Update README.md
Browse files
README.md
CHANGED
|
@@ -14,50 +14,47 @@ datasets:
|
|
| 14 |
- greengerong/leetcode
|
| 15 |
---
|
| 16 |
|
| 17 |
-
.png)
|
| 18 |
|
| 19 |
+
# BokantLM 0.1β0.5B
|
| 20 |
|
| 21 |
+
## BokantLM β "Small but Supreme in Its Domain"
|
| 22 |
|
| 23 |
+
BokantLM is **not** a general-purpose model that tries to do everything well.
|
| 24 |
+
Instead, it is an **ultra-lightweight LLM** designed to focus on a single domain, delivering the **highest possible efficiency and performance** in that area.
|
| 25 |
|
| 26 |
---
|
| 27 |
|
| 28 |
+
## Overview
|
| 29 |
|
| 30 |
+
- **Model Name:** BokantLM 0.1β0.5B
|
| 31 |
+
- **Base Model:** [Qwen2.5-0.5B](https://huggingface.co/Qwen/Qwen2.5-0.5B)
|
| 32 |
+
- **Fine-tuning Dataset:** [`greengerong/leetcode`](https://huggingface.co/datasets/greengerong/leetcode)
|
| 33 |
|
| 34 |
---
|
| 35 |
|
| 36 |
+
## Philosophy
|
| 37 |
|
| 38 |
+
While most LLMs aim for versatility by learning across many fields,
|
| 39 |
+
BokantLM is built to **achieve top efficiency and performance within a specific domain**.
|
| 40 |
|
| 41 |
+
This **0.1β0.5B release** is specialized in **coding and algorithm problem solving**,
|
| 42 |
+
with a particular focus on **LeetCode-style challenges**.
|
| 43 |
|
| 44 |
---
|
| 45 |
|
| 46 |
+
## Future Plans
|
| 47 |
|
| 48 |
+
- β
**Coding-specialized** model release (current version)
|
| 49 |
+
- π Mathematics problem-solving specialized version
|
| 50 |
+
- π Domain-specific ultra-lightweight models for **law, medicine, science**, etc.
|
| 51 |
+
- π **Attempt** at applying large LLM knowledge distillation
|
| 52 |
|
| 53 |
---
|
| 54 |
|
| 55 |
+
## License
|
| 56 |
|
| 57 |
+
This repository and model are for research and non-commercial use only.
|
| 58 |
+
For commercial usage, please contact us separately.
|
| 59 |
|
| 60 |
---
|
|
|
|
|
|
|
|
|
|
|
|