing LumiChats community who helped shape this model.

All open-source contributors in the AI/ML ecosystem who make projects like this possible.

For inspiring us to make AI accessible and affordable for everyone.

</td> </tr> </table> <br>

🛠️ Built With

<div align="center"> <p> <a href="https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B"> <img src="https://img.shields.io/badge/Qwen2.5--Coder-Base_Model-FF6B35?style=for-the-badge&labelColor=1a1b27&logo=alibabacloud&logoColor=white"/> </a> <a href="https://github.com/unslothai/unsloth"> <img src="https://img.shields.io/badge/Unsloth-Fine--Tuning-00D9FF?style=for-the-badge&labelColor=1a1b27&logo=github&logoColor=white"/> </a> <a href="https://github.com/epfl-dlab/transformers-CFG"> <img src="https://img.shields.io/badge/transformers--CFG-Grammar-Constraints-10B981?style=for-the-badge&labelColor=1a1b27&logo=github&logoColor=white"/> </a> <a href="https://github.com/huggingface/transformers"> <img src="https://img.shields.io/badge/HF_Transformers-Framework-FFD21F?style=for-the-badge&labelColor=1a1b27&logo=huggingface&logoColor=white"/> </a> </p> <br> <table> <tr> <td align="center" width="25%"> <img src="https://skillicons.dev/icons?i=python&theme=dark" width="50"/> <br><br> <b>Python</b> <br> <sub>Core language</sub> </td> <td align="center" width="25%"> <img src="https://skillicons.dev/icons?i=pytorch&theme=dark" width="50"/> <br><br> <b>PyTorch</b> <br> <sub>Deep learning</sub> </td> <td align="center" width="25%"> <img src="https://cdn.jsdelivr.net/gh/devicons/devicon/icons/huggingface/huggingface-original.svg" width="50"/> <br><br> <b>Transformers</b> <br> <sub>Model framework</sub> </td> <td align="center" width="25%"> <img src="https://cdn.jsdelivr.net/gh/devicons/devicon/icons/fastapi/fastapi-original.svg" width="50"/> <br><br> <b>FastAPI</b> <br> <sub>API integration</sub> </td> </tr> </table> </div>  <img src="https://user-images.githubusercontent.com/73097560/115834477-dbab4500-a447-11eb-908a-139a6edaec5c.gif"> <br>

<img src="https://media.giphy.com/media/M9gbBd9nbDrOTu1Mqx/giphy.gif" width="35"> Contact & Support

💬 Get in Touch

</div>

🌐 LumiChats Resources

<div align="center"> <p> <a href="https://www.lumichats.com"> <img src="https://img.shields.io/badge/🌐_Website-Visit_LumiChats-FF6B35?style=for-the-badge&labelColor=1a1b27"/> </a> <a href="https://www.lumichats.com"> <img src="https://img.shields.io/badge/💬_Support-Get_Help-00D9FF?style=for-the-badge&labelColor=1a1b27"/> </a> <a href="mailto:[email protected]"> <img src="https://img.shields.io/badge/📧_Email-Contact_Us-10B981?style=for-the-badge&labelColor=1a1b27"/> </a> </p> <br> <table> <tr> <td align="center" width="33%"> <img src="https://media.giphy.com/media/26tn33aiTi1jkl6H6/giphy.gif" width="80"/> <br><br> <img src="https://img.shields.io/badge/🐛-Report_Issues-EF4444?style=for-the-badge&labelColor=1a1b27"/> <br><br> Use the model card <br> discussion tab for <br> bug reports & feedback </td> <td align="center" width="33%"> <img src="https://media.giphy.com/media/3oKIPnAiaMCws8nOsE/giphy.gif" width="80"/> <br><br> <img src="https://img.shields.io/badge/💡-Feature_Requests-FFD93D?style=for-the-badge&labelColor=1a1b27"/> <br><br> Share your ideas for <br> improvements and <br> new capabilities </td> <td align="center" width="33%"> <img src="https://media.giphy.com/media/l0HlDHQEiIdY3kxlm/giphy.gif" width="80"/> <br><br> <img src="https://img.shields.io/badge/📚-Documentation-4ECDC4?style=for-the-badge&labelColor=1a1b27"/> <br><br> Check this README <br> for comprehensive <br> usage guides </td> </tr> </table> <br>

👨‍💻 About the Founder

Aditya Kumar Jha

<br>

Founder of LumiChats • Passionate about democratizing AI access

Mission: Make premium AI accessible to students, developers, and creators worldwide—without subscription fatigue or wasted money. Pay only when your brain needs a boost. 🧠

</div>  <img src="https://user-images.githubusercontent.com/73097560/115834477-dbab4500-a447-11eb-908a-139a6edaec5c.gif"> <br>

<img src="https://media.giphy.com/media/iY8CRBdQXODJSCERIr/giphy.gif" width="35"> Model Card Information

📋 Technical Summary

<br> <table> <tr> <th>Attribute</th> <th>Value</th> </tr> <tr> <td><b>Developed by</b></td> <td>Aditya Kumar Jha / LumiChats</td> </tr> <tr> <td><b>Model type</b></td> <td>Causal Language Model (Function Calling Specialist)</td> </tr> <tr> <td><b>Language(s)</b></td> <td>English (primary)</td> </tr> <tr> <td><b>License</b></td> <td>Apache 2.0</td> </tr> <tr> <td><b>Fine-tuned from</b></td> <td><a href="https://huggingface.co/unsloth/Qwen2.5-Coder-1.5B-Instruct">unsloth/Qwen2.5-Coder-1.5B-Instruct</a></td> </tr> <tr> <td><b>Model size</b></td> <td>1.54B parameters (1.31B non-embedding)</td> </tr> <tr> <td><b>Context length</b></td> <td>32,768 tokens</td> </tr> <tr> <td><b>Architecture</b></td> <td>Transformer (GQA, RoPE, SwiGLU, RMSNorm)</td> </tr> <tr> <td><b>Training framework</b></td> <td>Unsloth (2x faster, 60% less VRAM)</td> </tr> <tr> <td><b>Specialization</b></td> <td>Function calling, tool use, JSON generation</td> </tr> </table> </div>  <img src="https://user-images.githubusercontent.com/73097560/115834477-dbab4500-a447-11eb-908a-139a6edaec5c.gif"> <br>

<img src="https://media.giphy.com/media/j2pOGeGYKe2xCCKwfi/giphy.gif" width="35"> Quick Links

🔗 Essential Resources

<br> <table> <tr> <td align="center" width="25%"> <a href="https://www.lumichats.com"> <img src="https://media.giphy.com/media/26tn33aiTi1jkl6H6/giphy.gif" width="60"/> </a> <br><br> <a href="https://www.lumichats.com"> <img src="https://img.shields.io/badge/LumiChats-Platform-FF6B35?style=for-the-badge&labelColor=1a1b27"/> </a> <br> <sub>Premium AI at ₹39/day</sub> </td> <td align="center" width="25%"> <a href="https://huggingface.co/lumichats/lumichat-coder-v2.1"> <img src="https://media.giphy.com/media/3oKIPnAiaMCws8nOsE/giphy.gif" width="60"/> </a> <br><br> <a href="https://huggingface.co/lumichats/lumichat-coder-v2.1"> <img src="https://img.shields.io/badge/Model_Card-HuggingFace-FFD21F?style=for-the-badge&labelColor=1a1b27"/> </a> <br> <sub>Download & documentation</sub> </td> <td align="center" width="25%"> <a href="https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B"> <img src="https://media.giphy.com/media/l0HlBO7eyXzSZkJri/giphy.gif" width="60"/> </a> <br><br> <a href="https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B"> <img src="https://img.shields.io/badge/Base_Model-Qwen2.5-00D9FF?style=for-the-badge&labelColor=1a1b27"/> </a> <br> <sub>Original foundation</sub> </td> <td align="center" width="25%"> <a href="https://github.com/unslothai/unsloth"> <img src="https://media.giphy.com/media/l0HlDHQEiIdY3kxlm/giphy.gif" width="60"/> </a> <br><br> <a href="https://github.com/unslothai/unsloth"> <img src="https://img.shields.io/badge/Unsloth-Framework-10B981?style=for-the-badge&labelColor=1a1b27"/> </a> <br> <sub>Optimization toolkit</sub> </td> </tr> </table> </div>  <img src="https://user-images.githubusercontent.com/73097560/115834477-dbab4500-a447-11eb-908a-139a6edaec5c.gif"> <br>

<img src="https://media.giphy.com/media/WUlplcMpOCEmTGBtBW/giphy.gif" width="35"> Why Choose Lumichat Coder?

🎯 The Function-Calling Specialist

<br> <table> <tr> <td width="50%" align="center"> <img src="https://media.giphy.com/media/l0HlBO7eyXzSZkJri/giphy.gif" width="150"/> <br><br> <img src="https://img.shields.io/badge/✅-Precision_Engineering-10B981?style=for-the-badge&labelColor=1a1b27"/> <br><br> <h3>Built for Production</h3> <br> Not a general-purpose model trying to do everything. <br><br> <b>Specifically engineered for tool calling</b> <br> with 96.5% accuracy and 99.8% JSON validity. <br><br> Deploy with confidence in customer-facing applications. </td> <td width="50%" align="center"> <img src="https://media.giphy.com/media/67ThRZlYBvibtdF9JH/giphy.gif" width="150"/> <br><br> <img src="https://img.shields.io/badge/⚡-Unsloth_Optimized-FFD93D?style=for-the-badge&labelColor=1a1b27"/> <br><br> <h3>Fast & Efficient</h3> <br> 2x faster inference than standard fine-tuning. <br><br> <b>60% less memory consumption</b> <br> means deploy on consumer GPUs. <br><br> No enterprise hardware budgets required. </td> </tr> <tr> <td width="50%" align="center"> <img src="https://media.giphy.com/media/3oKIPnAiaMCws8nOsE/giphy.gif" width="150"/> <br><br> <img src="https://img.shields.io/badge/🎓-Accessible_to_All-FF6B35?style=for-the-badge&labelColor=1a1b27"/> <br><br> <h3>Student & Developer Friendly</h3> <br> From LumiChats, the platform that saves students <br> ₹1,200-2,600 monthly on AI costs. <br><br> <b>Open source, Apache 2.0 licensed</b> <br> Free to use, modify, and commercialize. </td> <td width="50%" align="center"> <img src="https://media.giphy.com/media/qgQUggAC3Pfv687qPC/giphy.gif" width="150"/> <br><br> <img src="https://img.shields.io/badge/🔒-Guaranteed_Valid_JSON-00D9FF?style=for-the-badge&labelColor=1a1b27"/> <br><br> <h3>Grammar-Constrained Generation</h3> <br> Uses transformers-CFG for guaranteed output. <br><br> <b>No more parsing errors or malformed JSON.</b> <br> 99.8% validity rate in production. <br><br> Reliable automation you can trust. </td> </tr> </table> </div>  <img src="https://user-images.githubusercontent.com/73097560/115834477-dbab4500-a447-11eb-908a-139a6edaec5c.gif"> <br>

<img src="https://media.giphy.com/media/hvRJCLFzcasrR4ia7z/giphy.gif" width="35"> Technical Specifications

🔧 Built on Cutting-Edge Architecture

📊 Model Architecture

🏗️ Foundation

Base Model: unsloth/Qwen2.5-Coder-1.5B-Instruct
Model Type: Causal Language Model (Decoder-only)
Architecture: Transformer with RoPE, SwiGLU, RMSNorm
Attention: Grouped Query Attention (GQA)

📈 Scale

Total Parameters: 1.54B
Non-Embedding: 1.31B
Layers: 28
Hidden Size: 1,536

</td> <td width="50%">

🎯 Capacity

Attention Heads (Q): 12
Attention Heads (KV): 2
Context Length: 32,768 tokens
Vocabulary Size: 151,936

⚙️ Components

✅ Rotary Position Embeddings (RoPE)
✅ SwiGLU Activation
✅ RMS Normalization
✅ QKV Attention Bias
✅ Tied Word Embeddings

</td> </tr> </table> <br>

💾 Supported Formats

<table> <tr> <td width="33%" align="center"> <img src="https://img.shields.io/badge/Safetensors-Recommended-4ECDC4?style=for-the-badge&labelColor=1a1b27&logo=rust&logoColor=white"/> <br> <sub>Fast, safe model loading</sub> </td> <td width="33%" align="center"> <img src="https://img.shields.io/badge/PyTorch-Supported-EE4C2C?style=for-the-badge&labelColor=1a1b27&logo=pytorch&logoColor=white"/> <br> <sub>Native framework support</sub> </td> <td width="33%" align="center"> <img src="https://img.shields.io/badge/Precision-BF16_|_FP16_|_INT8_|_INT4-FFD93D?style=for-the-badge&labelColor=1a1b27&logo=nvidia&logoColor=white"/> <br> <sub>Flexible deployment</sub> </td> </tr> </table> <br>

🔌 Inference Engines

<img src="https://media.giphy.com/media/LnQjpWaON8nhr21vNW/giphy.gif" width="35"> Usage

💻 Get Started in Minutes

📦 Installation

pip install torch transformers accelerate unsloth transformers-cfg

<br>

🚀 Basic Inference

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
import json

# Load model and tokenizer
model_name = "lumichats/lumichat-coder-v2.1"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

# Define your available tools
tools = [
    {
        "name": "get_vector_sum",
        "description": "Calculate the sum of two vectors",
        "parameters": {
            "type": "object",
            "properties": {
                "a": {"type": "array", "items": {"type": "number"}},
                "b": {"type": "array", "items": {"type": "number"}}
            },
            "required": ["a", "b"]
        }
    }
]

# Create prompt
user_query = "Find the sum of a = [1, -1, 2] and b = [3, 0, -4]"
prompt = f"""Available tools:
{json.dumps(tools, indent=2)}

User query: {user_query}

Generate the appropriate tool call in JSON format. Only output valid JSON.
"""

# Generate
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(
    **inputs,
    max_new_tokens=256,
    temperature=0.1,
    do_sample=True
)

# Decode and parse
result = tokenizer.decode(outputs[0], skip_special_tokens=True)
# Extract the JSON part (remove the prompt)
json_str = result.split("Generate the appropriate tool call in JSON format. Only output valid JSON.")[-1].strip()
tool_call = json.loads(json_str)

print(json.dumps(tool_call, indent=2))

<br>

🎯 Grammar-Constrained Decoding

from transformers_cfg.grammar_utils import IncrementalGrammarConstraint
from transformers_cfg.generation.logits_process import GrammarConstrainedLogitsProcessor

# Define JSON schema grammar
json_grammar = """
root ::= array
array ::= "[" ws object (ws "," ws object)* ws "]"
object ::= "{" ws "\"name\"" ws ":" ws string ws "," ws "\"arguments\"" ws ":" ws dict ws "}"
dict ::= "{" ws (string ws ":" ws value (ws "," ws string ws ":" ws value)*)? ws "}"
value ::= string | number | array | dict | "true" | "false" | "null"
string ::= "\"" [^"]* "\""
number ::= "-"? [0-9]+ ("." [0-9]+)?
ws ::= [ \t\n\r]*
"""

# Create grammar constraint
grammar = IncrementalGrammarConstraint(json_grammar, "root", tokenizer)
grammar_processor = GrammarConstrainedLogitsProcessor(grammar)

# Generate with constraint
outputs = model.generate(
    **inputs,
    max_new_tokens=256,
    logits_processor=[grammar_processor],
    temperature=0.1
)

<br>

🌐 FastAPI Integration

from fastapi import FastAPI
from pydantic import BaseModel
import json

app = FastAPI()

class ToolCallRequest(BaseModel):
    query: str
    tools: list

@app.post("/tool-call")
async def generate_tool_call(request: ToolCallRequest):
    prompt = f"""Available tools:
{json.dumps(request.tools, indent=2)}

User query: {request.query}

Generate the appropriate tool call in JSON format.
"""
    
    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
    outputs = model.generate(**inputs, max_new_tokens=256, temperature=0.1)
    
    result = tokenizer.decode(outputs[0], skip_special_tokens=True)
    json_str = result.split("Generate the appropriate tool call in JSON format.")[-1].strip()
    tool_call = json.loads(json_str)
    
    return {"tool_call": tool_call}

<br>

⚙️ Advanced: Streaming Responses

from transformers import TextIteratorStreamer
from threading import Thread

streamer = TextIteratorStreamer(tokenizer, skip_special_tokens=True)

generation_kwargs = dict(
    inputs=inputs,
    streamer=streamer,
    max_new_tokens=256,
    temperature=0.1
)

thread = Thread(target=model.generate, kwargs=generation_kwargs)
thread.start()

for new_text in streamer:
    print(new_text, end="", flush=True)

thread.join()

<img src="https://user-images.githubusercontent.com/73097560/115834477-dbab4500-a447-11eb-908a-139a6edaec5c.gif"> <br>

<img src="https://media.giphy.com/media/hvRJCLFzcasrR4ia7z/giphy.gif" width="35"> Examples

🎯 Real-World Use Cases

1️⃣ Mathematical Operations

📝 Query:

Calculate the dot product of 
vectors [2, 3, 1] and [4, -1, 2]

</td> <td width="50%">

🤖 Output:

[
  {
    "name": "calculate_dot_product",
    "arguments": {
      "vector_a": [2, 3, 1],
      "vector_b": [4, -1, 2]
    }
  }
]

</td> </tr> </table> <br>

2️⃣ Data Processing

📝 Query:

Filter the list [1, 5, 12, 8, 3, 15] 
to keep only numbers greater than 7

</td> <td width="50%">

🤖 Output:

[
  {
    "name": "filter_list",
    "arguments": {
      "data": [1, 5, 12, 8, 3, 15],
      "condition": "greater_than",
      "threshold": 7
    }
  }
]

</td> </tr> </table> <br>

3️⃣ Email Automation

📝 Query:

Send an email to [email protected] 
with subject 'Meeting Reminder' 
and body 'Don't forget our 
meeting at 3 PM'

</td> <td width="50%">

🤖 Output:

[
  {
    "name": "send_email",
    "arguments": {
      "recipient": "[email protected]",
      "subject": "Meeting Reminder",
      "body": "Don't forget our meeting at 3 PM"
    }
  }
]

</td> </tr> </table> <br>

4️⃣ Database Queries

📝 Query:

Find all users in the database 
who registered after January 1, 2024 
and are from India

</td> <td width="50%">

🤖 Output:

[
  {
    "name": "query_database",
    "arguments": {
      "table": "users",
      "filters": {
        "registration_date": {
          "operator": "greater_than",
          "value": "2024-01-01"
        },
        "country": {
          "operator": "equals",
          "value": "India"
        }
      }
    }
  }
]

</td> </tr> </table>  <img src="https://user-images.githubusercontent.com/73097560/115834477-dbab4500-a447-11eb-908a-139a6edaec5c.gif"> <br>

<img src="https://media.giphy.com/media/WUlplcMpOCEmTGBtBW/giphy.gif" width="35"> Ready to Build?

🚀 Start Building AI Agents Today

<br>

Precision tool calling • 99.8% JSON validity • 32K context • Apache 2.0 licensed

<p> <a href="https://huggingface.co/lumichats/lumichat-coder-v2.1"> <img src="https://img.shields.io/badge/📥_DOWNLOAD_MODEL-HuggingFace-FFD21F?style=for-the-badge&labelColor=1a1b27&fontSize=20" alt="Download Model" height="50"/> </a> <a href="https://www.lumichats.com"> <img src="https://img.shields.io/badge/🚀_TRY_LUMICHATS-Start_Free-FF6B35?style=for-the-badge&labelColor=1a1b27&fontSize=20" alt="Try LumiChats" height="50"/> </a> </p> <br> <table> <tr> <td align="center" width="33%"> <img src="https://img.shields.io/badge/1.5B-Parameters-00D9FF?style=for-the-badge&labelColor=1a1b27"/> <br> <sub>Efficient deployment</sub> </td> <td align="center" width="33%"> <img src="https://img.shields.io/badge/32K-Context-10B981?style=for-the-badge&labelColor=1a1b27"/> <br> <sub>Extended conversations</sub> </td> <td align="center" width="33%"> <img src="https://img.shields.io/badge/Apache_2.0-Free-A855F7?style=for-the-badge&labelColor=1a1b27"/> <br> <sub>Commercial use allowed</sub> </td> </tr> </table> <br>

<br>

💡 Perfect For

<table> <tr> <td align="center" width="25%"> <img src="https://media.giphy.com/media/4H3Ii5eLChYul9p7NL/giphy.gif" width="60"/> <br><br> <b>🤖 AI Agents</b> <br> <sub>Autonomous systems</sub> <br> <sub>that interact with tools</sub> </td> <td align="center" width="25%"> <img src="https://media.giphy.com/media/qgQUggAC3Pfv687qPC/giphy.gif" width="60"/> <br><br> <b>⚙️ Automation</b> <br> <sub>Workflow orchestration</sub> <br> <sub>& data processing</sub> </td> <td align="center" width="25%"> <img src="https://media.giphy.com/media/3oKIPnAiaMCws8nOsE/giphy.gif" width="60"/> <br><br> <b>🔌 API Integration</b> <br> <sub>Natural language</sub> <br> <sub>to API calls</sub> </td> <td align="center" width="25%"> <img src="https://media.giphy.com/media/l0HlDHQEiIdY3kxlm/giphy.gif" width="60"/> <br><br> <b>💬 Chat Interfaces</b> <br> <sub>Conversational UIs</sub> <br> <sub>with actions</sub> </td> </tr> </table> <br>

🌟 Join the Community

⭐ Star this model if you believe in accessible AI!

<br>

Developed by Aditya Kumar Jha

<p> <a href="https://www.lumichats.com"> <img src="https://img.shields.io/badge/🌐-lumichats.com-FF6B35?style=flat-square&labelColor=1a1b27"/> </a> <a href="mailto:[email protected]"> <img src="https://img.shields.io/badge/📧-Contact-00D9FF?style=flat-square&labelColor=1a1b27"/> </a> <a href="https://github.com/adityajhakumar"> <img src="https://img.shields.io/badge/💻-GitHub-181717?style=flat-square&labelColor=1a1b27"/> </a> </p> </div> ```

Task: Text Generation
Library: transformers
Type: qwen2
License: apache-2.0
Languages: en
Created: Jan 24, 2026
Updated: Jan 24, 2026