Instructions to use MRaviteja/qwen2.5-3b-toolcalling with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MRaviteja/qwen2.5-3b-toolcalling with Transformers:

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

pipe = pipeline("text-generation", model="MRaviteja/qwen2.5-3b-toolcalling")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MRaviteja/qwen2.5-3b-toolcalling")
model = AutoModelForCausalLM.from_pretrained("MRaviteja/qwen2.5-3b-toolcalling", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

PEFT
How to use MRaviteja/qwen2.5-3b-toolcalling with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MRaviteja/qwen2.5-3b-toolcalling with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MRaviteja/qwen2.5-3b-toolcalling"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MRaviteja/qwen2.5-3b-toolcalling",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MRaviteja/qwen2.5-3b-toolcalling

SGLang

How to use MRaviteja/qwen2.5-3b-toolcalling with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "MRaviteja/qwen2.5-3b-toolcalling" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MRaviteja/qwen2.5-3b-toolcalling",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "MRaviteja/qwen2.5-3b-toolcalling" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MRaviteja/qwen2.5-3b-toolcalling",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MRaviteja/qwen2.5-3b-toolcalling with Docker Model Runner:
```
docker model run hf.co/MRaviteja/qwen2.5-3b-toolcalling
```

Qwen2.5-3B Business Tool-Calling

A fine-tuned version of Qwen2.5-3B-Instruct optimized for structured tool calling, business analytics, and robust reasoning over noisy real-world tabular data.

Unlike the base model, this version focuses on producing schema-valid JSON tool calls, handling inconsistent CSV structures, and performing multi-step KPI calculations with significantly higher reliability.

Highlights

🧠 Fine-tuned using Supervised Fine-Tuning (SFT) + QLoRA (PEFT)
📊 Optimized for business analytics workflows
🔧 Reliable JSON-RPC tool invocation
📁 Handles noisy and malformed CSV schemas
⚡ 4-bit quantized inference support
🤖 Designed for MCP (Model Context Protocol) tool integration

Model Details

Property	Value
Base Model	Qwen2.5-3B-Instruct
Fine-tuning	SFT + QLoRA
Framework	PyTorch
Libraries	Transformers, PEFT, TRL
Intended Use	Tool Calling, Business Analytics, KPI Reasoning
Quantization	4-bit inference supported

Motivation

Large language models frequently struggle with structured business data because real-world datasets are rarely clean.

Common failure modes include:

malformed JSON tool calls
incorrect function arguments
hallucinated fields
broken numerical reasoning
inability to adapt to inconsistent column names

This project fine-tunes Qwen2.5-3B to improve reliability on these tasks while maintaining low inference latency.

Training

Fine-tuning Method

Supervised Fine-Tuning (SFT)
QLoRA parameter-efficient adaptation
Hugging Face Transformers
PEFT
TRL
PyTorch

Synthetic Data Pipeline

Training data was generated to simulate real-world business datasets by introducing:

inconsistent column names
missing values
malformed schemas
noisy numerical data
adversarial table layouts
ambiguous KPI requests

The objective was to improve robustness against inputs that commonly cause tool-calling failures.

Evaluation

Evaluation was performed on a held-out adversarial benchmark containing noisy business documents and malformed tabular schemas.

Results

Metric	Base Model	Fine-Tuned
Function-calling Schema Compliance	81.2%	99.6%
Reasoning / Output Failures	Baseline	76% Reduction
Inference Latency	—	<3.2 s

Intended Use

This model is designed for applications involving:

Business Intelligence
KPI Calculation
Financial Reporting
Dashboard Generation
CSV Analysis
Structured Tool Calling
Agentic AI Workflows
MCP-based Systems

Tool Calling

The model is trained to generate structured JSON-RPC calls for tools such as:

calculate_kpis
generate_chart

Example:

{
  "tool": "calculate_kpis",
  "arguments": {
    "metrics": [
      "Revenue",
      "Profit Margin",
      "YoY Growth"
    ]
  }
}

Example

from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "MRaviteja/qwen2.5-3b-toolcalling"

tokenizer = AutoTokenizer.from_pretrained(model_name)

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    device_map="auto"
)

Integration

This model was developed as the reasoning engine for an MCP-powered analytics platform.

It integrates directly with:

services/mcp_service.py
services/tool_service.py

If the fine-tuned weights are unavailable, the application gracefully falls back to an Ollama-hosted model without requiring changes to the surrounding tool pipeline.

Repository Contents

config.json
generation_config.json
model.safetensors
tokenizer.json
tokenizer_config.json
chat_template.jinja
README.md

Limitations

Although optimized for structured tool calling, this model:

is not intended as a general-purpose reasoning benchmark
has primarily been evaluated on business analytics workflows
may require additional fine-tuning for domains outside structured enterprise data

Citation

If you use this model in research or production, please cite this repository.

@misc{qwen-business-toolcalling,
  title={Qwen2.5-3B Business Tool Calling},
  author={Raviteja},
  year={2026},
  publisher={Hugging Face}
}

Acknowledgements

Alibaba Qwen Team
Hugging Face Transformers
PEFT
TRL
PyTorch

Downloads last month: 18

Safetensors

Model size

3B params

Tensor type

BF16

Model tree for MRaviteja/qwen2.5-3b-toolcalling

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-3B-Instruct

Finetuned

(1477)

this model