---
license: apache-2.0

base_model: Qwen/Qwen2.5-3B-Instruct

library_name: peft

pipeline_tag: text-generation

language:
  - en

datasets:
  - iamtarun/python_code_instructions_18k_alpaca

tags:
  - qwen2
  - qwen
  - qlora
  - lora
  - peft
  - transformers
  - instruction-tuning
  - code-generation
  - python
  - fine-tuning

model-index:
  - name: CodeForge AI
    results:
      - task:
          type: text-generation
        metrics:
          - type: train_loss
            value: 0.7047
            name: Training Loss
---

# 🚀 CodeForge AI

> Fine-tuned Qwen2.5-3B-Instruct using QLoRA + PEFT for software engineering tasks.
# 🚀 CodeForge AI

> A QLoRA fine-tuned version of **Qwen2.5-3B-Instruct** for software engineering and Python coding tasks.

![License](https://img.shields.io/badge/License-Apache--2.0-blue)
![Model](https://img.shields.io/badge/Base%20Model-Qwen2.5--3B-green)
![Method](https://img.shields.io/badge/Fine--Tuning-QLoRA-orange)
![Framework](https://img.shields.io/badge/Framework-Transformers-red)

---

# 📖 Overview

CodeForge AI is a parameter-efficient fine-tuned (PEFT) Large Language Model built on **Qwen2.5-3B-Instruct**.

The objective of this project is to demonstrate a complete end-to-end modern LLM fine-tuning workflow using:

* QLoRA
* LoRA
* PEFT
* Hugging Face Transformers
* TRL SFTTrainer
* Google Colab Tesla T4

Instead of updating all **3.1 billion** parameters, only **0.96%** of the parameters were trained, making the project lightweight and GPU-efficient.

---

# 🏗 Base Model

**Model**

Qwen/Qwen2.5-3B-Instruct

---

# ⚡ Fine-Tuning Technique

* QLoRA (4-bit Quantization)
* LoRA (Low-Rank Adaptation)
* PEFT (Parameter Efficient Fine Tuning)
* Supervised Fine-Tuning (SFT)

---

# 📚 Dataset

Dataset used:

**iamtarun/python_code_instructions_18k_alpaca**

Dataset contains approximately **18,000** Python instruction-following examples.

For this proof-of-concept training run, a subset of the dataset was used.

---

# ⚙ Training Configuration

| Parameter             | Value               |
| --------------------- | ------------------- |
| Base Model            | Qwen2.5-3B-Instruct |
| Fine-Tuning           | QLoRA               |
| LoRA Rank (r)         | 16                  |
| Alpha                 | 32                  |
| Dropout               | 0.05                |
| Quantization          | 4-bit NF4           |
| Optimizer             | AdamW               |
| Learning Rate         | 2e-4                |
| Max Steps             | 100                 |
| Batch Size            | 2                   |
| Gradient Accumulation | 4                   |
| Max Sequence Length   | 512                 |
| GPU                   | Tesla T4 (16 GB)    |

---

# 📊 Training Results

Training completed successfully.

Final Training Loss:

```
0.7047
```

Trainable Parameters:

```
29,933,568
```

Total Parameters:

```
3,115,872,256
```

Percentage of Trainable Parameters:

```
0.9607%
```

---

# 🧠 Architecture

```
Python Instruction Dataset
            │
            ▼
      Tokenization
            │
            ▼
Qwen2.5-3B-Instruct
            │
            ▼
    4-bit Quantization
            │
            ▼
          QLoRA
            │
            ▼
      LoRA Adapters
            │
            ▼
     Supervised Fine-Tuning
            │
            ▼
     Fine-Tuned Adapter
            │
            ▼
      Hugging Face Hub
```

---

# 💻 Usage

```python
from transformers import AutoTokenizer
from peft import AutoPeftModelForCausalLM

model = AutoPeftModelForCausalLM.from_pretrained(
    "banty1614/codeforge-qwen-lora",
    device_map="auto"
)

tokenizer = AutoTokenizer.from_pretrained(
    "banty1614/codeforge-qwen-lora"
)
```

Example:

```python
messages = [
    {
        "role": "user",
        "content": "Write a Python function to reverse a linked list."
    }
]

text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
```

---

# 📈 Evaluation

The model was compared with the original base model on multiple Python programming prompts.

Evaluation included:

* Code correctness
* Explanation quality
* Readability
* Response formatting

This project demonstrates the complete QLoRA fine-tuning workflow rather than claiming to outperform the original Qwen model across all programming tasks.

---

# ⚠ Limitations

* Trained for only 100 optimization steps.
* Uses a subset of the original dataset.
* Intended as a proof-of-concept for parameter-efficient fine-tuning.
* Not evaluated on standardized coding benchmarks.

---

# 🚀 Future Work

* Train on the complete dataset.
* Increase training epochs.
* Add evaluation on HumanEval and MBPP.
* Expand training to FastAPI, SQL, Docker, Git, and System Design.
* Support multiple LoRA adapters for different software engineering domains.

---

# 🙏 Acknowledgements

* Alibaba Cloud for Qwen2.5
* Hugging Face
* TRL
* PEFT
* BitsAndBytes
* Google Colab

---

If you use this project for learning or research, please consider giving the repository a ⭐.