Upload folder using huggingface_hub
Browse files
README.md
CHANGED
|
@@ -115,6 +115,7 @@ is 5 MB of text that none of the models trained on.
|
|
| 115 |
## More
|
| 116 |
|
| 117 |
- Article: [Can a model learn its own tokenizer?](https://claude.ai/artifact/AamTLQSJGp6uYueALTKjtm)
|
|
|
|
| 118 |
- Training data: [ShadeEngine/fineweb-edu-bytes-10BT](https://huggingface.co/datasets/ShadeEngine/fineweb-edu-bytes-10BT)
|
| 119 |
and [ShadeEngine/fineweb-edu-bpe32k-10BT](https://huggingface.co/datasets/ShadeEngine/fineweb-edu-bpe32k-10BT)
|
| 120 |
- The experiment follows Cartesia's
|
|
|
|
| 115 |
## More
|
| 116 |
|
| 117 |
- Article: [Can a model learn its own tokenizer?](https://claude.ai/artifact/AamTLQSJGp6uYueALTKjtm)
|
| 118 |
+
- Training and evaluation code: [https://github.com/Ganryuu/bytegpt](https://github.com/Ganryuu/bytegpt)
|
| 119 |
- Training data: [ShadeEngine/fineweb-edu-bytes-10BT](https://huggingface.co/datasets/ShadeEngine/fineweb-edu-bytes-10BT)
|
| 120 |
and [ShadeEngine/fineweb-edu-bpe32k-10BT](https://huggingface.co/datasets/ShadeEngine/fineweb-edu-bpe32k-10BT)
|
| 121 |
- The experiment follows Cartesia's
|