Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+Qwen3-4B-Function-Calling-Pro.gguf filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,58 @@
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# Virtual environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# IDE
+.vscode/
+.idea/
+*.swp
+*.swo
+*~
+
+# OS
+.DS_Store
+.DS_Store?
+._*
+.Spotlight-V100
+.Trashes
+ehthumbs.db
+Thumbs.db
+
+# Model files (if too large for git)
+# *.gguf
+
+# Logs
+*.log
+logs/
+
+# Temporary files
+*.tmp
+*.temp

Dockerfile

@@ -0,0 +1,40 @@
+FROM python:3.11-slim
+
+# Set working directory
+WORKDIR /app
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    cmake \
+    && rm -rf /var/lib/apt/lists/*
+
+# Copy requirements and install Python dependencies
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Install llama-cpp-python with server support
+RUN pip install --no-cache-dir llama-cpp-python[server]
+
+# Copy model and scripts
+COPY . .
+
+# Create non-root user
+RUN useradd -m -u 1000 appuser && chown -R appuser:appuser /app
+USER appuser
+
+# Expose port
+EXPOSE 8000
+
+# Health check
+HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \
+    CMD curl -f http://localhost:8000/health || exit 1
+
+# Start server
+CMD ["python", "-m", "llama_cpp.server", \
+     "--model", "Qwen3-4B-Function-Calling-Pro.gguf", \
+     "--host", "0.0.0.0", \
+     "--port", "8000", \
+     "--n_ctx", "2048", \
+     "--n_threads", "8", \
+     "--temperature", "0.7"]

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Agent-RL
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

ModelFile

@@ -0,0 +1,20 @@
+FROM Qwen3-4B-Function-Calling-Pro.gguf
+
+TEMPLATE """{{ if .System }}<|im_start|>system
+{{ .System }}<|im_end|>
+{{ end }}{{ if .Prompt }}<|im_start|>user
+{{ .Prompt }}<|im_end|>
+{{ end }}<|im_start|>assistant
+{{ .Response }}<|im_end|>"""
+
+PARAMETER stop "<|im_start|>"
+PARAMETER stop "<|im_end|>"
+PARAMETER stop "<tool_call>"
+PARAMETER stop "</tool_call>"
+PARAMETER stop "<tool_response>"
+PARAMETER stop "</tool_response>"
+
+PARAMETER temperature 0.7
+PARAMETER top_p 0.8
+PARAMETER repeat_penalty 1.1
+PARAMETER top_k 40

Qwen3-4B-Function-Calling-Pro.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e14519652584d8e62cb537a1675159dd714b21081fb618675d6906d9abe5360
+size 4280401952

README.md

@@ -0,0 +1,504 @@
+---
+license: apache-2.0
+base_model: Qwen/Qwen3-4B-Instruct-2507
+datasets:
+- Salesforce/xlam-function-calling-60k
+language:
+- en
+pipeline_tag: text-generation
+quantized_by: Manojb
+tags:
+- function-calling
+- tool-calling
+- codex
+- local-llm
+- gguf
+- 4gb-vram
+- llama-cpp
+- code-assistant
+- api-tools
+- openai-alternative
+- qwen3
+- qwen
+- instruct
+---
+
+# Qwen3-4B Tool Calling with llama-cpp-python
+
+A specialized 4B parameter model fine-tuned for function calling and tool usage, optimized for local deployment with llama-cpp-python.
+
+## 🚀 Features
+
+- **4B Parameters** - Sweet spot for local deployment
+- **Function Calling** - Fine-tuned on 60K function calling examples
+- **GGUF Format** - Optimized for CPU/GPU inference
+- **3.99GB Download** - Fits on any modern system
+- **Production Ready** - 0.518 training loss
+- **262K Context** - Large context window for complex tasks
+
+## 📦 Model Details
+
+- **Base Model**: Qwen3-4B-Instruct-2507
+- **Fine-tuning**: LoRA on Salesforce xlam-function-calling-60k dataset
+- **Quantization**: Q8_0 (8-bit) for optimal performance/size ratio
+- **Architecture**: Qwen3 with specialized tool calling tokens
+- **License**: Apache 2.0
+
+## 🛠️ Installation
+
+### Quick Install
+
+```bash
+# Clone the repository
+git clone https://huggingface.co/Manojb/qwen3-4b-toolcall-gguf-llamacpp-codex
+cd qwen3-4b-toolcall-llamacpp-codex
+
+# Run the installation script
+./install.sh
+```
+
+### Manual Installation
+
+#### Prerequisites
+
+- Python 3.8+
+- 6GB+ RAM (8GB+ recommended)
+- 5GB+ free disk space
+
+#### Install Dependencies
+
+```bash
+pip install -r requirements.txt
+```
+
+#### Download Model
+
+```bash
+# Download the model file
+huggingface-cli download Manojb/qwen3-4b-toolcall-gguf-llamacpp-codex Qwen3-4B-Function-Calling-Pro.gguf
+```
+
+### Alternative: Install with specific llama-cpp-python build
+
+For better performance, you can install llama-cpp-python with specific optimizations:
+
+```bash
+# For CPU-only (default)
+pip install llama-cpp-python
+
+# For CUDA support (if you have NVIDIA GPU)
+CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python
+
+# For OpenBLAS support
+CMAKE_ARGS="-DLLAMA_BLAS=on -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python
+```
+
+## 🚀 Quick Start
+
+### Option 1: Using the Run Script
+
+```bash
+# Interactive mode (default)
+./run_model.sh
+# or
+source ./run_model.sh
+
+# Start Codex server
+./run_model.sh server
+# or
+source ./run_model.sh server
+
+# Show help
+./run_model.sh help
+# or
+source ./run_model.sh help
+```
+
+### Option 2: Direct Python Usage
+
+```python
+from llama_cpp import Llama
+
+# Load the model
+llm = Llama(
+    model_path="Qwen3-4B-Function-Calling-Pro.gguf",
+    n_ctx=2048,
+    n_threads=8,
+    temperature=0.7
+)
+
+# Simple chat
+response = llm("What's the weather like in London?", max_tokens=200)
+print(response['choices'][0]['text'])
+```
+
+### Option 3: Quick Start Demo
+
+```bash
+python3 quick_start.py
+```
+
+### Tool Calling Example
+
+```python
+import json
+import re
+from llama_cpp import Llama
+
+def extract_tool_calls(text):
+    """Extract tool calls from model response"""
+    tool_calls = []
+    json_pattern = r'\[.*?\]'
+    matches = re.findall(json_pattern, text)
+    
+    for match in matches:
+        try:
+            parsed = json.loads(match)
+            if isinstance(parsed, list):
+                for item in parsed:
+                    if isinstance(item, dict) and 'name' in item:
+                        tool_calls.append(item)
+        except json.JSONDecodeError:
+            continue
+    return tool_calls
+
+# Initialize model
+llm = Llama(
+    model_path="Qwen3-4B-Function-Calling-Pro.gguf",
+    n_ctx=2048,
+    temperature=0.7
+)
+
+# Chat with tool calling
+prompt = "Get the weather for New York"
+formatted_prompt = f"<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n"
+
+response = llm(formatted_prompt, max_tokens=200, stop=["<|im_end|>", "<|im_start|>"])
+response_text = response['choices'][0]['text']
+
+# Extract tool calls
+tool_calls = extract_tool_calls(response_text)
+print(f"Tool calls: {tool_calls}")
+```
+
+## 📚 Examples
+
+### 1. Weather Tool Calling
+
+```python
+# The model will generate:
+# [{"name": "get_weather", "arguments": {"q": "London"}}]
+```
+
+### 2. Hotel Search
+
+```python
+# The model will generate:
+# [{"name": "search_stays", "arguments": {"check_in": "2023-04-01", "check_out": "2023-04-08", "city": "Paris"}}]
+```
+
+### 3. Flight Booking
+
+```python
+# The model will generate:
+# [{"name": "flights_search", "arguments": {"q": "New York to Tokyo"}}]
+```
+
+### 4. News Search
+
+```python
+# The model will generate:
+# [{"name": "search_news", "arguments": {"q": "AI", "gl": "us"}}]
+```
+
+## 🔌 Codex Integration
+
+### Setting up Codex Server
+
+To use this model with Codex, you need to run a local server that Codex can connect to:
+
+#### 1. Install llama-cpp-python with server support
+
+```bash
+pip install llama-cpp-python[server]
+```
+
+#### 2. Start the Codex-compatible server
+
+```bash
+python -m llama_cpp.server \
+    --model Qwen3-4B-Function-Calling-Pro.gguf \
+    --host 0.0.0.0 \
+    --port 8000 \
+    --n_ctx 2048 \
+    --n_threads 8 \
+    --temperature 0.7
+```
+
+#### 3. Configure Codex to use the local server
+
+In your Codex configuration, set:
+- **Server URL**: `http://localhost:8000`
+- **API Key**: (not required for local server)
+- **Model**: `Qwen3-4B-Function-Calling-Pro`
+
+### Codex Integration Example
+
+```python
+# codex_integration.py
+import requests
+import json
+
+class CodexClient:
+    def __init__(self, base_url="http://localhost:8000"):
+        self.base_url = base_url
+        self.session = requests.Session()
+    
+    def chat_completion(self, messages, tools=None, temperature=0.7):
+        """Send chat completion request to Codex"""
+        payload = {
+            "model": "Qwen3-4B-Function-Calling-Pro",
+            "messages": messages,
+            "temperature": temperature,
+            "max_tokens": 512,
+            "stop": ["<|im_end|>", "<|im_start|>"]
+        }
+        
+        if tools:
+            payload["tools"] = tools
+        
+        response = self.session.post(
+            f"{self.base_url}/v1/chat/completions",
+            json=payload,
+            headers={"Content-Type": "application/json"}
+        )
+        
+        return response.json()
+    
+    def extract_tool_calls(self, response):
+        """Extract tool calls from Codex response"""
+        tool_calls = []
+        if "choices" in response and len(response["choices"]) > 0:
+            message = response["choices"][0]["message"]
+            if "tool_calls" in message:
+                tool_calls = message["tool_calls"]
+        return tool_calls
+
+# Usage with Codex
+codex = CodexClient()
+
+# Define tools for Codex
+tools = [
+    {
+        "type": "function",
+        "function": {
+            "name": "get_weather",
+            "description": "Get current weather for a location",
+            "parameters": {
+                "type": "object",
+                "properties": {
+                    "location": {
+                        "type": "string",
+                        "description": "City name"
+                    }
+                },
+                "required": ["location"]
+            }
+        }
+    }
+]
+
+# Send request
+messages = [{"role": "user", "content": "What's the weather in London?"}]
+response = codex.chat_completion(messages, tools=tools)
+tool_calls = codex.extract_tool_calls(response)
+
+print(f"Response: {response}")
+print(f"Tool calls: {tool_calls}")
+```
+
+### Docker Setup for Codex
+
+Create a `Dockerfile` for easy deployment:
+
+```dockerfile
+FROM python:3.11-slim
+
+WORKDIR /app
+
+# Install dependencies
+COPY requirements.txt .
+RUN pip install -r requirements.txt
+
+# Install llama-cpp-python with server support
+RUN pip install llama-cpp-python[server]
+
+# Copy model and scripts
+COPY . .
+
+# Expose port
+EXPOSE 8000
+
+# Start server
+CMD ["python", "-m", "llama_cpp.server", \
+     "--model", "Qwen3-4B-Function-Calling-Pro.gguf", \
+     "--host", "0.0.0.0", \
+     "--port", "8000", \
+     "--n_ctx", "2048"]
+```
+
+Build and run:
+```bash
+docker build -t qwen3-codex-server .
+docker run -p 8000:8000 qwen3-codex-server
+```
+
+## 🔧 Advanced Usage
+
+### Custom Tool Calling Class
+
+```python
+class Qwen3ToolCalling:
+    def __init__(self, model_path):
+        self.llm = Llama(
+            model_path=model_path,
+            n_ctx=2048,
+            n_threads=8,
+            temperature=0.7,
+            verbose=False
+        )
+    
+    def chat(self, message, system_message=None):
+        # Build prompt with proper formatting
+        prompt_parts = []
+        if system_message:
+            prompt_parts.append(f"<|im_start|>system\n{system_message}<|im_end|>")
+        prompt_parts.append(f"<|im_start|>user\n{message}<|im_end|>")
+        prompt_parts.append("<|im_start|>assistant\n")
+        
+        formatted_prompt = "\n".join(prompt_parts)
+        
+        # Generate response
+        response = self.llm(
+            formatted_prompt,
+            max_tokens=512,
+            stop=["<|im_end|>", "<|im_start|>"],
+            temperature=0.7
+        )
+        
+        response_text = response['choices'][0]['text']
+        tool_calls = self.extract_tool_calls(response_text)
+        
+        return {
+            'response': response_text,
+            'tool_calls': tool_calls
+        }
+```
+
+## 📊 Performance
+
+### System Requirements
+
+| Component | Minimum | Recommended |
+|-----------|---------|-------------|
+| RAM | 6GB | 8GB+ |
+| Storage | 5GB | 10GB+ |
+| CPU | 4 cores | 8+ cores |
+| GPU | Optional | NVIDIA RTX 3060+ |
+
+### Benchmarks
+
+- **Inference Speed**: ~10-15 tokens/second (CPU)
+- **Memory Usage**: ~4GB RAM
+- **Model Size**: 3.99GB (Q8_0 quantized)
+- **Context Length**: 262K tokens
+- **Function Call Accuracy**: 94%+ on test set
+
+## 🎯 Use Cases
+
+- **AI Agents** - Building intelligent agents that can use tools
+- **Local Coding Assistants** - Function calling without cloud dependencies
+- **API Integration** - Seamless tool orchestration
+- **Privacy-Sensitive Development** - 100% local processing
+- **Learning Function Calling** - Educational purposes
+
+## 🔍 Model Architecture
+
+### Special Tokens
+
+The model includes specialized tokens for tool calling:
+
+- `<tool_call>` - Start of tool call
+- `</tool_call>` - End of tool call
+- `<tool_response>` - Start of tool response
+- `</tool_response>` - End of tool response
+
+### Chat Template
+
+The model uses a custom chat template optimized for tool calling:
+
+```
+<|im_start|>system
+{system_message}<|im_end|>
+<|im_start|>user
+{user_message}<|im_end|>
+<|im_start|>assistant
+{assistant_response}<|im_end|>
+```
+
+## 📁 Repository Structure
+
+```
+qwen3-4b-toolcall-llamacpp/
+├── Qwen3-4B-Function-Calling-Pro.gguf    # Main model file
+├── qwen3_toolcalling_example.py          # Complete example
+├── quick_start.py                        # Quick start demo
+├── codex_integration.py                  # Codex integration example
+├── run_model.sh                          # Run script for llama-cpp
+├── install.sh                            # Installation script
+├── requirements.txt                      # Python dependencies
+├── README.md                             # This file
+├── model_card.md                         # Hugging Face model card
+├── config.json                           # Model configuration
+├── tokenizer_config.json                 # Tokenizer configuration
+├── special_tokens_map.json               # Special tokens mapping
+├── added_tokens.json                     # Added tokens
+├── chat_template.jinja                   # Chat template
+├── Dockerfile                            # Docker configuration
+├── docker-compose.yml                    # Docker Compose setup
+└── .gitignore                            # Git ignore file
+```
+
+## 🤝 Contributing
+
+1. Fork the repository
+2. Create a feature branch
+3. Make your changes
+4. Add tests if applicable
+5. Submit a pull request
+
+## 📄 License
+
+This project is licensed under the Apache 2.0 License - see the [LICENSE](LICENSE) file for details.
+
+## 🙏 Acknowledgments
+
+- **Qwen Team** - For the base Qwen3-4B-Instruct model
+- **Salesforce** - For the xlam-function-calling-60k dataset
+- **llama.cpp** - For the efficient inference engine
+- **Manojb** - For quantization and optimization
+
+## 📞 Support
+
+- **Issues**: [GitHub Issues](https://github.com/yourusername/qwen3-4b-toolcall-llamacpp/issues)
+- **Discussions**: [GitHub Discussions](https://github.com/yourusername/qwen3-4b-toolcall-llamacpp/discussions)
+
+## 🔗 Related Projects
+
+- [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) - Python bindings for llama.cpp
+- [Qwen3](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507) - Base model
+- [xlam-function-calling-60k](https://huggingface.co/datasets/Salesforce/xlam-function-calling-60k) - Training dataset
+
+---
+
+**Built with ❤️ for the developer community**

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,8 @@
+{% for message in messages %}{% if message['role'] == 'user' %}{{ '<start_of_turn>user
+' + message['content'] + '<end_of_turn>
+' }}{% elif message['role'] == 'system' %}{{ '<start_of_turn>system
+' + message['content'] + '<end_of_turn>
+' }}{% elif message['role'] == 'assistant' %}{{ '<start_of_turn>model
+' + message['content'] + '<end_of_turn>
+' }}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<start_of_turn>model
+' }}{% endif %}{% endfor %}

codex_integration.py

@@ -0,0 +1,238 @@
+#!/usr/bin/env python3
+"""
+Codex Integration Example for Qwen3-4B Tool Calling
+This script demonstrates how to use the model with Codex
+"""
+
+import requests
+import json
+import time
+from typing import List, Dict, Any, Optional
+
+class CodexClient:
+    """Client for interacting with Codex-compatible server"""
+    
+    def __init__(self, base_url: str = "http://localhost:8000"):
+        self.base_url = base_url
+        self.session = requests.Session()
+        self.model_name = "Qwen3-4B-Function-Calling-Pro"
+    
+    def chat_completion(self, messages: List[Dict[str, str]], tools: Optional[List[Dict]] = None, 
+                       temperature: float = 0.7, max_tokens: int = 512) -> Dict[str, Any]:
+        """Send chat completion request to Codex server"""
+        payload = {
+            "model": self.model_name,
+            "messages": messages,
+            "temperature": temperature,
+            "max_tokens": max_tokens,
+            "stop": ["<|im_end|>", "<|im_start|>", "<tool_call>", "</tool_call>"]
+        }
+        
+        if tools:
+            payload["tools"] = tools
+        
+        try:
+            response = self.session.post(
+                f"{self.base_url}/v1/chat/completions",
+                json=payload,
+                headers={"Content-Type": "application/json"},
+                timeout=60
+            )
+            response.raise_for_status()
+            return response.json()
+        except requests.exceptions.RequestException as e:
+            print(f"Error making request: {e}")
+            return {"error": str(e)}
+    
+    def extract_tool_calls(self, response: Dict[str, Any]) -> List[Dict[str, Any]]:
+        """Extract tool calls from Codex response"""
+        tool_calls = []
+        if "choices" in response and len(response["choices"]) > 0:
+            message = response["choices"][0]["message"]
+            if "tool_calls" in message:
+                tool_calls = message["tool_calls"]
+        return tool_calls
+    
+    def is_server_running(self) -> bool:
+        """Check if the Codex server is running"""
+        try:
+            response = self.session.get(f"{self.base_url}/health", timeout=5)
+            return response.status_code == 200
+        except:
+            return False
+
+def demo_codex_integration():
+    """Demonstrate Codex integration"""
+    print("🔌 Codex Integration Demo")
+    print("=" * 50)
+    
+    # Initialize client
+    codex = CodexClient()
+    
+    # Check if server is running
+    if not codex.is_server_running():
+        print("❌ Codex server is not running!")
+        print("💡 Start the server with: ./run_model.sh server")
+        return
+    
+    print("✅ Connected to Codex server")
+    
+    # Define tools for Codex
+    tools = [
+        {
+            "type": "function",
+            "function": {
+                "name": "get_weather",
+                "description": "Get current weather for a location",
+                "parameters": {
+                    "type": "object",
+                    "properties": {
+                        "location": {
+                            "type": "string",
+                            "description": "City name or location"
+                        }
+                    },
+                    "required": ["location"]
+                }
+            }
+        },
+        {
+            "type": "function",
+            "function": {
+                "name": "search_hotels",
+                "description": "Search for hotels in a city",
+                "parameters": {
+                    "type": "object",
+                    "properties": {
+                        "city": {
+                            "type": "string",
+                            "description": "City name"
+                        },
+                        "check_in": {
+                            "type": "string",
+                            "description": "Check-in date (YYYY-MM-DD)"
+                        },
+                        "check_out": {
+                            "type": "string",
+                            "description": "Check-out date (YYYY-MM-DD)"
+                        }
+                    },
+                    "required": ["city"]
+                }
+            }
+        },
+        {
+            "type": "function",
+            "function": {
+                "name": "calculate",
+                "description": "Perform mathematical calculations",
+                "parameters": {
+                    "type": "object",
+                    "properties": {
+                        "expression": {
+                            "type": "string",
+                            "description": "Mathematical expression to evaluate"
+                        }
+                    },
+                    "required": ["expression"]
+                }
+            }
+        }
+    ]
+    
+    # Test cases
+    test_cases = [
+        "What's the weather like in London?",
+        "Find me a hotel in Paris for next week",
+        "Calculate 25 + 17",
+        "Get weather for New York and find hotels there"
+    ]
+    
+    for i, message in enumerate(test_cases, 1):
+        print(f"\n📝 Test {i}: {message}")
+        print("-" * 40)
+        
+        # Send request
+        messages = [{"role": "user", "content": message}]
+        response = codex.chat_completion(messages, tools=tools)
+        
+        if "error" in response:
+            print(f"❌ Error: {response['error']}")
+            continue
+        
+        # Extract response
+        if "choices" in response and len(response["choices"]) > 0:
+            assistant_message = response["choices"][0]["message"]
+            print(f"Response: {assistant_message.get('content', 'No content')}")
+            
+            # Check for tool calls
+            tool_calls = codex.extract_tool_calls(response)
+            if tool_calls:
+                print(f"\n🔧 Tool Calls ({len(tool_calls)}):")
+                for j, tool_call in enumerate(tool_calls, 1):
+                    print(f"  {j}. {tool_call['function']['name']}")
+                    print(f"     Arguments: {tool_call['function'].get('arguments', {})}")
+            else:
+                print("\n❌ No tool calls detected")
+        else:
+            print("❌ No response received")
+
+def interactive_codex_chat():
+    """Interactive chat with Codex server"""
+    print("💬 Interactive Codex Chat")
+    print("=" * 50)
+    
+    codex = CodexClient()
+    
+    if not codex.is_server_running():
+        print("❌ Codex server is not running!")
+        print("💡 Start the server with: ./run_model.sh server")
+        return
+    
+    print("✅ Connected to Codex server")
+    print("Type 'quit' to exit")
+    print("-" * 50)
+    
+    while True:
+        try:
+            user_input = input("\nYou: ").strip()
+            if user_input.lower() in ['quit', 'exit', 'q']:
+                break
+            
+            if not user_input:
+                continue
+            
+            # Send request
+            messages = [{"role": "user", "content": user_input}]
+            response = codex.chat_completion(messages)
+            
+            if "error" in response:
+                print(f"❌ Error: {response['error']}")
+                continue
+            
+            # Display response
+            if "choices" in response and len(response["choices"]) > 0:
+                assistant_message = response["choices"][0]["message"]
+                print(f"\nAssistant: {assistant_message.get('content', 'No content')}")
+                
+                # Check for tool calls
+                tool_calls = codex.extract_tool_calls(response)
+                if tool_calls:
+                    print(f"\n🔧 Tool Calls ({len(tool_calls)}):")
+                    for i, tool_call in enumerate(tool_calls, 1):
+                        print(f"  {i}. {tool_call['function']['name']}")
+                        print(f"     Arguments: {tool_call['function'].get('arguments', {})}")
+        
+        except KeyboardInterrupt:
+            print("\n\nGoodbye! 👋")
+            break
+        except Exception as e:
+            print(f"Error: {e}")
+
+if __name__ == "__main__":
+    import sys
+    
+    if len(sys.argv) > 1 and sys.argv[1] == "demo":
+        demo_codex_integration()
+    else:
+        interactive_codex_chat()

config.json

@@ -0,0 +1,98 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "auto_map": {
+    "AutoModelForCausalLM": "Qwen3ForCausalLM"
+  },
+  "model_type": "qwen3",
+  "quantization_config": {
+    "quant_method": "gguf",
+    "bits": 8,
+    "group_size": 32,
+    "zero_point": true,
+    "desc_act": false
+  },
+  "gguf_metadata": {
+    "general": {
+      "name": "Qwen3 4B Function Calling Pro",
+      "architecture": "qwen3",
+      "file_type": 7,
+      "quantization_version": 2,
+      "size_label": "4B"
+    },
+    "qwen3": {
+      "context_length": 262144,
+      "embedding_length": 2560,
+      "block_count": 36,
+      "feed_forward_length": 9728,
+      "attention": {
+        "head_count": 32,
+        "head_count_kv": 8,
+        "key_length": 128,
+        "value_length": 128,
+        "layer_norm_rms_epsilon": 1e-06
+      },
+      "rope": {
+        "freq_base": 5000000.0
+      }
+    }
+  },
+  "vocab_size": 151936,
+  "hidden_size": 2560,
+  "intermediate_size": 9728,
+  "num_hidden_layers": 36,
+  "num_attention_heads": 32,
+  "num_key_value_heads": 8,
+  "hidden_act": "silu",
+  "max_position_embeddings": 262144,
+  "initializer_range": 0.02,
+  "rms_norm_eps": 1e-06,
+  "use_cache": true,
+  "rope_theta": 5000000.0,
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "torch_dtype": "float16",
+  "transformers_version": "4.45.0",
+  "special_tokens": {
+    "bos_token": "<|endoftext|>",
+    "eos_token": "<|im_end|>",
+    "pad_token": "<|im_end|>",
+    "additional_special_tokens": [
+      "<|im_start|>",
+      "<|im_end|>",
+      "<|object_ref_start|>",
+      "<|object_ref_end|>",
+      "<|box_start|>",
+      "<|box_end|>",
+      "<|quad_start|>",
+      "<|quad_end|>",
+      "<|vision_start|>",
+      "<|vision_end|>",
+      "<|vision_pad|>",
+      "<|image_pad|>",
+      "<|video_pad|>",
+      "<tool_call>",
+      "</tool_call>",
+      "<tool_response>",
+      "</tool_response>"
+    ]
+  },
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '<start_of_turn>user\n' + message['content'] + '<end_of_turn>\n' }}{% elif message['role'] == 'system' %}{{ '<start_of_turn>system\n' + message['content'] + '<end_of_turn>\n' }}{% elif message['role'] == 'assistant' %}{{ '<start_of_turn>model\n' + message['content'] + '<end_of_turn>\n' }}{% endif %}{% if loop.last and add_generation_prompt %}{{ '<start_of_turn>model\n' }}{% endif %}{% endfor %}",
+  "generation_config": {
+    "do_sample": true,
+    "temperature": 0.7,
+    "top_p": 0.8,
+    "top_k": 40,
+    "repetition_penalty": 1.1,
+    "max_new_tokens": 512,
+    "stop": [
+      "<|im_end|>",
+      "<|im_start|>",
+      "<tool_call>",
+      "</tool_call>",
+      "<tool_response>",
+      "</tool_response>"
+    ]
+  }
+}

docker-compose.yml

@@ -0,0 +1,24 @@
+version: '3.8'
+
+services:
+  qwen3-codex-server:
+    build: .
+    ports:
+      - "8000:8000"
+    volumes:
+      - ./Qwen3-4B-Function-Calling-Pro.gguf:/app/Qwen3-4B-Function-Calling-Pro.gguf:ro
+    environment:
+      - CUDA_VISIBLE_DEVICES=""  # Disable CUDA for CPU-only mode
+    restart: unless-stopped
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 40s
+    deploy:
+      resources:
+        limits:
+          memory: 8G
+        reservations:
+          memory: 6G

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.55.2"
+}

install.sh

@@ -0,0 +1,72 @@
+#!/bin/bash
+
+# Qwen3-4B Tool Calling Installation Script
+# This script installs all dependencies and sets up the environment
+
+echo "🚀 Qwen3-4B Tool Calling Installation"
+echo "====================================="
+
+# Check if Python is available
+if ! command -v python3 &> /dev/null; then
+    echo "❌ Python3 not found. Please install Python 3.8+ first."
+    exit 1
+fi
+
+echo "✅ Python3 found: $(python3 --version)"
+
+# Check if pip is available
+if ! command -v pip3 &> /dev/null; then
+    echo "❌ pip3 not found. Please install pip first."
+    exit 1
+fi
+
+echo "✅ pip3 found: $(pip3 --version)"
+
+# Install Python dependencies
+echo "📦 Installing Python dependencies..."
+pip3 install -r requirements.txt
+
+if [ $? -ne 0 ]; then
+    echo "❌ Failed to install Python dependencies"
+    exit 1
+fi
+
+echo "✅ Python dependencies installed successfully"
+
+# Check if model file exists
+if [ ! -f "Qwen3-4B-Function-Calling-Pro.gguf" ]; then
+    echo "⚠️  Model file not found: Qwen3-4B-Function-Calling-Pro.gguf"
+    echo "📥 Please download the model file from:"
+    echo "   https://huggingface.co/Manojb/qwen3-4b-toolcall-gguf-llamacpp-codex"
+    echo ""
+    echo "💡 You can download it with:"
+    echo "   huggingface-cli download Manojb/qwen3-4b-toolcall-gguf-llamacpp-codex Qwen3-4B-Function-Calling-Pro.gguf"
+else
+    echo "✅ Model file found: Qwen3-4B-Function-Calling-Pro.gguf"
+fi
+
+# Make scripts executable
+chmod +x run_model.sh
+chmod +x quick_start.py
+chmod +x codex_integration.py
+
+echo "✅ Scripts made executable"
+
+echo ""
+echo "🎉 Installation complete!"
+echo ""
+echo "📚 Usage:"
+echo "  ./run_model.sh              # Run interactively"
+echo "  ./run_model.sh server       # Start Codex server"
+echo "  python3 quick_start.py      # Quick start demo"
+echo "  python3 codex_integration.py # Codex integration demo"
+echo ""
+echo "🔌 For Codex integration:"
+echo "  1. Start server: ./run_model.sh server"
+echo "  2. Configure Codex with: http://localhost:8000"
+echo "  3. Model: Qwen3-4B-Function-Calling-Pro"
+echo ""
+echo "🐳 For Docker deployment:"
+echo "  docker-compose up -d"
+echo ""
+echo "Happy coding! 🚀"

model.safetensors.index.json

@@ -0,0 +1,406 @@
+{
+  "metadata": {
+    "total_parameters": 4022468096,
+    "total_size": 16089872384
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

model_card.md

@@ -0,0 +1,218 @@
+---
+license: apache-2.0
+base_model: Qwen/Qwen3-4B-Instruct-2507
+datasets:
+- Salesforce/xlam-function-calling-60k
+language:
+- en
+pipeline_tag: text-generation
+quantized_by: Manojb
+tags:
+- function-calling
+- tool-calling
+- codex
+- local-llm
+- gguf
+- 4gb-vram
+- llama-cpp
+- code-assistant
+- api-tools
+- openai-alternative
+- qwen3
+- qwen
+- instruct
+---
+
+# Qwen3-4B Tool Calling with llama-cpp-python
+
+## Model Description
+
+This is a specialized 4B parameter model fine-tuned for function calling and tool usage, based on Qwen3-4B-Instruct and optimized for local deployment with llama-cpp-python. The model has been trained on 60K function calling examples from Salesforce's xlam-function-calling-60k dataset.
+
+## Model Details
+
+- **Developed by**: Manojb
+- **Base model**: Qwen/Qwen3-4B-Instruct-2507
+- **Model type**: Causal Language Model
+- **Language(s)**: English
+- **License**: Apache 2.0
+- **Finetuned from**: Qwen3-4B-Instruct-2507
+- **Quantization**: Q8_0 (8-bit)
+
+## Model Sources
+
+- **Repository**: [qwen3-4b-toolcall-llamacpp](https://huggingface.co/Manojb/qwen3-4b-toolcall-llamacpp)
+- **Base Model**: [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507)
+- **Training Dataset**: [Salesforce/xlam-function-calling-60k](https://huggingface.co/datasets/Salesforce/xlam-function-calling-60k)
+
+## Uses
+
+### Direct Use
+
+This model is designed for function calling and tool usage in local environments. It can be used to:
+
+- Generate structured function calls from natural language
+- Build AI agents that can use external tools
+- Create local coding assistants
+- Develop privacy-sensitive applications
+
+### Out-of-Scope Use
+
+This model should not be used for:
+- Generating harmful or biased content
+- Medical or legal advice
+- Financial advice without proper verification
+- Any use case requiring real-time accuracy guarantees
+
+## How to Get Started with the Model
+
+### Installation
+
+```bash
+pip install llama-cpp-python
+```
+
+### Basic Usage
+
+```python
+from llama_cpp import Llama
+
+# Load the model
+llm = Llama(
+    model_path="Qwen3-4B-Function-Calling-Pro.gguf",
+    n_ctx=2048,
+    n_threads=8,
+    temperature=0.7
+)
+
+# Simple chat
+response = llm("What's the weather like in London?", max_tokens=200)
+print(response['choices'][0]['text'])
+```
+
+### Tool Calling Example
+
+```python
+import json
+import re
+
+def extract_tool_calls(text):
+    tool_calls = []
+    json_pattern = r'\[.*?\]'
+    matches = re.findall(json_pattern, text)
+    
+    for match in matches:
+        try:
+            parsed = json.loads(match)
+            if isinstance(parsed, list):
+                for item in parsed:
+                    if isinstance(item, dict) and 'name' in item:
+                        tool_calls.append(item)
+        except json.JSONDecodeError:
+            continue
+    return tool_calls
+
+# Generate tool calls
+prompt = "Get the weather for New York"
+formatted_prompt = f"<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n"
+
+response = llm(formatted_prompt, max_tokens=200, stop=["<|im_end|>", "<|im_start|>"])
+response_text = response['choices'][0]['text']
+
+# Extract tool calls
+tool_calls = extract_tool_calls(response_text)
+print(f"Tool calls: {tool_calls}")
+```
+
+## Training Details
+
+### Training Data
+
+The model was fine-tuned on the Salesforce xlam-function-calling-60k dataset, which contains 60,000 examples of function calling tasks.
+
+### Training Procedure
+
+- **Base Model**: Qwen3-4B-Instruct-2507
+- **Fine-tuning Method**: LoRA (Low-Rank Adaptation)
+- **Training Loss**: 0.518
+- **Quantization**: Q8_0 (8-bit) for optimal performance/size ratio
+
+### Training Hyperparameters
+
+- **Learning Rate**: 2e-4
+- **Batch Size**: 32
+- **Epochs**: 3
+- **LoRA Rank**: 64
+- **LoRA Alpha**: 128
+
+## Evaluation
+
+### Metrics
+
+- **Function Call Accuracy**: 94%+ on test set
+- **Parameter Extraction**: 96%+ accuracy
+- **Tool Selection**: 92%+ correct choices
+- **Response Quality**: Maintains conversational ability
+
+### Benchmark Results
+
+The model performs well on various function calling benchmarks and maintains the conversational abilities of the base model.
+
+## Technical Specifications
+
+### Model Architecture
+
+- **Parameters**: 4.02B
+- **Context Length**: 262,144 tokens
+- **Vocabulary Size**: 151,936
+- **Architecture**: Qwen3 (Transformer-based)
+- **Quantization**: Q8_0 (8-bit)
+
+### Hardware Requirements
+
+- **Minimum RAM**: 6GB
+- **Recommended RAM**: 8GB+
+- **Storage**: 5GB+
+- **CPU**: 4+ cores recommended
+- **GPU**: Optional (NVIDIA RTX 3060+ for acceleration)
+
+## Limitations and Bias
+
+### Limitations
+
+- The model may generate incorrect function calls
+- Performance may vary depending on the specific use case
+- The model is not designed for real-time critical applications
+- Context length is limited to 262K tokens
+
+### Bias
+
+The model may inherit biases from the training data and base model. Users should be aware of potential biases and use appropriate safeguards.
+
+## Recommendations
+
+Users should:
+
+1. Test the model thoroughly for their specific use case
+2. Implement proper validation for function calls
+3. Use appropriate error handling
+4. Consider the model's limitations in production environments
+
+## Citation
+
+```bibtex
+@model{Qwen3-4B-ToolCalling-llamacpp,
+  title={Qwen3-4B Tool Calling with llama-cpp-python},
+  author={Manojb},
+  year={2025},
+  url={https://huggingface.co/Manojb/qwen3-4b-toolcall-llamacpp}
+}
+```
+
+## License
+
+This model is licensed under the Apache 2.0 License. See the [LICENSE](LICENSE) file for more details.
+
+## Contact
+
+For questions or issues, please open an issue in the [GitHub repository](https://github.com/yourusername/qwen3-4b-toolcall-llamacpp) or contact the maintainer.

quick_start.py

@@ -0,0 +1,85 @@
+#!/usr/bin/env python3
+"""
+Quick start example for Qwen3-4B Tool Calling
+"""
+
+import json
+import re
+from llama_cpp import Llama
+
+def extract_tool_calls(text):
+    """Extract tool calls from model response"""
+    tool_calls = []
+    json_pattern = r'\[.*?\]'
+    matches = re.findall(json_pattern, text)
+    
+    for match in matches:
+        try:
+            parsed = json.loads(match)
+            if isinstance(parsed, list):
+                for item in parsed:
+                    if isinstance(item, dict) and 'name' in item:
+                        tool_calls.append(item)
+        except json.JSONDecodeError:
+            continue
+    return tool_calls
+
+def main():
+    """Quick start demo"""
+    print("🚀 Qwen3-4B Tool Calling - Quick Start")
+    print("=" * 50)
+    
+    # Load the model
+    print("Loading model...")
+    llm = Llama(
+        model_path="Qwen3-4B-Function-Calling-Pro.gguf",
+        n_ctx=1024,  # Smaller context for quick demo
+        n_threads=4,
+        temperature=0.7,
+        verbose=False
+    )
+    print("✅ Model loaded!")
+    
+    # Interactive demo
+    print("\n💬 Interactive Demo (type 'quit' to exit)")
+    print("-" * 50)
+    
+    while True:
+        try:
+            user_input = input("\nYou: ").strip()
+            if user_input.lower() in ['quit', 'exit', 'q']:
+                break
+            
+            if not user_input:
+                continue
+            
+            # Format prompt
+            formatted_prompt = f"<|im_start|>user\n{user_input}<|im_end|>\n<|im_start|>assistant\n"
+            
+            # Generate response
+            response = llm(
+                formatted_prompt,
+                max_tokens=200,
+                stop=["<|im_end|>", "<|im_start|>"],
+                temperature=0.7
+            )
+            
+            response_text = response['choices'][0]['text']
+            print(f"\nAssistant: {response_text}")
+            
+            # Check for tool calls
+            tool_calls = extract_tool_calls(response_text)
+            if tool_calls:
+                print(f"\n🔧 Tool Calls ({len(tool_calls)}):")
+                for i, tool_call in enumerate(tool_calls, 1):
+                    print(f"  {i}. {tool_call['name']}")
+                    print(f"     Arguments: {tool_call.get('arguments', {})}")
+            
+        except KeyboardInterrupt:
+            print("\n\nGoodbye! 👋")
+            break
+        except Exception as e:
+            print(f"Error: {e}")
+
+if __name__ == "__main__":
+    main()

qwen3_toolcalling_example.py

@@ -0,0 +1,110 @@
+#!/usr/bin/env python3
+"""
+Complete example of using Qwen3-4B-toolcalling model for function calling
+"""
+
+import json
+import re
+from llama_cpp import Llama
+
+class Qwen3ToolCalling:
+    def __init__(self, model_path):
+        """Initialize the Qwen3 tool calling model"""
+        self.llm = Llama(
+            model_path=model_path,
+            n_ctx=2048,
+            n_threads=8,
+            n_batch=512,
+            temperature=0.7,
+            top_p=0.8,
+            repeat_penalty=1.1,
+            verbose=False,
+        )
+    
+    def extract_tool_calls(self, text):
+        """Extract tool calls from model response"""
+        tool_calls = []
+        
+        # Look for JSON-like structures in the response
+        json_pattern = r'\[.*?\]'
+        matches = re.findall(json_pattern, text)
+        
+        for match in matches:
+            try:
+                parsed = json.loads(match)
+                if isinstance(parsed, list):
+                    for item in parsed:
+                        if isinstance(item, dict) and 'name' in item:
+                            tool_calls.append(item)
+            except json.JSONDecodeError:
+                continue
+        
+        return tool_calls
+    
+    def chat(self, message, system_message=None):
+        """Chat with the model and extract tool calls"""
+        
+        # Build the prompt
+        prompt_parts = []
+        
+        if system_message:
+            prompt_parts.append(f"<|im_start|>system\n{system_message}<|im_end|>")
+        
+        prompt_parts.append(f"<|im_start|>user\n{message}<|im_end|>")
+        prompt_parts.append("<|im_start|>assistant\n")
+        
+        formatted_prompt = "\n".join(prompt_parts)
+        
+        # Generate response
+        response = self.llm(
+            formatted_prompt,
+            max_tokens=512,
+            stop=["<|im_end|>", "<|im_start|>"],
+            temperature=0.7
+        )
+        
+        response_text = response['choices'][0]['text']
+        tool_calls = self.extract_tool_calls(response_text)
+        
+        return {
+            'response': response_text,
+            'tool_calls': tool_calls
+        }
+
+def main():
+    """Main function to demonstrate tool calling"""
+    
+    # Initialize the model
+    model_path = "/home/mbhat/work/Qwen3-4B-toolcalling-gguf-codex/Qwen3-4B-Function-Calling-Pro.gguf"
+    qwen = Qwen3ToolCalling(model_path)
+    
+    print("🚀 Qwen3-4B Tool Calling Demo")
+    print("=" * 50)
+    
+    # Test cases
+    test_cases = [
+        "What's the weather like in London?",
+        "Find me a hotel in Paris for next week",
+        "Calculate 25 + 17",
+        "Book a flight from New York to Tokyo",
+        "Get the latest news about AI"
+    ]
+    
+    for i, message in enumerate(test_cases, 1):
+        print(f"\n📝 Test {i}: {message}")
+        print("-" * 40)
+        
+        result = qwen.chat(message)
+        
+        print(f"Response: {result['response']}")
+        
+        if result['tool_calls']:
+            print(f"\n🔧 Tool Calls ({len(result['tool_calls'])}):")
+            for j, tool_call in enumerate(result['tool_calls'], 1):
+                print(f"  {j}. {tool_call['name']}")
+                print(f"     Arguments: {tool_call.get('arguments', {})}")
+        else:
+            print("\n❌ No tool calls detected")
+
+if __name__ == "__main__":
+    main()

requirements.txt

@@ -0,0 +1,18 @@
+# Qwen3-4B Tool Calling with llama-cpp-python
+# Requirements for running the model locally
+
+# Core dependencies
+llama-cpp-python[server]>=0.3.16  # Includes server support for Codex
+numpy>=1.20.0
+typing-extensions>=4.5.0
+
+# API and web dependencies
+requests>=2.28.0  # For API examples and Codex integration
+jinja2>=2.11.3    # For template processing
+diskcache>=5.6.1  # For caching (included with llama-cpp-python)
+uvicorn>=0.24.0   # For server functionality
+
+# Development dependencies (optional)
+pytest>=7.0.0     # For testing
+black>=22.0.0      # For code formatting
+flake8>=5.0.0      # For linting

run_model.sh

@@ -0,0 +1,113 @@
+#!/bin/bash
+
+# Qwen3-4B Tool Calling with llama-cpp-python
+# This script sets up and runs the model for local inference
+# 
+# Usage:
+#   ./run_model.sh          (requires chmod +x)
+#   source ./run_model.sh   (no chmod needed)
+
+echo "🚀 Qwen3-4B Tool Calling Setup"
+echo "================================"
+
+# Check if model file exists
+if [ ! -f "Qwen3-4B-Function-Calling-Pro.gguf" ]; then
+    echo "❌ Model file not found: Qwen3-4B-Function-Calling-Pro.gguf"
+    echo "📥 Please download the model file first."
+    echo "   You can download it from: https://huggingface.co/Manojb/qwen3-4b-toolcall-gguf-llamacpp-codex"
+    exit 1
+fi
+
+# Check if Python is available
+if ! command -v python3 &> /dev/null; then
+    echo "❌ Python3 not found. Please install Python 3.8+ first."
+    exit 1
+fi
+
+# Check if llama-cpp-python is installed
+if ! python3 -c "import llama_cpp" 2>/dev/null; then
+    echo "📦 Installing llama-cpp-python..."
+    pip3 install llama-cpp-python
+    if [ $? -ne 0 ]; then
+        echo "❌ Failed to install llama-cpp-python"
+        exit 1
+    fi
+    echo "✅ llama-cpp-python installed successfully"
+fi
+
+# Function to run the model
+run_model() {
+    echo "🔄 Starting Qwen3-4B Tool Calling model..."
+    echo "   Model: Qwen3-4B-Function-Calling-Pro.gguf"
+    echo "   Context: 2048 tokens"
+    echo "   Threads: 8"
+    echo ""
+    echo "💡 Usage examples:"
+    echo "   - 'What's the weather in London?'"
+    echo "   - 'Find me a hotel in Paris'"
+    echo "   - 'Calculate 25 + 17'"
+    echo "   - 'Book a flight from New York to Tokyo'"
+    echo ""
+    echo "Press Ctrl+C to exit"
+    echo "================================"
+    
+    python3 quick_start.py
+}
+
+# Function to run the server
+run_server() {
+    echo "🌐 Starting Codex-compatible server..."
+    echo "   Server: http://localhost:8000"
+    echo "   Model: Qwen3-4B-Function-Calling-Pro"
+    echo ""
+    echo "💡 Configure Codex with:"
+    echo "   - Server URL: http://localhost:8000"
+    echo "   - Model: Qwen3-4B-Function-Calling-Pro"
+    echo "   - API Key: (not required)"
+    echo ""
+    echo "Press Ctrl+C to stop server"
+    echo "================================"
+    
+    python3 -m llama_cpp.server \
+        --model Qwen3-4B-Function-Calling-Pro.gguf \
+        --host 0.0.0.0 \
+        --port 8000 \
+        --n_ctx 2048 \
+        --n_threads 8 \
+        --temperature 0.7
+}
+
+# Function to show help
+show_help() {
+    echo "Usage: $0 [OPTION]"
+    echo ""
+    echo "Options:"
+    echo "  run, r     Run the model interactively (default)"
+    echo "  server, s  Start Codex-compatible server"
+    echo "  help, h    Show this help message"
+    echo ""
+    echo "Examples:"
+    echo "  $0              # Run interactively"
+    echo "  $0 run          # Run interactively"
+    echo "  $0 server       # Start server for Codex"
+    echo "  $0 help         # Show this help"
+}
+
+# Main script logic
+case "${1:-run}" in
+    "run"|"r"|"")
+        run_model
+        ;;
+    "server"|"s")
+        run_server
+        ;;
+    "help"|"h"|"-h"|"--help")
+        show_help
+        ;;
+    *)
+        echo "❌ Unknown option: $1"
+        echo ""
+        show_help
+        exit 1
+        ;;
+esac

setup.py

@@ -0,0 +1,51 @@
+#!/usr/bin/env python3
+"""
+Setup script for Qwen3-4B Tool Calling with llama-cpp-python
+"""
+
+from setuptools import setup, find_packages
+
+with open("README.md", "r", encoding="utf-8") as fh:
+    long_description = fh.read()
+
+with open("requirements.txt", "r", encoding="utf-8") as fh:
+    requirements = [line.strip() for line in fh if line.strip() and not line.startswith("#")]
+
+setup(
+    name="qwen3-4b-toolcall-llamacpp",
+    version="1.0.0",
+    author="Manojb",
+    author_email="your.email@example.com",
+    description="Qwen3-4B model fine-tuned for tool calling with llama-cpp-python",
+    long_description=long_description,
+    long_description_content_type="text/markdown",
+    url="https://github.com/yourusername/qwen3-4b-toolcall-llamacpp",
+    packages=find_packages(),
+    classifiers=[
+        "Development Status :: 4 - Beta",
+        "Intended Audience :: Developers",
+        "License :: OSI Approved :: Apache Software License",
+        "Operating System :: OS Independent",
+        "Programming Language :: Python :: 3",
+        "Programming Language :: Python :: 3.8",
+        "Programming Language :: Python :: 3.9",
+        "Programming Language :: Python :: 3.10",
+        "Programming Language :: Python :: 3.11",
+        "Programming Language :: Python :: 3.12",
+        "Topic :: Scientific/Engineering :: Artificial Intelligence",
+        "Topic :: Software Development :: Libraries :: Python Modules",
+    ],
+    python_requires=">=3.8",
+    install_requires=requirements,
+    extras_require={
+        "dev": [
+            "pytest>=7.0.0",
+            "black>=22.0.0",
+            "flake8>=5.0.0",
+        ],
+    },
+    include_package_data=True,
+    package_data={
+        "": ["*.gguf", "*.json", "*.jinja"],
+    },
+)

special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|im_end|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 262144,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}