Update README.md
#2
by
tmickleydoyle
- opened
README.md
CHANGED
|
@@ -4,4 +4,25 @@ datasets:
|
|
| 4 |
license: apache-2.0
|
| 5 |
---
|
| 6 |
|
| 7 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
license: apache-2.0
|
| 5 |
---
|
| 6 |
|
| 7 |
+

|
| 8 |
+
|
| 9 |
+
# Edit Prediction: Fine-Tuned from Qwen2.5-Coder-7B
|
| 10 |
+
|
| 11 |
+
This repository contains a fine-tuned version of **Qwen2.5-Coder-7B** to support [edit prediction](https://zed.dev/edit-prediction) in Zed.
|
| 12 |
+
|
| 13 |
+
## Training Details
|
| 14 |
+
|
| 15 |
+
The model has been fine-tuned using the [zeta dataset](https://huggingface.co/datasets/zed-industries/zeta). If you want to fine-tune the model yourself, you can refer to the following scripts:
|
| 16 |
+
|
| 17 |
+
- **DPO Fine-Tuning**: [View Notebook](https://huggingface.co/datasets/zed-industries/zeta/blob/main/script/dpo.ipynb)
|
| 18 |
+
- **SFT Fine-Tuning**: [View Notebook](https://huggingface.co/datasets/zed-industries/zeta/blob/main/script/sft.ipynb)
|
| 19 |
+
|
| 20 |
+
## Dataset
|
| 21 |
+
|
| 22 |
+
The dataset used for training is available at:
|
| 23 |
+
[zed-industries/zeta](https://huggingface.co/datasets/zed-industries/zeta)
|
| 24 |
+
|
| 25 |
+
## Learn More
|
| 26 |
+
|
| 27 |
+
For more insights about the model and its integration in Zed, check out the official blog post:
|
| 28 |
+
[Zed Blog - Edit Prediction](https://zed-k1xdvw833-zed-industries.vercel.app/blog/edit-prediction)
|