README.md

---
tags:
- autotrain
- text-generation-inference
- text-generation
library_name: transformers
base_model: Qwen/Qwen2.5-0.5B
widget:
  - messages:
      - role: user
        content: What is your favorite condiment?
license: apache-2.0
datasets:
- greengerong/leetcode
---

![BokantLM Logo](https://raw.githubusercontent.com/llaa33219/BokantLM-logo/refs/heads/main/New%20Project%20(7).png)

# BokantLM 0.1–0.5B

## BokantLM – "Small but Supreme in Its Domain"

BokantLM is **not** a general-purpose model that tries to do everything well.  
Instead, it is an **ultra-lightweight LLM** designed to focus on a single domain, delivering the **highest possible efficiency and performance** in that area.

---

## Overview

- **Model Name:** BokantLM 0.1–0.5B  
- **Base Model:** [Qwen2.5-0.5B](https://huggingface.co/Qwen/Qwen2.5-0.5B)  
- **Fine-tuning Dataset:** [`greengerong/leetcode`](https://huggingface.co/datasets/greengerong/leetcode)  

---

## Philosophy

While most LLMs aim for versatility by learning across many fields,  
BokantLM is built to **achieve top efficiency and performance within a specific domain**.

This **0.1–0.5B release** is specialized in **coding and algorithm problem solving**,  
with a particular focus on **LeetCode-style challenges**.

---

## The reason I created this model

I created this model based on the idea that **if I focus intensively on learning only Python** , even a **small model** could become **very good at Python programming.**

---

## Future Plans

- ✅ **Coding(Python)-specialized** model release (current version)  
- 🔄 Mathematics problem-solving specialized version  
- 🔄 Domain-specific ultra-lightweight models for **law, medicine, science**, etc.  
- 🔄 **Attempt** at applying large LLM knowledge distillation  

---