GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
MRaviteja
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
MRaviteja
Model Tree
Qwen/Qwen2.5-3B-Instruct
Input Modalities
Output Modalities
Supported Functionality
| 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 |
Large language models frequently struggle with structured business data because real-world datasets are rarely clean.
Common failure modes include:
This project fine-tunes Qwen2.5-3B to improve reliability on these tasks while maintaining low inference latency.
Training data was generated to simulate real-world business datasets by introducing:
The objective was to improve robustness against inputs that commonly cause tool-calling failures.
Evaluation was performed on a held-out adversarial benchmark containing noisy business documents and malformed tabular schemas.
| Metric | Base Model | Fine-Tuned |
|---|---|---|
| Function-calling Schema Compliance | 81.2% | 99.6% |
| Reasoning / Output Failures | Baseline | 76% Reduction |
| Inference Latency | — | <3.2 s |
This model is designed for applications involving:
The model is trained to generate structured JSON-RPC calls for tools such as:
calculate_kpisgenerate_chartExample:
json
{"tool": "calculate_kpis","arguments": {"metrics": ["Revenue","Profit Margin","YoY Growth"]}}
python
from transformers import AutoTokenizer, AutoModelForCausalLMmodel_name = "MRaviteja/qwen2.5-3b-toolcalling"tokenizer = AutoTokenizer.from_pretrained(model_name)model = AutoModelForCausalLM.from_pretrained(model_name,device_map="auto")
This model was developed as the reasoning engine for an MCP-powered analytics platform.
It integrates directly with:
services/mcp_service.pyservices/tool_service.pyIf the fine-tuned weights are unavailable, the application gracefully falls back to an Ollama-hosted model without requiring changes to the surrounding tool pipeline.
markdown
config.jsongeneration_config.jsonmodel.safetensorstokenizer.jsontokenizer_config.jsonchat_template.jinjaREADME.md
Although optimized for structured tool calling, this model:
If you use this model in research or production, please cite this repository.
markdown
@misc{qwen-business-toolcalling,title={Qwen2.5-3B Business Tool Calling},author={Raviteja},year={2026},publisher={Hugging Face}}