---
language:
- en
license: apache-2.0
tags:
- code
- python
- lora
- qwen
- fine-tuned
- code-generation
base_model: Qwen/Qwen2.5-Coder-0.5B-Instruct
---

<div align="center">

# 🔥 Pyroton

> A lightweight Python code generation model fine-tuned from Qwen2.5-Coder-0.5B-Instruct.

![Python](https://img.shields.io/badge/Python-3.12-blue?logo=python)
![License](https://img.shields.io/badge/License-Apache%202.0-green)
![Status](https://img.shields.io/badge/Status-Active-brightgreen)
![Downloads](https://img.shields.io/badge/Downloads-1.6k%2B-purple)

</div>

---

## Overview

**Pyroton** is a lightweight Python-focused code generation model fine-tuned from [Qwen/Qwen2.5-Coder-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-0.5B-Instruct) using supervised fine-tuning (SFT) on Python instruction-style datasets.

The goal is to create a small, efficient model that handles easy to medium Python tasks while remaining practical for free-tier GPUs and lightweight deployment including mobile phones.

---

## Model Variants

### Base adapter
- **[shohuu/pyroton](https://huggingface.co/shohuu/pyroton)** — general Python instruction-tuned adapter

### Prime-fix patched adapter
- **[shohuu/pyroton-primefix-v3](https://huggingface.co/shohuu/pyroton-primefix-v3)** — targeted repair finetuning for correctness bugs (recommended)

---

## Quick Start

### Load latest patched adapter (recommended)

```python
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

base = AutoModelForCausalLM.from_pretrained(
    "Qwen/Qwen2.5-Coder-0.5B-Instruct",
    dtype=torch.bfloat16,
    device_map="auto",
)

model = PeftModel.from_pretrained(base, "shohuu/pyroton-primefix-v3")
tokenizer = AutoTokenizer.from_pretrained("shohuu/pyroton-primefix-v3")
tokenizer.pad_token = tokenizer.eos_token

prompt = "### Instruction:\nWrite a Python function to reverse a string\n\n### Response:\n"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

outputs = model.generate(
    **inputs,
    max_new_tokens=220,
    do_sample=False,
    repetition_penalty=1.1,
)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))
```

### Run GGUF locally (Ollama / LM Studio / PocketPal)

```bash
# Download pyroton-q4.gguf from Files tab
# Then load in your preferred local LLM app
```

---

## Recommended Inference Settings

### Correctness mode (recommended)
Most reliable for code generation:

```python
outputs = model.generate(
    **inputs,
    max_new_tokens=220,
    do_sample=False,
    repetition_penalty=1.1,
)
```

### Sampled mode (more variety, less stable)

```python
outputs = model.generate(
    **inputs,
    max_new_tokens=220,
    do_sample=True,
    temperature=0.1,
    top_p=0.9,
    repetition_penalty=1.2,
)
```

---

## Example Output

**Prompt:**
```
Write a Python function to check if a number is prime
```

**Pyroton Output:**
```python
import math

def is_prime(n):
    """Check if the given integer n is prime."""
    if n <= 1:
        return False
    for i in range(2, int(math.sqrt(n)) + 1):
        if n % i == 0:
            return False
    return True
```

---

## Training Details

| Setting | Value |
|---|---|
| Base Model | Qwen2.5-Coder-0.5B-Instruct |
| Datasets | python_code_instructions_18k_alpaca, CodeAlpaca-20k, code_instructions_122k_alpaca_style |
| Total Samples | ~95,362 (Python-filtered) |
| Training Strategy | Chunked SFT (5 chunks) |
| LoRA Rank | 16 |
| LoRA Alpha | 32 |
| Batch Size | 2 |
| Gradient Accumulation | 8 |
| Learning Rate | 1e-4 |
| Precision | BFloat16 |
| Max Length | 512 |
| Final Training Loss | ~0.712 |

### Repair finetuning
After main training, targeted repair finetuning was applied to fix:
- Missing `import math` / `math.sqrt` issues
- Incorrect handling of edge cases (negative numbers, 0, 1)
- Latest patched adapter: `shohuu/pyroton-primefix-v3`

### Evaluation
Tested against execution-based harness on `is_prime()` with inputs: `-1, 0, 1, 2, 3, 4, 6, 9, 17, 49`
- **Greedy decoding:** 5/5 passing ✅
- **Sampled decoding:** improved but less stable

---

## GGUF / Mobile Deployment

Pyroton is available as a GGUF file for local deployment:

| File | Quantization | Size |
|---|---|---|
| `pyroton-q4.gguf` | Q4_K_M | ~397MB |

Compatible apps:
- **PocketPal AI** (Android/iOS) — search `shohuu/Pyroton`
- **LM Studio** (Desktop)
- **Ollama** (Desktop)

---

## Known Limitations

- 0.5B model — can degrade on harder tasks or complex reasoning
- Greedy decoding is more reliable than sampling for correctness
- Most thoroughly tested on short Python coding tasks
- Broader evaluation across more libraries still needed

---

## GitHub

[github.com/TunasTuna/pyroton](https://github.com/TunasTuna/pyroton)

---

## Requirements

```
transformers
datasets
trl
peft
bitsandbytes
accelerate
torchao
```

---

## License

Apache 2.0 — see [LICENSE](https://github.com/TunasTuna/pyroton/blob/main/LICENSE) for details.

Base model (Qwen2.5-Coder) is also Apache 2.0. Attribution to Alibaba Cloud / Qwen Team.

---

## Acknowledgements

- [Qwen Team](https://huggingface.co/Qwen) for the base model
- [iamtarun](https://huggingface.co/datasets/iamtarun/python_code_instructions_18k_alpaca) for the original dataset
- [Hugging Face](https://huggingface.co/) for the training ecosystem
- My friend [Yumi](https://www.tiktok.com/@yumi_naomi6?_r=1&_t=ZS-96ok4qcUKij) for the name 🔥