Update README.md
Browse files
README.md
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
---
|
| 2 |
-
license:
|
| 3 |
library_name: onnx
|
| 4 |
tags:
|
| 5 |
- chess
|
|
@@ -10,23 +10,23 @@ tags:
|
|
| 10 |
- game-ai
|
| 11 |
- basic model
|
| 12 |
datasets:
|
| 13 |
-
-
|
| 14 |
language:
|
| 15 |
- en
|
| 16 |
pipeline_tag: reinforcement-learning
|
| 17 |
---
|
| 18 |
|
| 19 |
-
# ♟️
|
| 20 |
|
| 21 |
<div align="center">
|
| 22 |
|
| 23 |
-
](https://creativecommons.org/licenses/by-nc/4.0/)
|
| 26 |

|
| 27 |

|
| 28 |
|
| 29 |
-
[**Live Demo**](https://chessmate-engine.onrender.com) • [**GitHub Repository**](https://github.com/Rafsan1711/Chessmate-Engine)
|
| 30 |
|
| 31 |
</div>
|
| 32 |
|
|
@@ -34,7 +34,7 @@ pipeline_tag: reinforcement-learning
|
|
| 34 |
|
| 35 |
This is a **Convolutional Neural Network (CNN)** trained to evaluate chess positions. It takes a board state as input and outputs a scalar evaluation score between `-1` (Black winning) and `+1` (White winning).
|
| 36 |
|
| 37 |
-
It is the core "brain" of the **
|
| 38 |
|
| 39 |
- **Architecture:** 3-Layer CNN with Batch Normalization and ReLU activation.
|
| 40 |
- **Framework:** Trained in PyTorch, exported to ONNX (Opset 14).
|
|
@@ -91,14 +91,7 @@ console.log(`Position Score: ${evaluation}`);
|
|
| 91 |
|
| 92 |
## ⚠️ License & Limitations
|
| 93 |
|
| 94 |
-
This model is licensed under **
|
| 95 |
-
|
| 96 |
-
**You are free to:**
|
| 97 |
-
- Use this model for research, education, and personal projects.
|
| 98 |
-
- Modify and adapt the model.
|
| 99 |
-
|
| 100 |
-
**You may NOT:**
|
| 101 |
-
- Sell this model or use it in a commercial product without permission.
|
| 102 |
|
| 103 |
---
|
| 104 |
|
|
|
|
| 1 |
---
|
| 2 |
+
license: gpl-3.0
|
| 3 |
library_name: onnx
|
| 4 |
tags:
|
| 5 |
- chess
|
|
|
|
| 10 |
- game-ai
|
| 11 |
- basic model
|
| 12 |
datasets:
|
| 13 |
+
- GambitFlow/Starter-Data
|
| 14 |
language:
|
| 15 |
- en
|
| 16 |
pipeline_tag: reinforcement-learning
|
| 17 |
---
|
| 18 |
|
| 19 |
+
# ♟️ Nexus-Nano - CNN Evaluation Model
|
| 20 |
|
| 21 |
<div align="center">
|
| 22 |
|
| 23 |
+

|
| 24 |
+
|
| 25 |
+
[](https://www.gnu.org/licenses/gpl-3.0)
|
| 26 |
|
|
|
|
| 27 |

|
| 28 |

|
| 29 |
|
|
|
|
| 30 |
|
| 31 |
</div>
|
| 32 |
|
|
|
|
| 34 |
|
| 35 |
This is a **Convolutional Neural Network (CNN)** trained to evaluate chess positions. It takes a board state as input and outputs a scalar evaluation score between `-1` (Black winning) and `+1` (White winning).
|
| 36 |
|
| 37 |
+
It is the core "brain" of the **Nexus-Nano** project, designed to run efficiently in web browsers using `onnxruntime-web`.
|
| 38 |
|
| 39 |
- **Architecture:** 3-Layer CNN with Batch Normalization and ReLU activation.
|
| 40 |
- **Framework:** Trained in PyTorch, exported to ONNX (Opset 14).
|
|
|
|
| 91 |
|
| 92 |
## ⚠️ License & Limitations
|
| 93 |
|
| 94 |
+
This model is licensed under **GPL v3 (GNU General Public License Version 3)**
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 95 |
|
| 96 |
---
|
| 97 |
|